diff --git a/.gitignore b/.gitignore
new file mode 100644
index 00000000..7eade253
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,5 @@
+*.pkl
+*.zip
+data/
+.ipynb_checkpoints
+
diff --git a/.gitingore b/.gitingore
deleted file mode 100644
index a42991c5..00000000
--- a/.gitingore
+++ /dev/null
@@ -1 +0,0 @@
-Untitled.ipynb
diff --git a/README.md b/README.md
index 39173656..59ac3300 100644
--- a/README.md
+++ b/README.md
@@ -1,11 +1,7 @@
-
+
--------------------------------------------------------------------------------
-
-
-
-
This repository provides tutorial code for deep learning researchers to learn [PyTorch](https://github.com/pytorch/pytorch). In the tutorial, most of the models were implemented with less than 30 lines of code. Before starting this tutorial, it is recommended to finish [Official Pytorch Tutorial](http://pytorch.org/tutorials/beginner/deep_learning_60min_blitz.html).
@@ -13,19 +9,27 @@ This repository provides tutorial code for deep learning researchers to learn [P
## Table of Contents
-* [PyTorch Basics](https://github.com/yunjey/pytorch-tutorial/tree/master/tutorials/00%20-%20PyTorch%20Basics/main.py)
-* [Linear Regression](https://github.com/yunjey/pytorch-tutorial/blob/master/tutorials/01%20-%20Linear%20Regression/main.py#L24-L31)
-* [Logistic Regression](https://github.com/yunjey/pytorch-tutorial/blob/master/tutorials/02%20-%20Logistic%20Regression/main.py#L35-L42)
-* [Feedforward Neural Network](https://github.com/yunjey/pytorch-tutorial/blob/master/tutorials/03%20-%20Feedforward%20Neural%20Network/main.py#L36-L47)
-* [Convolutional Neural Network](https://github.com/yunjey/pytorch-tutorial/blob/master/tutorials/04%20-%20Convolutional%20Neural%20Network/main.py#L33-L53)
-* [Deep Residual Network](https://github.com/yunjey/pytorch-tutorial/blob/master/tutorials/05%20-%20Deep%20Residual%20Network/main.py#L67-L103)
-* [Recurrent Neural Network](https://github.com/yunjey/pytorch-tutorial/blob/master/tutorials/06%20-%20Recurrent%20Neural%20Network/main.py#L38-L56)
-* [Bidirectional Recurrent Neural Network](https://github.com/yunjey/pytorch-tutorial/blob/master/tutorials/07%20-%20Bidirectional%20Recurrent%20Neural%20Network/main.py#L38-L57)
-* [Language Model (RNNLM)](https://github.com/yunjey/pytorch-tutorial/blob/master/tutorials/08%20-%20Language%20Model/main.py#L28-L53)
-* [Image Captioning (CNN-RNN)](https://github.com/yunjey/pytorch-tutorial/tree/master/tutorials/09%20-%20Image%20Captioning)
-* [Generative Adversarial Network](https://github.com/yunjey/pytorch-tutorial/blob/master/tutorials/10%20-%20Generative%20Adversarial%20Network/main.py#L25-L51)
-* [Deep Convolutional Generative Adversarial Network](https://github.com/yunjey/pytorch-tutorial/blob/master/tutorials/11%20-%20Deep%20Convolutional%20Generative%20Adversarial%20Network/main.py#L32-L50)
-* [Deep Q-Network and Q-learning (WIP)](https://github.com/yunjey/pytorch-tutorial/blob/master/tutorials/12%20-%20Deep%20Q%20Network/dqn13.py)
+#### 1. Basics
+* [PyTorch Basics](https://github.com/yunjey/pytorch-tutorial/tree/master/tutorials/01-basics/pytorch_basics/main.py)
+* [Linear Regression](https://github.com/yunjey/pytorch-tutorial/tree/master/tutorials/01-basics/linear_regression/main.py#L22-L23)
+* [Logistic Regression](https://github.com/yunjey/pytorch-tutorial/tree/master/tutorials/01-basics/logistic_regression/main.py#L33-L34)
+* [Feedforward Neural Network](https://github.com/yunjey/pytorch-tutorial/tree/master/tutorials/01-basics/feedforward_neural_network/main.py#L37-L49)
+
+#### 2. Intermediate
+* [Convolutional Neural Network](https://github.com/yunjey/pytorch-tutorial/tree/master/tutorials/02-intermediate/convolutional_neural_network/main.py#L35-L56)
+* [Deep Residual Network](https://github.com/yunjey/pytorch-tutorial/tree/master/tutorials/02-intermediate/deep_residual_network/main.py#L76-L113)
+* [Recurrent Neural Network](https://github.com/yunjey/pytorch-tutorial/tree/master/tutorials/02-intermediate/recurrent_neural_network/main.py#L39-L58)
+* [Bidirectional Recurrent Neural Network](https://github.com/yunjey/pytorch-tutorial/tree/master/tutorials/02-intermediate/bidirectional_recurrent_neural_network/main.py#L39-L58)
+* [Language Model (RNN-LM)](https://github.com/yunjey/pytorch-tutorial/tree/master/tutorials/02-intermediate/language_model/main.py#L30-L50)
+
+#### 3. Advanced
+* [Generative Adversarial Networks](https://github.com/yunjey/pytorch-tutorial/blob/master/tutorials/03-advanced/generative_adversarial_network/main.py#L41-L57)
+* [Variational Auto-Encoder](https://github.com/yunjey/pytorch-tutorial/blob/master/tutorials/03-advanced/variational_autoencoder/main.py#L38-L65)
+* [Neural Style Transfer](https://github.com/yunjey/pytorch-tutorial/tree/master/tutorials/03-advanced/neural_style_transfer)
+* [Image Captioning (CNN-RNN)](https://github.com/yunjey/pytorch-tutorial/tree/master/tutorials/03-advanced/image_captioning)
+
+#### 4. Utilities
+* [TensorBoard in PyTorch](https://github.com/yunjey/pytorch-tutorial/tree/master/tutorials/04-utils/tensorboard)
@@ -33,18 +37,16 @@ This repository provides tutorial code for deep learning researchers to learn [P
## Getting Started
```bash
$ git clone https://github.com/yunjey/pytorch-tutorial.git
-$ cd pytorch-tutorial/tutorials/project_path
-$ python main.py # cpu version
-$ python main-gpu.py # gpu version
+$ cd pytorch-tutorial/tutorials/PATH_TO_PROJECT
+$ python main.py
```
## Dependencies
-* [pytorch](http://pytorch.org)
-* [pytorch-vision](http://pytorch.org/)
+* [Python 2.7 or 3.5+](https://www.continuum.io/downloads)
+* [PyTorch 0.4.0+](http://pytorch.org/)
-
diff --git a/logo/README.md b/logo/README.md
deleted file mode 100644
index 5304bcf7..00000000
--- a/logo/README.md
+++ /dev/null
@@ -1 +0,0 @@
-create folder
diff --git a/logo/pytorch_logo_2018.svg b/logo/pytorch_logo_2018.svg
new file mode 100644
index 00000000..5e530003
--- /dev/null
+++ b/logo/pytorch_logo_2018.svg
@@ -0,0 +1,33 @@
+
+
+
diff --git a/tutorials/00 - PyTorch Basics/basics.ipynb b/tutorials/00 - PyTorch Basics/basics.ipynb
deleted file mode 100644
index 4024f112..00000000
--- a/tutorials/00 - PyTorch Basics/basics.ipynb
+++ /dev/null
@@ -1,397 +0,0 @@
-{
- "cells": [
- {
- "cell_type": "code",
- "execution_count": 19,
- "metadata": {
- "collapsed": true
- },
- "outputs": [],
- "source": [
- "import torch \n",
- "import torchvision\n",
- "import torch.nn as nn\n",
- "import torch.utils.data as data\n",
- "import numpy as np\n",
- "import torchvision.transforms as transforms\n",
- "import torchvision.datasets as dsets\n",
- "from torch.autograd import Variable"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## Simple Example"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 2,
- "metadata": {
- "collapsed": false
- },
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "\n",
- "-1.2532 -1.1120 0.9717\n",
- "-2.3617 0.1516 1.1280\n",
- "-2.1599 0.0828 -1.4305\n",
- " 0.5265 0.5020 -2.1852\n",
- "-0.9197 0.1772 -1.1378\n",
- "[torch.FloatTensor of size 5x3]\n",
- "\n"
- ]
- }
- ],
- "source": [
- "# random normal\n",
- "x = torch.randn(5, 3)\n",
- "print (x)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 3,
- "metadata": {
- "collapsed": false
- },
- "outputs": [],
- "source": [
- "# build a layer\n",
- "linear = nn.Linear(3, 2)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 4,
- "metadata": {
- "collapsed": false
- },
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Parameter containing:\n",
- " 0.3884 -0.3335 -0.5146\n",
- "-0.3692 0.1977 -0.4081\n",
- "[torch.FloatTensor of size 2x3]\n",
- "\n",
- "Parameter containing:\n",
- "-0.4826\n",
- "-0.0038\n",
- "[torch.FloatTensor of size 2]\n",
- "\n"
- ]
- }
- ],
- "source": [
- "# Sess weight and bias\n",
- "print (linear.weight)\n",
- "print (linear.bias)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 5,
- "metadata": {
- "collapsed": false
- },
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Variable containing:\n",
- "-1.0986 -0.1575\n",
- "-2.0311 0.4378\n",
- "-0.6131 1.3938\n",
- " 0.6790 0.7929\n",
- "-0.3134 0.8351\n",
- "[torch.FloatTensor of size 5x2]\n",
- "\n"
- ]
- }
- ],
- "source": [
- "# forward propagate\n",
- "y = linear(Variable(x))\n",
- "print (y)"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## Convert numpy array to torch tensor"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {
- "collapsed": false
- },
- "outputs": [],
- "source": [
- "# convert numpy array to tensor\n",
- "a = np.array([[1,2], [3,4]])\n",
- "b = torch.from_numpy(a)\n",
- "print (b)"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## Input pipeline"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "#### (1) Preprocessing"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 18,
- "metadata": {
- "collapsed": true
- },
- "outputs": [],
- "source": [
- "# Image Preprocessing \n",
- "transform = transforms.Compose([\n",
- " transforms.Scale(40),\n",
- " transforms.RandomHorizontalFlip(),\n",
- " transforms.RandomCrop(32),\n",
- " transforms.ToTensor()])"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### (2) Define Dataset"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 14,
- "metadata": {
- "collapsed": false
- },
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Files already downloaded and verified\n",
- "torch.Size([3, 32, 32])\n",
- "6\n"
- ]
- }
- ],
- "source": [
- "# download and loading dataset f\n",
- "train_dataset = dsets.CIFAR10(root='./data/',\n",
- " train=True, \n",
- " transform=transform,\n",
- " download=True)\n",
- "\n",
- "image, label = train_dataset[0]\n",
- "print (image.size())\n",
- "print (label)"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### (3) Data Loader"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 16,
- "metadata": {
- "collapsed": true
- },
- "outputs": [],
- "source": [
- "# data loader provides queue and thread in a very simple way\n",
- "train_loader = data.DataLoader(dataset=train_dataset,\n",
- " batch_size=100, \n",
- " shuffle=True,\n",
- " num_workers=2)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {
- "collapsed": true
- },
- "outputs": [],
- "source": [
- "# iteration start then queue and thread start\n",
- "data_iter = iter(train_loader)\n",
- "\n",
- "# mini-batch images and labels\n",
- "images, labels = data_iter.next()\n",
- "\n",
- "for images, labels in train_loader:\n",
- " # your training code will be written here\n",
- " pass"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### (4) What about custom dataset not cifar10?"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 25,
- "metadata": {
- "collapsed": false
- },
- "outputs": [],
- "source": [
- "class CustomDataset(data.Dataset):\n",
- " def __init__(self):\n",
- " pass\n",
- " def __getitem__(self, index):\n",
- " # You should build this function to return one data for given index\n",
- " pass\n",
- " def __len__(self):\n",
- " pass"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 26,
- "metadata": {
- "collapsed": false
- },
- "outputs": [
- {
- "ename": "TypeError",
- "evalue": "'NoneType' object cannot be interpreted as an integer",
- "output_type": "error",
- "traceback": [
- "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
- "\u001b[0;31mTypeError\u001b[0m Traceback (most recent call last)",
- "\u001b[0;32m\u001b[0m in \u001b[0;36m\u001b[0;34m()\u001b[0m\n\u001b[1;32m 3\u001b[0m \u001b[0mbatch_size\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m100\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 4\u001b[0m \u001b[0mshuffle\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mTrue\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 5\u001b[0;31m num_workers=2)\n\u001b[0m",
- "\u001b[0;32m/home/yunjey/anaconda3/lib/python3.5/site-packages/torch/utils/data/dataloader.py\u001b[0m in \u001b[0;36m__init__\u001b[0;34m(self, dataset, batch_size, shuffle, sampler, num_workers, collate_fn, pin_memory)\u001b[0m\n\u001b[1;32m 250\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msampler\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0msampler\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 251\u001b[0m \u001b[0;32melif\u001b[0m \u001b[0mshuffle\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 252\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msampler\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mRandomSampler\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdataset\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 253\u001b[0m \u001b[0;32melif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mshuffle\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 254\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msampler\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mSequentialSampler\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdataset\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
- "\u001b[0;32m/home/yunjey/anaconda3/lib/python3.5/site-packages/torch/utils/data/sampler.py\u001b[0m in \u001b[0;36m__init__\u001b[0;34m(self, data_source)\u001b[0m\n\u001b[1;32m 45\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 46\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0m__init__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdata_source\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 47\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mnum_samples\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdata_source\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 48\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 49\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0m__iter__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
- "\u001b[0;31mTypeError\u001b[0m: 'NoneType' object cannot be interpreted as an integer"
- ]
- }
- ],
- "source": [
- "custom_dataset = CustomDataset()\n",
- "data.DataLoader(dataset=custom_dataset,\n",
- " batch_size=100, \n",
- " shuffle=True,\n",
- " num_workers=2)"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## Using Pretrained Model"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 17,
- "metadata": {
- "collapsed": false
- },
- "outputs": [
- {
- "name": "stderr",
- "output_type": "stream",
- "text": [
- "Downloading: \"https://s3.amazonaws.com/pytorch/models/resnet18-5c106cde.pth\" to /home/yunjey/.torch/models/resnet18-5c106cde.pth\n",
- "100%|██████████| 46827520/46827520 [07:48<00:00, 99907.53it/s] \n"
- ]
- }
- ],
- "source": [
- "# Download and load pretrained model\n",
- "resnet = torchvision.models.resnet18(pretrained=True)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {
- "collapsed": true
- },
- "outputs": [],
- "source": [
- "# delete top layer for finetuning\n",
- "sub_model = nn.Sequentialtial(*list(resnet.children()[:-1]))\n",
- "\n",
- "# for test\n",
- "images = Variable(torch.randn(10, 3, 256, 256))\n",
- "print (resnet(images).size())\n",
- "print (sub_model(images).size())"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## Save and Load Model"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {
- "collapsed": true
- },
- "outputs": [],
- "source": [
- "# Save and load the trained model\n",
- "torch.save(sub_model, 'model.pkl')\n",
- "\n",
- "model = torch.load('model.pkl')"
- ]
- }
- ],
- "metadata": {
- "anaconda-cloud": {},
- "kernelspec": {
- "display_name": "Python [conda root]",
- "language": "python",
- "name": "conda-root-py"
- },
- "language_info": {
- "codemirror_mode": {
- "name": "ipython",
- "version": 3
- },
- "file_extension": ".py",
- "mimetype": "text/x-python",
- "name": "python",
- "nbconvert_exporter": "python",
- "pygments_lexer": "ipython3",
- "version": "3.5.2"
- }
- },
- "nbformat": 4,
- "nbformat_minor": 1
-}
diff --git a/tutorials/00 - PyTorch Basics/main.py b/tutorials/00 - PyTorch Basics/main.py
deleted file mode 100644
index 17a50707..00000000
--- a/tutorials/00 - PyTorch Basics/main.py
+++ /dev/null
@@ -1,165 +0,0 @@
-import torch
-import torchvision
-import torch.nn as nn
-import numpy as np
-import torch.utils.data as data
-import torchvision.transforms as transforms
-import torchvision.datasets as dsets
-from torch.autograd import Variable
-
-
-#========================== Table of Contents ==========================#
-# 1. Basic autograd example 1 (Line 21 to 36)
-# 2. Basic autograd example 2 (Line 39 to 77)
-# 3. Loading data from numpy (Line 80 to 83)
-# 4. Implementing the input pipline (Line 86 to 113)
-# 5. Input pipline for custom dataset (Line 116 to 138)
-# 6. Using pretrained model (Line 141 to 155)
-# 7. Save and load model (Line 158 to 165)
-
-
-#======================= Basic autograd example 1 =======================#
-# Create tensors.
-x = Variable(torch.Tensor([1]), requires_grad=True)
-w = Variable(torch.Tensor([2]), requires_grad=True)
-b = Variable(torch.Tensor([3]), requires_grad=True)
-
-# Build a computational graph.
-y = w * x + b # y = 2 * x + 3
-
-# Compute gradients.
-y.backward()
-
-# Print out the gradients.
-print(x.grad) # x.grad = 2
-print(w.grad) # w.grad = 1
-print(b.grad) # b.grad = 1
-
-
-#======================== Basic autograd example 2 =======================#
-# Create tensors.
-x = Variable(torch.randn(5, 3))
-y = Variable(torch.randn(5, 2))
-
-# Build a linear layer.
-linear = nn.Linear(3, 2)
-print ('w: ', linear.weight)
-print ('b: ', linear.bias)
-
-# Build Loss and Optimizer.
-criterion = nn.MSELoss()
-optimizer = torch.optim.SGD(linear.parameters(), lr=0.01)
-
-# Forward propagation.
-pred = linear(x)
-
-# Compute loss.
-loss = criterion(pred, y)
-print('loss: ', loss.data[0])
-
-# Backpropagation.
-loss.backward()
-
-# Print out the gradients.
-print ('dL/dw: ', linear.weight.grad)
-print ('dL/db: ', linear.bias.grad)
-
-# 1-step Optimization (gradient descent).
-optimizer.step()
-
-# You can also do optimization at the low level as shown below.
-# linear.weight.data.sub_(0.01 * linear.weight.grad.data)
-# linear.bias.data.sub_(0.01 * linear.bias.grad.data)
-
-# Print out the loss after optimization.
-pred = linear(x)
-loss = criterion(pred, y)
-print('loss after 1 step optimization: ', loss.data[0])
-
-
-#======================== Loading data from numpy ========================#
-a = np.array([[1,2], [3,4]])
-b = torch.from_numpy(a) # convert numpy array to torch tensor
-c = b.numpy() # convert torch tensor to numpy array
-
-
-#===================== Implementing the input pipline =====================#
-# Download and construct dataset.
-train_dataset = dsets.CIFAR10(root='../data/',
- train=True,
- transform=transforms.ToTensor(),
- download=True)
-
-# Select one data pair (read data from disk).
-image, label = train_dataset[0]
-print (image.size())
-print (label)
-
-# Data Loader (this provides queue and thread in a very simple way).
-train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
- batch_size=100,
- shuffle=True,
- num_workers=2)
-
-# When iteration starts, queue and thread start to load dataset from files.
-data_iter = iter(train_loader)
-
-# Mini-batch images and labels.
-images, labels = data_iter.next()
-
-# Actual usage of data loader is as below.
-for images, labels in train_loader:
- # Your training code will be written here
- pass
-
-
-#===================== Input pipline for custom dataset =====================#
-# You should build custom dataset as below.
-class CustomDataset(data.Dataset):
- def __init__(self):
- # TODO
- # 1. Initialize file path or list of file names.
- pass
- def __getitem__(self, index):
- # TODO
- # 1. Read one data from file (e.g. using numpy.fromfile, PIL.Image.open).
- # 2. Preprocess the data (e.g. torchvision.Transform).
- # 3. Return a data pair (e.g. image and label).
- pass
- def __len__(self):
- # You should change 0 to the total size of your dataset.
- return 0
-
-# Then, you can just use prebuilt torch's data loader.
-custom_dataset = CustomDataset()
-train_loader = torch.utils.data.DataLoader(dataset=custom_dataset,
- batch_size=100,
- shuffle=True,
- num_workers=2)
-
-
-#========================== Using pretrained model ==========================#
-# Download and load pretrained resnet.
-resnet = torchvision.models.resnet18(pretrained=True)
-
-# If you want to finetune only top layer of the model.
-for param in resnet.parameters():
- param.requires_grad = False
-
-# Replace top layer for finetuning.
-resnet.fc = nn.Linear(resnet.fc.in_features, 100) # 100 is for example.
-
-# For test.
-images = Variable(torch.randn(10, 3, 256, 256))
-outputs = resnet(images)
-print (outputs.size()) # (10, 100)
-
-
-#============================ Save and load the model ============================#
-# Save and load the entire model.
-torch.save(resnet, 'model.pkl')
-model = torch.load('model.pkl')
-
-# Save and load only the model parameters(recommended).
-torch.save(resnet.state_dict(), 'params.pkl')
-resnet.load_state_dict(torch.load('params.pkl'))
\ No newline at end of file
diff --git a/tutorials/01-basics/feedforward_neural_network/main.py b/tutorials/01-basics/feedforward_neural_network/main.py
new file mode 100644
index 00000000..0c766a7e
--- /dev/null
+++ b/tutorials/01-basics/feedforward_neural_network/main.py
@@ -0,0 +1,94 @@
+import torch
+import torch.nn as nn
+import torchvision
+import torchvision.transforms as transforms
+
+
+# Device configuration
+device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+
+# Hyper-parameters
+input_size = 784
+hidden_size = 500
+num_classes = 10
+num_epochs = 5
+batch_size = 100
+learning_rate = 0.001
+
+# MNIST dataset
+train_dataset = torchvision.datasets.MNIST(root='../../data',
+ train=True,
+ transform=transforms.ToTensor(),
+ download=True)
+
+test_dataset = torchvision.datasets.MNIST(root='../../data',
+ train=False,
+ transform=transforms.ToTensor())
+
+# Data loader
+train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
+ batch_size=batch_size,
+ shuffle=True)
+
+test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
+ batch_size=batch_size,
+ shuffle=False)
+
+# Fully connected neural network with one hidden layer
+class NeuralNet(nn.Module):
+ def __init__(self, input_size, hidden_size, num_classes):
+ super(NeuralNet, self).__init__()
+ self.fc1 = nn.Linear(input_size, hidden_size)
+ self.relu = nn.ReLU()
+ self.fc2 = nn.Linear(hidden_size, num_classes)
+
+ def forward(self, x):
+ out = self.fc1(x)
+ out = self.relu(out)
+ out = self.fc2(out)
+ return out
+
+model = NeuralNet(input_size, hidden_size, num_classes).to(device)
+
+# Loss and optimizer
+criterion = nn.CrossEntropyLoss()
+optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
+
+# Train the model
+total_step = len(train_loader)
+for epoch in range(num_epochs):
+ for i, (images, labels) in enumerate(train_loader):
+ # Move tensors to the configured device
+ images = images.reshape(-1, 28*28).to(device)
+ labels = labels.to(device)
+
+ # Forward pass
+ outputs = model(images)
+ loss = criterion(outputs, labels)
+
+ # Backward and optimize
+ optimizer.zero_grad()
+ loss.backward()
+ optimizer.step()
+
+ if (i+1) % 100 == 0:
+ print ('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}'
+ .format(epoch+1, num_epochs, i+1, total_step, loss.item()))
+
+# Test the model
+# In test phase, we don't need to compute gradients (for memory efficiency)
+with torch.no_grad():
+ correct = 0
+ total = 0
+ for images, labels in test_loader:
+ images = images.reshape(-1, 28*28).to(device)
+ labels = labels.to(device)
+ outputs = model(images)
+ _, predicted = torch.max(outputs.data, 1)
+ total += labels.size(0)
+ correct += (predicted == labels).sum().item()
+
+ print('Accuracy of the network on the 10000 test images: {} %'.format(100 * correct / total))
+
+# Save the model checkpoint
+torch.save(model.state_dict(), 'model.ckpt')
\ No newline at end of file
diff --git a/tutorials/01 - Linear Regression/main.py b/tutorials/01-basics/linear_regression/main.py
similarity index 52%
rename from tutorials/01 - Linear Regression/main.py
rename to tutorials/01-basics/linear_regression/main.py
index 0cebd38b..b3715d99 100644
--- a/tutorials/01 - Linear Regression/main.py
+++ b/tutorials/01-basics/linear_regression/main.py
@@ -2,16 +2,15 @@
import torch.nn as nn
import numpy as np
import matplotlib.pyplot as plt
-from torch.autograd import Variable
-# Hyper Parameters
+# Hyper-parameters
input_size = 1
output_size = 1
num_epochs = 60
learning_rate = 0.001
-# Toy Dataset
+# Toy dataset
x_train = np.array([[3.3], [4.4], [5.5], [6.71], [6.93], [4.168],
[9.779], [6.182], [7.59], [2.167], [7.042],
[10.791], [5.313], [7.997], [3.1]], dtype=np.float32)
@@ -20,45 +19,37 @@
[3.366], [2.596], [2.53], [1.221], [2.827],
[3.465], [1.65], [2.904], [1.3]], dtype=np.float32)
-# Linear Regression Model
-class LinearRegression(nn.Module):
- def __init__(self, input_size, output_size):
- super(LinearRegression, self).__init__()
- self.linear = nn.Linear(input_size, output_size)
-
- def forward(self, x):
- out = self.linear(x)
- return out
-
-model = LinearRegression(input_size, output_size)
+# Linear regression model
+model = nn.Linear(input_size, output_size)
-# Loss and Optimizer
+# Loss and optimizer
criterion = nn.MSELoss()
optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate)
-# Train the Model
+# Train the model
for epoch in range(num_epochs):
- # Convert numpy array to torch Variable
- inputs = Variable(torch.from_numpy(x_train))
- targets = Variable(torch.from_numpy(y_train))
+ # Convert numpy arrays to torch tensors
+ inputs = torch.from_numpy(x_train)
+ targets = torch.from_numpy(y_train)
- # Forward + Backward + Optimize
- optimizer.zero_grad()
+ # Forward pass
outputs = model(inputs)
loss = criterion(outputs, targets)
+
+ # Backward and optimize
+ optimizer.zero_grad()
loss.backward()
optimizer.step()
if (epoch+1) % 5 == 0:
- print ('Epoch [%d/%d], Loss: %.4f'
- %(epoch+1, num_epochs, loss.data[0]))
-
+ print ('Epoch [{}/{}], Loss: {:.4f}'.format(epoch+1, num_epochs, loss.item()))
+
# Plot the graph
-predicted = model(Variable(torch.from_numpy(x_train))).data.numpy()
+predicted = model(torch.from_numpy(x_train)).detach().numpy()
plt.plot(x_train, y_train, 'ro', label='Original data')
plt.plot(x_train, predicted, label='Fitted line')
plt.legend()
plt.show()
-# Save the Model
-torch.save(model.state_dict(), 'model.pkl')
\ No newline at end of file
+# Save the model checkpoint
+torch.save(model.state_dict(), 'model.ckpt')
\ No newline at end of file
diff --git a/tutorials/01-basics/logistic_regression/main.py b/tutorials/01-basics/logistic_regression/main.py
new file mode 100644
index 00000000..c7eb378b
--- /dev/null
+++ b/tutorials/01-basics/logistic_regression/main.py
@@ -0,0 +1,76 @@
+import torch
+import torch.nn as nn
+import torchvision
+import torchvision.transforms as transforms
+
+
+# Hyper-parameters
+input_size = 28 * 28 # 784
+num_classes = 10
+num_epochs = 5
+batch_size = 100
+learning_rate = 0.001
+
+# MNIST dataset (images and labels)
+train_dataset = torchvision.datasets.MNIST(root='../../data',
+ train=True,
+ transform=transforms.ToTensor(),
+ download=True)
+
+test_dataset = torchvision.datasets.MNIST(root='../../data',
+ train=False,
+ transform=transforms.ToTensor())
+
+# Data loader (input pipeline)
+train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
+ batch_size=batch_size,
+ shuffle=True)
+
+test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
+ batch_size=batch_size,
+ shuffle=False)
+
+# Logistic regression model
+model = nn.Linear(input_size, num_classes)
+
+# Loss and optimizer
+# nn.CrossEntropyLoss() computes softmax internally
+criterion = nn.CrossEntropyLoss()
+optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate)
+
+# Train the model
+total_step = len(train_loader)
+for epoch in range(num_epochs):
+ for i, (images, labels) in enumerate(train_loader):
+ # Reshape images to (batch_size, input_size)
+ images = images.reshape(-1, input_size)
+
+ # Forward pass
+ outputs = model(images)
+ loss = criterion(outputs, labels)
+
+ # Backward and optimize
+ optimizer.zero_grad()
+ loss.backward()
+ optimizer.step()
+
+ if (i+1) % 100 == 0:
+ print ('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}'
+ .format(epoch+1, num_epochs, i+1, total_step, loss.item()))
+
+# Test the model
+# In test phase, we don't need to compute gradients (for memory efficiency)
+with torch.no_grad():
+ correct = 0
+ total = 0
+ for images, labels in test_loader:
+ images = images.reshape(-1, input_size)
+ outputs = model(images)
+ _, predicted = torch.max(outputs.data, 1)
+ total += labels.size(0)
+ correct += (predicted == labels).sum()
+
+ print('Accuracy of the model on the 10000 test images: {} %'.format(100 * correct / total))
+
+# Save the model checkpoint
+torch.save(model.state_dict(), 'model.ckpt')
diff --git a/tutorials/01-basics/pytorch_basics/main.py b/tutorials/01-basics/pytorch_basics/main.py
new file mode 100644
index 00000000..744400c2
--- /dev/null
+++ b/tutorials/01-basics/pytorch_basics/main.py
@@ -0,0 +1,189 @@
+import torch
+import torchvision
+import torch.nn as nn
+import numpy as np
+import torchvision.transforms as transforms
+
+
+# ================================================================== #
+# Table of Contents #
+# ================================================================== #
+
+# 1. Basic autograd example 1 (Line 25 to 39)
+# 2. Basic autograd example 2 (Line 46 to 83)
+# 3. Loading data from numpy (Line 90 to 97)
+# 4. Input pipline (Line 104 to 129)
+# 5. Input pipline for custom dataset (Line 136 to 156)
+# 6. Pretrained model (Line 163 to 176)
+# 7. Save and load model (Line 183 to 189)
+
+
+# ================================================================== #
+# 1. Basic autograd example 1 #
+# ================================================================== #
+
+# Create tensors.
+x = torch.tensor(1., requires_grad=True)
+w = torch.tensor(2., requires_grad=True)
+b = torch.tensor(3., requires_grad=True)
+
+# Build a computational graph.
+y = w * x + b # y = 2 * x + 3
+
+# Compute gradients.
+y.backward()
+
+# Print out the gradients.
+print(x.grad) # x.grad = 2
+print(w.grad) # w.grad = 1
+print(b.grad) # b.grad = 1
+
+
+# ================================================================== #
+# 2. Basic autograd example 2 #
+# ================================================================== #
+
+# Create tensors of shape (10, 3) and (10, 2).
+x = torch.randn(10, 3)
+y = torch.randn(10, 2)
+
+# Build a fully connected layer.
+linear = nn.Linear(3, 2)
+print ('w: ', linear.weight)
+print ('b: ', linear.bias)
+
+# Build loss function and optimizer.
+criterion = nn.MSELoss()
+optimizer = torch.optim.SGD(linear.parameters(), lr=0.01)
+
+# Forward pass.
+pred = linear(x)
+
+# Compute loss.
+loss = criterion(pred, y)
+print('loss: ', loss.item())
+
+# Backward pass.
+loss.backward()
+
+# Print out the gradients.
+print ('dL/dw: ', linear.weight.grad)
+print ('dL/db: ', linear.bias.grad)
+
+# 1-step gradient descent.
+optimizer.step()
+
+# You can also perform gradient descent at the low level.
+# linear.weight.data.sub_(0.01 * linear.weight.grad.data)
+# linear.bias.data.sub_(0.01 * linear.bias.grad.data)
+
+# Print out the loss after 1-step gradient descent.
+pred = linear(x)
+loss = criterion(pred, y)
+print('loss after 1 step optimization: ', loss.item())
+
+
+# ================================================================== #
+# 3. Loading data from numpy #
+# ================================================================== #
+
+# Create a numpy array.
+x = np.array([[1, 2], [3, 4]])
+
+# Convert the numpy array to a torch tensor.
+y = torch.from_numpy(x)
+
+# Convert the torch tensor to a numpy array.
+z = y.numpy()
+
+
+# ================================================================== #
+# 4. Input pipeline #
+# ================================================================== #
+
+# Download and construct CIFAR-10 dataset.
+train_dataset = torchvision.datasets.CIFAR10(root='../../data/',
+ train=True,
+ transform=transforms.ToTensor(),
+ download=True)
+
+# Fetch one data pair (read data from disk).
+image, label = train_dataset[0]
+print (image.size())
+print (label)
+
+# Data loader (this provides queues and threads in a very simple way).
+train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
+ batch_size=64,
+ shuffle=True)
+
+# When iteration starts, queue and thread start to load data from files.
+data_iter = iter(train_loader)
+
+# Mini-batch images and labels.
+images, labels = data_iter.next()
+
+# Actual usage of the data loader is as below.
+for images, labels in train_loader:
+ # Training code should be written here.
+ pass
+
+
+# ================================================================== #
+# 5. Input pipeline for custom dataset #
+# ================================================================== #
+
+# You should build your custom dataset as below.
+class CustomDataset(torch.utils.data.Dataset):
+ def __init__(self):
+ # TODO
+ # 1. Initialize file paths or a list of file names.
+ pass
+ def __getitem__(self, index):
+ # TODO
+ # 1. Read one data from file (e.g. using numpy.fromfile, PIL.Image.open).
+ # 2. Preprocess the data (e.g. torchvision.Transform).
+ # 3. Return a data pair (e.g. image and label).
+ pass
+ def __len__(self):
+ # You should change 0 to the total size of your dataset.
+ return 0
+
+# You can then use the prebuilt data loader.
+custom_dataset = CustomDataset()
+train_loader = torch.utils.data.DataLoader(dataset=custom_dataset,
+ batch_size=64,
+ shuffle=True)
+
+
+# ================================================================== #
+# 6. Pretrained model #
+# ================================================================== #
+
+# Download and load the pretrained ResNet-18.
+resnet = torchvision.models.resnet18(pretrained=True)
+
+# If you want to finetune only the top layer of the model, set as below.
+for param in resnet.parameters():
+ param.requires_grad = False
+
+# Replace the top layer for finetuning.
+resnet.fc = nn.Linear(resnet.fc.in_features, 100) # 100 is an example.
+
+# Forward pass.
+images = torch.randn(64, 3, 224, 224)
+outputs = resnet(images)
+print (outputs.size()) # (64, 100)
+
+
+# ================================================================== #
+# 7. Save and load the model #
+# ================================================================== #
+
+# Save and load the entire model.
+torch.save(resnet, 'model.ckpt')
+model = torch.load('model.ckpt')
+
+# Save and load only the model parameters (recommended).
+torch.save(resnet.state_dict(), 'params.ckpt')
+resnet.load_state_dict(torch.load('params.ckpt'))
diff --git a/tutorials/02 - Logistic Regression/main.py b/tutorials/02 - Logistic Regression/main.py
deleted file mode 100644
index e52651c6..00000000
--- a/tutorials/02 - Logistic Regression/main.py
+++ /dev/null
@@ -1,82 +0,0 @@
-import torch
-import torch.nn as nn
-import torchvision.datasets as dsets
-import torchvision.transforms as transforms
-from torch.autograd import Variable
-
-
-# Hyper Parameters
-input_size = 784
-num_classes = 10
-num_epochs = 5
-batch_size = 100
-learning_rate = 0.001
-
-# MNIST Dataset (Images and Labels)
-train_dataset = dsets.MNIST(root='../data',
- train=True,
- transform=transforms.ToTensor(),
- download=True)
-
-test_dataset = dsets.MNIST(root='../data',
- train=False,
- transform=transforms.ToTensor())
-
-# Dataset Loader (Input Pipline)
-train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
- batch_size=batch_size,
- shuffle=True)
-
-test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
- batch_size=batch_size,
- shuffle=False)
-
-# Model
-class LogisticRegression(nn.Module):
- def __init__(self, input_size, num_classes):
- super(LogisticRegression, self).__init__()
- self.linear = nn.Linear(input_size, num_classes)
-
- def forward(self, x):
- out = self.linear(x)
- return out
-
-model = LogisticRegression(input_size, num_classes)
-
-# Loss and Optimizer
-# Softmax is internally computed.
-# Set parameters to be updated.
-criterion = nn.CrossEntropyLoss()
-optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate)
-
-# Training the Model
-for epoch in range(num_epochs):
- for i, (images, labels) in enumerate(train_loader):
- images = Variable(images.view(-1, 28*28))
- labels = Variable(labels)
-
- # Forward + Backward + Optimize
- optimizer.zero_grad()
- outputs = model(images)
- loss = criterion(outputs, labels)
- loss.backward()
- optimizer.step()
-
- if (i+1) % 100 == 0:
- print ('Epoch: [%d/%d], Step: [%d/%d], Loss: %.4f'
- % (epoch+1, num_epochs, i+1, len(train_dataset)//batch_size, loss.data[0]))
-
-# Test the Model
-correct = 0
-total = 0
-for images, labels in test_loader:
- images = Variable(images.view(-1, 28*28))
- outputs = model(images)
- _, predicted = torch.max(outputs.data, 1)
- total += labels.size(0)
- correct += (predicted == labels).sum()
-
-print('Accuracy of the model on the 10000 test images: %d %%' % (100 * correct / total))
-
-# Save the Model
-torch.save(model.state_dict(), 'model.pkl')
\ No newline at end of file
diff --git a/tutorials/02-intermediate/bidirectional_recurrent_neural_network/main.py b/tutorials/02-intermediate/bidirectional_recurrent_neural_network/main.py
new file mode 100644
index 00000000..a0ecd773
--- /dev/null
+++ b/tutorials/02-intermediate/bidirectional_recurrent_neural_network/main.py
@@ -0,0 +1,102 @@
+import torch
+import torch.nn as nn
+import torchvision
+import torchvision.transforms as transforms
+
+
+# Device configuration
+device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+
+# Hyper-parameters
+sequence_length = 28
+input_size = 28
+hidden_size = 128
+num_layers = 2
+num_classes = 10
+batch_size = 100
+num_epochs = 2
+learning_rate = 0.003
+
+# MNIST dataset
+train_dataset = torchvision.datasets.MNIST(root='../../data/',
+ train=True,
+ transform=transforms.ToTensor(),
+ download=True)
+
+test_dataset = torchvision.datasets.MNIST(root='../../data/',
+ train=False,
+ transform=transforms.ToTensor())
+
+# Data loader
+train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
+ batch_size=batch_size,
+ shuffle=True)
+
+test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
+ batch_size=batch_size,
+ shuffle=False)
+
+# Bidirectional recurrent neural network (many-to-one)
+class BiRNN(nn.Module):
+ def __init__(self, input_size, hidden_size, num_layers, num_classes):
+ super(BiRNN, self).__init__()
+ self.hidden_size = hidden_size
+ self.num_layers = num_layers
+ self.lstm = nn.LSTM(input_size, hidden_size, num_layers, batch_first=True, bidirectional=True)
+ self.fc = nn.Linear(hidden_size*2, num_classes) # 2 for bidirection
+
+ def forward(self, x):
+ # Set initial states
+ h0 = torch.zeros(self.num_layers*2, x.size(0), self.hidden_size).to(device) # 2 for bidirection
+ c0 = torch.zeros(self.num_layers*2, x.size(0), self.hidden_size).to(device)
+
+ # Forward propagate LSTM
+ out, _ = self.lstm(x, (h0, c0)) # out: tensor of shape (batch_size, seq_length, hidden_size*2)
+
+ # Decode the hidden state of the last time step
+ out = self.fc(out[:, -1, :])
+ return out
+
+model = BiRNN(input_size, hidden_size, num_layers, num_classes).to(device)
+
+
+# Loss and optimizer
+criterion = nn.CrossEntropyLoss()
+optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
+
+# Train the model
+total_step = len(train_loader)
+for epoch in range(num_epochs):
+ for i, (images, labels) in enumerate(train_loader):
+ images = images.reshape(-1, sequence_length, input_size).to(device)
+ labels = labels.to(device)
+
+ # Forward pass
+ outputs = model(images)
+ loss = criterion(outputs, labels)
+
+ # Backward and optimize
+ optimizer.zero_grad()
+ loss.backward()
+ optimizer.step()
+
+ if (i+1) % 100 == 0:
+ print ('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}'
+ .format(epoch+1, num_epochs, i+1, total_step, loss.item()))
+
+# Test the model
+with torch.no_grad():
+ correct = 0
+ total = 0
+ for images, labels in test_loader:
+ images = images.reshape(-1, sequence_length, input_size).to(device)
+ labels = labels.to(device)
+ outputs = model(images)
+ _, predicted = torch.max(outputs.data, 1)
+ total += labels.size(0)
+ correct += (predicted == labels).sum().item()
+
+ print('Test Accuracy of the model on the 10000 test images: {} %'.format(100 * correct / total))
+
+# Save the model checkpoint
+torch.save(model.state_dict(), 'model.ckpt')
\ No newline at end of file
diff --git a/tutorials/02-intermediate/convolutional_neural_network/main.py b/tutorials/02-intermediate/convolutional_neural_network/main.py
new file mode 100644
index 00000000..ec904f1f
--- /dev/null
+++ b/tutorials/02-intermediate/convolutional_neural_network/main.py
@@ -0,0 +1,100 @@
+import torch
+import torch.nn as nn
+import torchvision
+import torchvision.transforms as transforms
+
+
+# Device configuration
+device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
+
+# Hyper parameters
+num_epochs = 5
+num_classes = 10
+batch_size = 100
+learning_rate = 0.001
+
+# MNIST dataset
+train_dataset = torchvision.datasets.MNIST(root='../../data/',
+ train=True,
+ transform=transforms.ToTensor(),
+ download=True)
+
+test_dataset = torchvision.datasets.MNIST(root='../../data/',
+ train=False,
+ transform=transforms.ToTensor())
+
+# Data loader
+train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
+ batch_size=batch_size,
+ shuffle=True)
+
+test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
+ batch_size=batch_size,
+ shuffle=False)
+
+# Convolutional neural network (two convolutional layers)
+class ConvNet(nn.Module):
+ def __init__(self, num_classes=10):
+ super(ConvNet, self).__init__()
+ self.layer1 = nn.Sequential(
+ nn.Conv2d(1, 16, kernel_size=5, stride=1, padding=2),
+ nn.BatchNorm2d(16),
+ nn.ReLU(),
+ nn.MaxPool2d(kernel_size=2, stride=2))
+ self.layer2 = nn.Sequential(
+ nn.Conv2d(16, 32, kernel_size=5, stride=1, padding=2),
+ nn.BatchNorm2d(32),
+ nn.ReLU(),
+ nn.MaxPool2d(kernel_size=2, stride=2))
+ self.fc = nn.Linear(7*7*32, num_classes)
+
+ def forward(self, x):
+ out = self.layer1(x)
+ out = self.layer2(out)
+ out = out.reshape(out.size(0), -1)
+ out = self.fc(out)
+ return out
+
+model = ConvNet(num_classes).to(device)
+
+# Loss and optimizer
+criterion = nn.CrossEntropyLoss()
+optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
+
+# Train the model
+total_step = len(train_loader)
+for epoch in range(num_epochs):
+ for i, (images, labels) in enumerate(train_loader):
+ images = images.to(device)
+ labels = labels.to(device)
+
+ # Forward pass
+ outputs = model(images)
+ loss = criterion(outputs, labels)
+
+ # Backward and optimize
+ optimizer.zero_grad()
+ loss.backward()
+ optimizer.step()
+
+ if (i+1) % 100 == 0:
+ print ('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}'
+ .format(epoch+1, num_epochs, i+1, total_step, loss.item()))
+
+# Test the model
+model.eval() # eval mode (batchnorm uses moving mean/variance instead of mini-batch mean/variance)
+with torch.no_grad():
+ correct = 0
+ total = 0
+ for images, labels in test_loader:
+ images = images.to(device)
+ labels = labels.to(device)
+ outputs = model(images)
+ _, predicted = torch.max(outputs.data, 1)
+ total += labels.size(0)
+ correct += (predicted == labels).sum().item()
+
+ print('Test Accuracy of the model on the 10000 test images: {} %'.format(100 * correct / total))
+
+# Save the model checkpoint
+torch.save(model.state_dict(), 'model.ckpt')
\ No newline at end of file
diff --git a/tutorials/05 - Deep Residual Network/main-gpu.py b/tutorials/02-intermediate/deep_residual_network/main.py
similarity index 53%
rename from tutorials/05 - Deep Residual Network/main-gpu.py
rename to tutorials/02-intermediate/deep_residual_network/main.py
index 30ba548e..69dbe5fb 100644
--- a/tutorials/05 - Deep Residual Network/main-gpu.py
+++ b/tutorials/02-intermediate/deep_residual_network/main.py
@@ -1,45 +1,56 @@
-# Implementation of https://arxiv.org/pdf/1512.03385.pdf/
-# See section 4.2 for model architecture on CIFAR-10.
-# Some part of the code was referenced below.
-# https://github.com/pytorch/vision/blob/master/torchvision/models/resnet.py
-import torch
+# ---------------------------------------------------------------------------- #
+# An implementation of https://arxiv.org/pdf/1512.03385.pdf #
+# See section 4.2 for the model architecture on CIFAR-10 #
+# Some part of the code was referenced from below #
+# https://github.com/pytorch/vision/blob/master/torchvision/models/resnet.py #
+# ---------------------------------------------------------------------------- #
+
+import torch
import torch.nn as nn
-import torchvision.datasets as dsets
+import torchvision
import torchvision.transforms as transforms
-from torch.autograd import Variable
-# Image Preprocessing
+
+# Device configuration
+device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+
+# Hyper-parameters
+num_epochs = 80
+batch_size = 100
+learning_rate = 0.001
+
+# Image preprocessing modules
transform = transforms.Compose([
- transforms.Scale(40),
+ transforms.Pad(4),
transforms.RandomHorizontalFlip(),
transforms.RandomCrop(32),
transforms.ToTensor()])
-# CIFAR-10 Dataset
-train_dataset = dsets.CIFAR10(root='../data/',
- train=True,
- transform=transform,
- download=True)
+# CIFAR-10 dataset
+train_dataset = torchvision.datasets.CIFAR10(root='../../data/',
+ train=True,
+ transform=transform,
+ download=True)
-test_dataset = dsets.CIFAR10(root='../data/',
- train=False,
- transform=transforms.ToTensor())
+test_dataset = torchvision.datasets.CIFAR10(root='../../data/',
+ train=False,
+ transform=transforms.ToTensor())
-# Data Loader (Input Pipeline)
+# Data loader
train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
- batch_size=100,
+ batch_size=batch_size,
shuffle=True)
test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
- batch_size=100,
+ batch_size=batch_size,
shuffle=False)
-# 3x3 Convolution
+# 3x3 convolution
def conv3x3(in_channels, out_channels, stride=1):
return nn.Conv2d(in_channels, out_channels, kernel_size=3,
stride=stride, padding=1, bias=False)
-# Residual Block
+# Residual block
class ResidualBlock(nn.Module):
def __init__(self, in_channels, out_channels, stride=1, downsample=None):
super(ResidualBlock, self).__init__()
@@ -63,7 +74,7 @@ def forward(self, x):
out = self.relu(out)
return out
-# ResNet Module
+# ResNet
class ResNet(nn.Module):
def __init__(self, block, layers, num_classes=10):
super(ResNet, self).__init__()
@@ -72,8 +83,8 @@ def __init__(self, block, layers, num_classes=10):
self.bn = nn.BatchNorm2d(16)
self.relu = nn.ReLU(inplace=True)
self.layer1 = self.make_layer(block, 16, layers[0])
- self.layer2 = self.make_layer(block, 32, layers[0], 2)
- self.layer3 = self.make_layer(block, 64, layers[1], 2)
+ self.layer2 = self.make_layer(block, 32, layers[1], 2)
+ self.layer3 = self.make_layer(block, 64, layers[2], 2)
self.avg_pool = nn.AvgPool2d(8)
self.fc = nn.Linear(64, num_classes)
@@ -102,46 +113,58 @@ def forward(self, x):
out = self.fc(out)
return out
-resnet = ResNet(ResidualBlock, [3, 3, 3])
-resnet.cuda()
+model = ResNet(ResidualBlock, [2, 2, 2]).to(device)
-# Loss and Optimizer
+
+# Loss and optimizer
criterion = nn.CrossEntropyLoss()
-lr = 0.001
-optimizer = torch.optim.Adam(resnet.parameters(), lr=lr)
-
-# Training
-for epoch in range(80):
+optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
+
+# For updating learning rate
+def update_lr(optimizer, lr):
+ for param_group in optimizer.param_groups:
+ param_group['lr'] = lr
+
+# Train the model
+total_step = len(train_loader)
+curr_lr = learning_rate
+for epoch in range(num_epochs):
for i, (images, labels) in enumerate(train_loader):
- images = Variable(images.cuda())
- labels = Variable(labels.cuda())
+ images = images.to(device)
+ labels = labels.to(device)
- # Forward + Backward + Optimize
- optimizer.zero_grad()
- outputs = resnet(images)
+ # Forward pass
+ outputs = model(images)
loss = criterion(outputs, labels)
+
+ # Backward and optimize
+ optimizer.zero_grad()
loss.backward()
optimizer.step()
if (i+1) % 100 == 0:
- print ("Epoch [%d/%d], Iter [%d/%d] Loss: %.4f" %(epoch+1, 80, i+1, 500, loss.data[0]))
+ print ("Epoch [{}/{}], Step [{}/{}] Loss: {:.4f}"
+ .format(epoch+1, num_epochs, i+1, total_step, loss.item()))
- # Decaying Learning Rate
+ # Decay learning rate
if (epoch+1) % 20 == 0:
- lr /= 3
- optimizer = torch.optim.Adam(resnet.parameters(), lr=lr)
-
-# Test
-correct = 0
-total = 0
-for images, labels in test_loader:
- images = Variable(images.cuda())
- outputs = resnet(images)
- _, predicted = torch.max(outputs.data, 1)
- total += labels.size(0)
- correct += (predicted.cpu() == labels).sum()
-
-print('Accuracy of the model on the test images: %d %%' % (100 * correct / total))
-
-# Save the Model
-torch.save(resnet.state_dict(), 'resnet.pkl')
\ No newline at end of file
+ curr_lr /= 3
+ update_lr(optimizer, curr_lr)
+
+# Test the model
+model.eval()
+with torch.no_grad():
+ correct = 0
+ total = 0
+ for images, labels in test_loader:
+ images = images.to(device)
+ labels = labels.to(device)
+ outputs = model(images)
+ _, predicted = torch.max(outputs.data, 1)
+ total += labels.size(0)
+ correct += (predicted == labels).sum().item()
+
+ print('Accuracy of the model on the test images: {} %'.format(100 * correct / total))
+
+# Save the model checkpoint
+torch.save(model.state_dict(), 'resnet.ckpt')
diff --git a/tutorials/08 - Language Model/data/train.txt b/tutorials/02-intermediate/language_model/data/train.txt
similarity index 100%
rename from tutorials/08 - Language Model/data/train.txt
rename to tutorials/02-intermediate/language_model/data/train.txt
diff --git a/tutorials/08 - Language Model/data_utils.py b/tutorials/02-intermediate/language_model/data_utils.py
similarity index 89%
rename from tutorials/08 - Language Model/data_utils.py
rename to tutorials/02-intermediate/language_model/data_utils.py
index e0238b81..91bc6053 100644
--- a/tutorials/08 - Language Model/data_utils.py
+++ b/tutorials/02-intermediate/language_model/data_utils.py
@@ -1,6 +1,7 @@
import torch
import os
+
class Dictionary(object):
def __init__(self):
self.word2idx = {}
@@ -15,12 +16,11 @@ def add_word(self, word):
def __len__(self):
return len(self.word2idx)
-
+
+
class Corpus(object):
- def __init__(self, path='./data'):
+ def __init__(self):
self.dictionary = Dictionary()
- self.train = os.path.join(path, 'train.txt')
- self.test = os.path.join(path, 'test.txt')
def get_data(self, path, batch_size=20):
# Add words to the dictionary
diff --git a/tutorials/02-intermediate/language_model/main.py b/tutorials/02-intermediate/language_model/main.py
new file mode 100644
index 00000000..ef135bb7
--- /dev/null
+++ b/tutorials/02-intermediate/language_model/main.py
@@ -0,0 +1,120 @@
+# Some part of the code was referenced from below.
+# https://github.com/pytorch/examples/tree/master/word_language_model
+import torch
+import torch.nn as nn
+import numpy as np
+from torch.nn.utils import clip_grad_norm_
+from data_utils import Dictionary, Corpus
+
+
+# Device configuration
+device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+
+# Hyper-parameters
+embed_size = 128
+hidden_size = 1024
+num_layers = 1
+num_epochs = 5
+num_samples = 1000 # number of words to be sampled
+batch_size = 20
+seq_length = 30
+learning_rate = 0.002
+
+# Load "Penn Treebank" dataset
+corpus = Corpus()
+ids = corpus.get_data('data/train.txt', batch_size)
+vocab_size = len(corpus.dictionary)
+num_batches = ids.size(1) // seq_length
+
+
+# RNN based language model
+class RNNLM(nn.Module):
+ def __init__(self, vocab_size, embed_size, hidden_size, num_layers):
+ super(RNNLM, self).__init__()
+ self.embed = nn.Embedding(vocab_size, embed_size)
+ self.lstm = nn.LSTM(embed_size, hidden_size, num_layers, batch_first=True)
+ self.linear = nn.Linear(hidden_size, vocab_size)
+
+ def forward(self, x, h):
+ # Embed word ids to vectors
+ x = self.embed(x)
+
+ # Forward propagate LSTM
+ out, (h, c) = self.lstm(x, h)
+
+ # Reshape output to (batch_size*sequence_length, hidden_size)
+ out = out.reshape(out.size(0)*out.size(1), out.size(2))
+
+ # Decode hidden states of all time steps
+ out = self.linear(out)
+ return out, (h, c)
+
+model = RNNLM(vocab_size, embed_size, hidden_size, num_layers).to(device)
+
+# Loss and optimizer
+criterion = nn.CrossEntropyLoss()
+optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
+
+# Truncated backpropagation
+def detach(states):
+ return [state.detach() for state in states]
+
+# Train the model
+for epoch in range(num_epochs):
+ # Set initial hidden and cell states
+ states = (torch.zeros(num_layers, batch_size, hidden_size).to(device),
+ torch.zeros(num_layers, batch_size, hidden_size).to(device))
+
+ for i in range(0, ids.size(1) - seq_length, seq_length):
+ # Get mini-batch inputs and targets
+ inputs = ids[:, i:i+seq_length].to(device)
+ targets = ids[:, (i+1):(i+1)+seq_length].to(device)
+
+ # Forward pass
+ states = detach(states)
+ outputs, states = model(inputs, states)
+ loss = criterion(outputs, targets.reshape(-1))
+
+ # Backward and optimize
+ optimizer.zero_grad()
+ loss.backward()
+ clip_grad_norm_(model.parameters(), 0.5)
+ optimizer.step()
+
+ step = (i+1) // seq_length
+ if step % 100 == 0:
+ print ('Epoch [{}/{}], Step[{}/{}], Loss: {:.4f}, Perplexity: {:5.2f}'
+ .format(epoch+1, num_epochs, step, num_batches, loss.item(), np.exp(loss.item())))
+
+# Test the model
+with torch.no_grad():
+ with open('sample.txt', 'w') as f:
+ # Set intial hidden ane cell states
+ state = (torch.zeros(num_layers, 1, hidden_size).to(device),
+ torch.zeros(num_layers, 1, hidden_size).to(device))
+
+ # Select one word id randomly
+ prob = torch.ones(vocab_size)
+ input = torch.multinomial(prob, num_samples=1).unsqueeze(1).to(device)
+
+ for i in range(num_samples):
+ # Forward propagate RNN
+ output, state = model(input, state)
+
+ # Sample a word id
+ prob = output.exp()
+ word_id = torch.multinomial(prob, num_samples=1).item()
+
+ # Fill input with sampled word id for the next time step
+ input.fill_(word_id)
+
+ # File write
+ word = corpus.dictionary.idx2word[word_id]
+ word = '\n' if word == '' else word + ' '
+ f.write(word)
+
+ if (i+1) % 100 == 0:
+ print('Sampled [{}/{}] words and save to {}'.format(i+1, num_samples, 'sample.txt'))
+
+# Save the model checkpoints
+torch.save(model.state_dict(), 'model.ckpt')
\ No newline at end of file
diff --git a/tutorials/02-intermediate/recurrent_neural_network/main.py b/tutorials/02-intermediate/recurrent_neural_network/main.py
new file mode 100644
index 00000000..c138c5ad
--- /dev/null
+++ b/tutorials/02-intermediate/recurrent_neural_network/main.py
@@ -0,0 +1,103 @@
+import torch
+import torch.nn as nn
+import torchvision
+import torchvision.transforms as transforms
+
+
+# Device configuration
+device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+
+# Hyper-parameters
+sequence_length = 28
+input_size = 28
+hidden_size = 128
+num_layers = 2
+num_classes = 10
+batch_size = 100
+num_epochs = 2
+learning_rate = 0.01
+
+# MNIST dataset
+train_dataset = torchvision.datasets.MNIST(root='../../data/',
+ train=True,
+ transform=transforms.ToTensor(),
+ download=True)
+
+test_dataset = torchvision.datasets.MNIST(root='../../data/',
+ train=False,
+ transform=transforms.ToTensor())
+
+# Data loader
+train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
+ batch_size=batch_size,
+ shuffle=True)
+
+test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
+ batch_size=batch_size,
+ shuffle=False)
+
+# Recurrent neural network (many-to-one)
+class RNN(nn.Module):
+ def __init__(self, input_size, hidden_size, num_layers, num_classes):
+ super(RNN, self).__init__()
+ self.hidden_size = hidden_size
+ self.num_layers = num_layers
+ self.lstm = nn.LSTM(input_size, hidden_size, num_layers, batch_first=True)
+ self.fc = nn.Linear(hidden_size, num_classes)
+
+ def forward(self, x):
+ # Set initial hidden and cell states
+ h0 = torch.zeros(self.num_layers, x.size(0), self.hidden_size).to(device)
+ c0 = torch.zeros(self.num_layers, x.size(0), self.hidden_size).to(device)
+
+ # Forward propagate LSTM
+ out, _ = self.lstm(x, (h0, c0)) # out: tensor of shape (batch_size, seq_length, hidden_size)
+
+ # Decode the hidden state of the last time step
+ out = self.fc(out[:, -1, :])
+ return out
+
+model = RNN(input_size, hidden_size, num_layers, num_classes).to(device)
+
+
+# Loss and optimizer
+criterion = nn.CrossEntropyLoss()
+optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
+
+# Train the model
+total_step = len(train_loader)
+for epoch in range(num_epochs):
+ for i, (images, labels) in enumerate(train_loader):
+ images = images.reshape(-1, sequence_length, input_size).to(device)
+ labels = labels.to(device)
+
+ # Forward pass
+ outputs = model(images)
+ loss = criterion(outputs, labels)
+
+ # Backward and optimize
+ optimizer.zero_grad()
+ loss.backward()
+ optimizer.step()
+
+ if (i+1) % 100 == 0:
+ print ('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}'
+ .format(epoch+1, num_epochs, i+1, total_step, loss.item()))
+
+# Test the model
+model.eval()
+with torch.no_grad():
+ correct = 0
+ total = 0
+ for images, labels in test_loader:
+ images = images.reshape(-1, sequence_length, input_size).to(device)
+ labels = labels.to(device)
+ outputs = model(images)
+ _, predicted = torch.max(outputs.data, 1)
+ total += labels.size(0)
+ correct += (predicted == labels).sum().item()
+
+ print('Test Accuracy of the model on the 10000 test images: {} %'.format(100 * correct / total))
+
+# Save the model checkpoint
+torch.save(model.state_dict(), 'model.ckpt')
\ No newline at end of file
diff --git a/tutorials/03 - Feedforward Neural Network/main-gpu.py b/tutorials/03 - Feedforward Neural Network/main-gpu.py
deleted file mode 100644
index 27fcf1cc..00000000
--- a/tutorials/03 - Feedforward Neural Network/main-gpu.py
+++ /dev/null
@@ -1,87 +0,0 @@
-import torch
-import torch.nn as nn
-import torchvision.datasets as dsets
-import torchvision.transforms as transforms
-from torch.autograd import Variable
-
-
-# Hyper Parameters
-input_size = 784
-hidden_size = 500
-num_classes = 10
-num_epochs = 5
-batch_size = 100
-learning_rate = 0.001
-
-# MNIST Dataset
-train_dataset = dsets.MNIST(root='../data',
- train=True,
- transform=transforms.ToTensor(),
- download=True)
-
-test_dataset = dsets.MNIST(root='../data',
- train=False,
- transform=transforms.ToTensor())
-
-# Data Loader (Input Pipeline)
-train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
- batch_size=batch_size,
- shuffle=True)
-
-test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
- batch_size=batch_size,
- shuffle=False)
-
-# Neural Network Model (1 hidden layer)
-class Net(nn.Module):
- def __init__(self, input_size, hidden_size, num_classes):
- super(Net, self).__init__()
- self.fc1 = nn.Linear(input_size, hidden_size)
- self.relu = nn.ReLU()
- self.fc2 = nn.Linear(hidden_size, num_classes)
-
- def forward(self, x):
- out = self.fc1(x)
- out = self.relu(out)
- out = self.fc2(out)
- return out
-
-net = Net(input_size, hidden_size, num_classes)
-net.cuda()
-
-# Loss and Optimizer
-criterion = nn.CrossEntropyLoss()
-optimizer = torch.optim.Adam(net.parameters(), lr=learning_rate)
-
-# Train the Model
-for epoch in range(num_epochs):
- for i, (images, labels) in enumerate(train_loader):
- # Convert torch tensor to Variable
- images = Variable(images.view(-1, 28*28)).cuda()
- labels = Variable(labels).cuda()
-
- # Forward + Backward + Optimize
- optimizer.zero_grad() # zero the gradient buffer
- outputs = net(images)
- loss = criterion(outputs, labels)
- loss.backward()
- optimizer.step()
-
- if (i+1) % 100 == 0:
- print ('Epoch [%d/%d], Step [%d/%d], Loss: %.4f'
- %(epoch+1, num_epochs, i+1, len(train_dataset)//batch_size, loss.data[0]))
-
-# Test the Model
-correct = 0
-total = 0
-for images, labels in test_loader:
- images = Variable(images.view(-1, 28*28)).cuda()
- outputs = net(images)
- _, predicted = torch.max(outputs.data, 1)
- total += labels.size(0)
- correct += (predicted.cpu() == labels).sum()
-
-print('Accuracy of the network on the 10000 test images: %d %%' % (100 * correct / total))
-
-# Save the Model
-torch.save(net.state_dict(), 'model.pkl')
\ No newline at end of file
diff --git a/tutorials/03 - Feedforward Neural Network/main.py b/tutorials/03 - Feedforward Neural Network/main.py
deleted file mode 100644
index 60788218..00000000
--- a/tutorials/03 - Feedforward Neural Network/main.py
+++ /dev/null
@@ -1,87 +0,0 @@
-import torch
-import torch.nn as nn
-import torchvision.datasets as dsets
-import torchvision.transforms as transforms
-from torch.autograd import Variable
-
-
-# Hyper Parameters
-input_size = 784
-hidden_size = 500
-num_classes = 10
-num_epochs = 5
-batch_size = 100
-learning_rate = 0.001
-
-# MNIST Dataset
-train_dataset = dsets.MNIST(root='../data',
- train=True,
- transform=transforms.ToTensor(),
- download=True)
-
-test_dataset = dsets.MNIST(root='../data',
- train=False,
- transform=transforms.ToTensor())
-
-# Data Loader (Input Pipeline)
-train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
- batch_size=batch_size,
- shuffle=True)
-
-test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
- batch_size=batch_size,
- shuffle=False)
-
-# Neural Network Model (1 hidden layer)
-class Net(nn.Module):
- def __init__(self, input_size, hidden_size, num_classes):
- super(Net, self).__init__()
- self.fc1 = nn.Linear(input_size, hidden_size)
- self.relu = nn.ReLU()
- self.fc2 = nn.Linear(hidden_size, num_classes)
-
- def forward(self, x):
- out = self.fc1(x)
- out = self.relu(out)
- out = self.fc2(out)
- return out
-
-net = Net(input_size, hidden_size, num_classes)
-
-
-# Loss and Optimizer
-criterion = nn.CrossEntropyLoss()
-optimizer = torch.optim.Adam(net.parameters(), lr=learning_rate)
-
-# Train the Model
-for epoch in range(num_epochs):
- for i, (images, labels) in enumerate(train_loader):
- # Convert torch tensor to Variable
- images = Variable(images.view(-1, 28*28))
- labels = Variable(labels)
-
- # Forward + Backward + Optimize
- optimizer.zero_grad() # zero the gradient buffer
- outputs = net(images)
- loss = criterion(outputs, labels)
- loss.backward()
- optimizer.step()
-
- if (i+1) % 100 == 0:
- print ('Epoch [%d/%d], Step [%d/%d], Loss: %.4f'
- %(epoch+1, num_epochs, i+1, len(train_dataset)//batch_size, loss.data[0]))
-
-# Test the Model
-correct = 0
-total = 0
-for images, labels in test_loader:
- images = Variable(images.view(-1, 28*28))
- outputs = net(images)
- _, predicted = torch.max(outputs.data, 1)
- total += labels.size(0)
- correct += (predicted == labels).sum()
-
-print('Accuracy of the network on the 10000 test images: %d %%' % (100 * correct / total))
-
-# Save the Model
-torch.save(net.state_dict(), 'model.pkl')
\ No newline at end of file
diff --git a/tutorials/03-advanced/generative_adversarial_network/main.py b/tutorials/03-advanced/generative_adversarial_network/main.py
new file mode 100644
index 00000000..c2062cf3
--- /dev/null
+++ b/tutorials/03-advanced/generative_adversarial_network/main.py
@@ -0,0 +1,148 @@
+import os
+import torch
+import torchvision
+import torch.nn as nn
+from torchvision import transforms
+from torchvision.utils import save_image
+
+
+# Device configuration
+device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+
+# Hyper-parameters
+latent_size = 64
+hidden_size = 256
+image_size = 784
+num_epochs = 200
+batch_size = 100
+sample_dir = 'samples'
+
+# Create a directory if not exists
+if not os.path.exists(sample_dir):
+ os.makedirs(sample_dir)
+
+# Image processing
+# transform = transforms.Compose([
+# transforms.ToTensor(),
+# transforms.Normalize(mean=(0.5, 0.5, 0.5), # 3 for RGB channels
+# std=(0.5, 0.5, 0.5))])
+transform = transforms.Compose([
+ transforms.ToTensor(),
+ transforms.Normalize(mean=[0.5], # 1 for greyscale channels
+ std=[0.5])])
+
+# MNIST dataset
+mnist = torchvision.datasets.MNIST(root='../../data/',
+ train=True,
+ transform=transform,
+ download=True)
+
+# Data loader
+data_loader = torch.utils.data.DataLoader(dataset=mnist,
+ batch_size=batch_size,
+ shuffle=True)
+
+# Discriminator
+D = nn.Sequential(
+ nn.Linear(image_size, hidden_size),
+ nn.LeakyReLU(0.2),
+ nn.Linear(hidden_size, hidden_size),
+ nn.LeakyReLU(0.2),
+ nn.Linear(hidden_size, 1),
+ nn.Sigmoid())
+
+# Generator
+G = nn.Sequential(
+ nn.Linear(latent_size, hidden_size),
+ nn.ReLU(),
+ nn.Linear(hidden_size, hidden_size),
+ nn.ReLU(),
+ nn.Linear(hidden_size, image_size),
+ nn.Tanh())
+
+# Device setting
+D = D.to(device)
+G = G.to(device)
+
+# Binary cross entropy loss and optimizer
+criterion = nn.BCELoss()
+d_optimizer = torch.optim.Adam(D.parameters(), lr=0.0002)
+g_optimizer = torch.optim.Adam(G.parameters(), lr=0.0002)
+
+def denorm(x):
+ out = (x + 1) / 2
+ return out.clamp(0, 1)
+
+def reset_grad():
+ d_optimizer.zero_grad()
+ g_optimizer.zero_grad()
+
+# Start training
+total_step = len(data_loader)
+for epoch in range(num_epochs):
+ for i, (images, _) in enumerate(data_loader):
+ images = images.reshape(batch_size, -1).to(device)
+
+ # Create the labels which are later used as input for the BCE loss
+ real_labels = torch.ones(batch_size, 1).to(device)
+ fake_labels = torch.zeros(batch_size, 1).to(device)
+
+ # ================================================================== #
+ # Train the discriminator #
+ # ================================================================== #
+
+ # Compute BCE_Loss using real images where BCE_Loss(x, y): - y * log(D(x)) - (1-y) * log(1 - D(x))
+ # Second term of the loss is always zero since real_labels == 1
+ outputs = D(images)
+ d_loss_real = criterion(outputs, real_labels)
+ real_score = outputs
+
+ # Compute BCELoss using fake images
+ # First term of the loss is always zero since fake_labels == 0
+ z = torch.randn(batch_size, latent_size).to(device)
+ fake_images = G(z)
+ outputs = D(fake_images)
+ d_loss_fake = criterion(outputs, fake_labels)
+ fake_score = outputs
+
+ # Backprop and optimize
+ d_loss = d_loss_real + d_loss_fake
+ reset_grad()
+ d_loss.backward()
+ d_optimizer.step()
+
+ # ================================================================== #
+ # Train the generator #
+ # ================================================================== #
+
+ # Compute loss with fake images
+ z = torch.randn(batch_size, latent_size).to(device)
+ fake_images = G(z)
+ outputs = D(fake_images)
+
+ # We train G to maximize log(D(G(z)) instead of minimizing log(1-D(G(z)))
+ # For the reason, see the last paragraph of section 3. https://arxiv.org/pdf/1406.2661.pdf
+ g_loss = criterion(outputs, real_labels)
+
+ # Backprop and optimize
+ reset_grad()
+ g_loss.backward()
+ g_optimizer.step()
+
+ if (i+1) % 200 == 0:
+ print('Epoch [{}/{}], Step [{}/{}], d_loss: {:.4f}, g_loss: {:.4f}, D(x): {:.2f}, D(G(z)): {:.2f}'
+ .format(epoch, num_epochs, i+1, total_step, d_loss.item(), g_loss.item(),
+ real_score.mean().item(), fake_score.mean().item()))
+
+ # Save real images
+ if (epoch+1) == 1:
+ images = images.reshape(images.size(0), 1, 28, 28)
+ save_image(denorm(images), os.path.join(sample_dir, 'real_images.png'))
+
+ # Save sampled images
+ fake_images = fake_images.reshape(fake_images.size(0), 1, 28, 28)
+ save_image(denorm(fake_images), os.path.join(sample_dir, 'fake_images-{}.png'.format(epoch+1)))
+
+# Save the model checkpoints
+torch.save(G.state_dict(), 'G.ckpt')
+torch.save(D.state_dict(), 'D.ckpt')
\ No newline at end of file
diff --git a/tutorials/03-advanced/image_captioning/README.md b/tutorials/03-advanced/image_captioning/README.md
new file mode 100644
index 00000000..409b62b4
--- /dev/null
+++ b/tutorials/03-advanced/image_captioning/README.md
@@ -0,0 +1,59 @@
+# Image Captioning
+The goal of image captioning is to convert a given input image into a natural language description. The encoder-decoder framework is widely used for this task. The image encoder is a convolutional neural network (CNN). In this tutorial, we used [resnet-152](https://arxiv.org/abs/1512.03385) model pretrained on the [ILSVRC-2012-CLS](http://www.image-net.org/challenges/LSVRC/2012/) image classification dataset. The decoder is a long short-term memory (LSTM) network.
+
+
+
+#### Training phase
+For the encoder part, the pretrained CNN extracts the feature vector from a given input image. The feature vector is linearly transformed to have the same dimension as the input dimension of the LSTM network. For the decoder part, source and target texts are predefined. For example, if the image description is **"Giraffes standing next to each other"**, the source sequence is a list containing **['\', 'Giraffes', 'standing', 'next', 'to', 'each', 'other']** and the target sequence is a list containing **['Giraffes', 'standing', 'next', 'to', 'each', 'other', '\']**. Using these source and target sequences and the feature vector, the LSTM decoder is trained as a language model conditioned on the feature vector.
+
+#### Test phase
+In the test phase, the encoder part is almost same as the training phase. The only difference is that batchnorm layer uses moving average and variance instead of mini-batch statistics. This can be easily implemented using [encoder.eval()](https://github.com/yunjey/pytorch-tutorial/blob/master/tutorials/03-advanced/image_captioning/sample.py#L37). For the decoder part, there is a significant difference between the training phase and the test phase. In the test phase, the LSTM decoder can't see the image description. To deal with this problem, the LSTM decoder feeds back the previosly generated word to the next input. This can be implemented using a [for-loop](https://github.com/yunjey/pytorch-tutorial/blob/master/tutorials/03-advanced/image_captioning/model.py#L48).
+
+
+
+## Usage
+
+
+#### 1. Clone the repositories
+```bash
+git clone https://github.com/pdollar/coco.git
+cd coco/PythonAPI/
+make
+python setup.py build
+python setup.py install
+cd ../../
+git clone https://github.com/yunjey/pytorch-tutorial.git
+cd pytorch-tutorial/tutorials/03-advanced/image_captioning/
+```
+
+#### 2. Download the dataset
+
+```bash
+pip install -r requirements.txt
+chmod +x download.sh
+./download.sh
+```
+
+#### 3. Preprocessing
+
+```bash
+python build_vocab.py
+python resize.py
+```
+
+#### 4. Train the model
+
+```bash
+python train.py
+```
+
+#### 5. Test the model
+
+```bash
+python sample.py --image='png/example.png'
+```
+
+
+
+## Pretrained model
+If you do not want to train the model from scratch, you can use a pretrained model. You can download the pretrained model [here](https://www.dropbox.com/s/ne0ixz5d58ccbbz/pretrained_model.zip?dl=0) and the vocabulary file [here](https://www.dropbox.com/s/26adb7y9m98uisa/vocap.zip?dl=0). You should extract pretrained_model.zip to `./models/` and vocab.pkl to `./data/` using `unzip` command.
diff --git a/tutorials/09 - Image Captioning/build_vocab.py b/tutorials/03-advanced/image_captioning/build_vocab.py
similarity index 78%
rename from tutorials/09 - Image Captioning/build_vocab.py
rename to tutorials/03-advanced/image_captioning/build_vocab.py
index 612920a5..946b4afb 100644
--- a/tutorials/09 - Image Captioning/build_vocab.py
+++ b/tutorials/03-advanced/image_captioning/build_vocab.py
@@ -36,38 +36,37 @@ def build_vocab(json, threshold):
tokens = nltk.tokenize.word_tokenize(caption.lower())
counter.update(tokens)
- if i % 1000 == 0:
- print("[%d/%d] Tokenized the captions." %(i, len(ids)))
+ if (i+1) % 1000 == 0:
+ print("[{}/{}] Tokenized the captions.".format(i+1, len(ids)))
# If the word frequency is less than 'threshold', then the word is discarded.
words = [word for word, cnt in counter.items() if cnt >= threshold]
- # Creates a vocab wrapper and add some special tokens.
+ # Create a vocab wrapper and add some special tokens.
vocab = Vocabulary()
vocab.add_word('')
vocab.add_word('')
vocab.add_word('')
vocab.add_word('')
- # Adds the words to the vocabulary.
+ # Add the words to the vocabulary.
for i, word in enumerate(words):
vocab.add_word(word)
return vocab
def main(args):
- vocab = build_vocab(json=args.caption_path,
- threshold=args.threshold)
+ vocab = build_vocab(json=args.caption_path, threshold=args.threshold)
vocab_path = args.vocab_path
with open(vocab_path, 'wb') as f:
- pickle.dump(vocab, f, pickle.HIGHEST_PROTOCOL)
- print("Total vocabulary size: %d" %len(vocab))
- print("Saved the vocabulary wrapper to '%s'" %vocab_path)
+ pickle.dump(vocab, f)
+ print("Total vocabulary size: {}".format(len(vocab)))
+ print("Saved the vocabulary wrapper to '{}'".format(vocab_path))
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('--caption_path', type=str,
- default='./data/annotations/captions_train2014.json',
+ default='data/annotations/captions_train2014.json',
help='path for train annotation file')
parser.add_argument('--vocab_path', type=str, default='./data/vocab.pkl',
help='path for saving vocabulary wrapper')
diff --git a/tutorials/09 - Image Captioning/data_loader.py b/tutorials/03-advanced/image_captioning/data_loader.py
similarity index 92%
rename from tutorials/09 - Image Captioning/data_loader.py
rename to tutorials/03-advanced/image_captioning/data_loader.py
index 165b3fed..0f0ef301 100644
--- a/tutorials/09 - Image Captioning/data_loader.py
+++ b/tutorials/03-advanced/image_captioning/data_loader.py
@@ -84,7 +84,6 @@ def collate_fn(data):
targets[i, :end] = cap[:end]
return images, targets, lengths
-
def get_loader(root, json, vocab, transform, batch_size, shuffle, num_workers):
"""Returns torch.utils.data.DataLoader for custom coco dataset."""
# COCO caption dataset
@@ -94,10 +93,10 @@ def get_loader(root, json, vocab, transform, batch_size, shuffle, num_workers):
transform=transform)
# Data loader for COCO dataset
- # This will return (images, captions, lengths) for every iteration.
- # images: tensor of shape (batch_size, 3, 224, 224).
- # captions: tensor of shape (batch_size, padded_length).
- # lengths: list indicating valid length for each caption. length is (batch_size).
+ # This will return (images, captions, lengths) for each iteration.
+ # images: a tensor of shape (batch_size, 3, 224, 224).
+ # captions: a tensor of shape (batch_size, padded_length).
+ # lengths: a list indicating valid length for each caption. length is (batch_size).
data_loader = torch.utils.data.DataLoader(dataset=coco,
batch_size=batch_size,
shuffle=shuffle,
diff --git a/tutorials/09 - Image Captioning/download.sh b/tutorials/03-advanced/image_captioning/download.sh
similarity index 68%
rename from tutorials/09 - Image Captioning/download.sh
rename to tutorials/03-advanced/image_captioning/download.sh
index 751c87d6..dace6aad 100755
--- a/tutorials/09 - Image Captioning/download.sh
+++ b/tutorials/03-advanced/image_captioning/download.sh
@@ -1,7 +1,7 @@
mkdir data
wget http://msvocds.blob.core.windows.net/annotations-1-0-3/captions_train-val2014.zip -P ./data/
-wget http://msvocds.blob.core.windows.net/coco2014/train2014.zip -P ./data/
-wget http://msvocds.blob.core.windows.net/coco2014/val2014.zip -P ./data/
+wget http://images.cocodataset.org/zips/train2014.zip -P ./data/
+wget http://images.cocodataset.org/zips/val2014.zip -P ./data/
unzip ./data/captions_train-val2014.zip -d ./data/
rm ./data/captions_train-val2014.zip
diff --git a/tutorials/09 - Image Captioning/model.py b/tutorials/03-advanced/image_captioning/model.py
similarity index 53%
rename from tutorials/09 - Image Captioning/model.py
rename to tutorials/03-advanced/image_captioning/model.py
index e79fa02a..b1aef0cd 100644
--- a/tutorials/09 - Image Captioning/model.py
+++ b/tutorials/03-advanced/image_captioning/model.py
@@ -2,46 +2,35 @@
import torch.nn as nn
import torchvision.models as models
from torch.nn.utils.rnn import pack_padded_sequence
-from torch.autograd import Variable
class EncoderCNN(nn.Module):
def __init__(self, embed_size):
"""Load the pretrained ResNet-152 and replace top fc layer."""
super(EncoderCNN, self).__init__()
- self.resnet = models.resnet152(pretrained=True)
- for param in self.resnet.parameters():
- param.requires_grad = False
- self.resnet.fc = nn.Linear(self.resnet.fc.in_features, embed_size)
+ resnet = models.resnet152(pretrained=True)
+ modules = list(resnet.children())[:-1] # delete the last fc layer.
+ self.resnet = nn.Sequential(*modules)
+ self.linear = nn.Linear(resnet.fc.in_features, embed_size)
self.bn = nn.BatchNorm1d(embed_size, momentum=0.01)
- self.init_weights()
-
- def init_weights(self):
- """Initialize the weights."""
- self.resnet.fc.weight.data.normal_(0.0, 0.02)
- self.resnet.fc.bias.data.fill_(0)
def forward(self, images):
- """Extract the image feature vectors."""
- features = self.resnet(images)
- features = self.bn(features)
+ """Extract feature vectors from input images."""
+ with torch.no_grad():
+ features = self.resnet(images)
+ features = features.reshape(features.size(0), -1)
+ features = self.bn(self.linear(features))
return features
-
-
+
+
class DecoderRNN(nn.Module):
- def __init__(self, embed_size, hidden_size, vocab_size, num_layers):
+ def __init__(self, embed_size, hidden_size, vocab_size, num_layers, max_seq_length=20):
"""Set the hyper-parameters and build the layers."""
super(DecoderRNN, self).__init__()
self.embed = nn.Embedding(vocab_size, embed_size)
self.lstm = nn.LSTM(embed_size, hidden_size, num_layers, batch_first=True)
self.linear = nn.Linear(hidden_size, vocab_size)
- self.init_weights()
-
- def init_weights(self):
- """Initialize weights."""
- self.embed.weight.data.uniform_(-0.1, 0.1)
- self.linear.weight.data.uniform_(-0.1, 0.1)
- self.linear.bias.data.fill_(0)
+ self.max_seg_length = max_seq_length
def forward(self, features, captions, lengths):
"""Decode image feature vectors and generates captions."""
@@ -52,15 +41,16 @@ def forward(self, features, captions, lengths):
outputs = self.linear(hiddens[0])
return outputs
- def sample(self, features, states):
- """Samples captions for given image features (Greedy search)."""
+ def sample(self, features, states=None):
+ """Generate captions for given image features using greedy search."""
sampled_ids = []
inputs = features.unsqueeze(1)
- for i in range(20): # maximum sampling length
- hiddens, states = self.lstm(inputs, states) # (batch_size, 1, hidden_size)
- outputs = self.linear(hiddens.squeeze(1)) # (batch_size, vocab_size)
- predicted = outputs.max(1)[1]
+ for i in range(self.max_seg_length):
+ hiddens, states = self.lstm(inputs, states) # hiddens: (batch_size, 1, hidden_size)
+ outputs = self.linear(hiddens.squeeze(1)) # outputs: (batch_size, vocab_size)
+ _, predicted = outputs.max(1) # predicted: (batch_size)
sampled_ids.append(predicted)
- inputs = self.embed(predicted)
- sampled_ids = torch.cat(sampled_ids, 1) # (batch_size, 20)
- return sampled_ids.squeeze()
\ No newline at end of file
+ inputs = self.embed(predicted) # inputs: (batch_size, embed_size)
+ inputs = inputs.unsqueeze(1) # inputs: (batch_size, 1, embed_size)
+ sampled_ids = torch.stack(sampled_ids, 1) # sampled_ids: (batch_size, max_seq_length)
+ return sampled_ids
\ No newline at end of file
diff --git a/tutorials/03-advanced/image_captioning/png/example.png b/tutorials/03-advanced/image_captioning/png/example.png
new file mode 100644
index 00000000..810228d8
Binary files /dev/null and b/tutorials/03-advanced/image_captioning/png/example.png differ
diff --git a/tutorials/03-advanced/image_captioning/png/image_captioning.png b/tutorials/03-advanced/image_captioning/png/image_captioning.png
new file mode 100644
index 00000000..2aceadd3
Binary files /dev/null and b/tutorials/03-advanced/image_captioning/png/image_captioning.png differ
diff --git a/tutorials/03-advanced/image_captioning/png/model.png b/tutorials/03-advanced/image_captioning/png/model.png
new file mode 100644
index 00000000..4fc7c7ab
Binary files /dev/null and b/tutorials/03-advanced/image_captioning/png/model.png differ
diff --git a/tutorials/09 - Image Captioning/requirements.txt b/tutorials/03-advanced/image_captioning/requirements.txt
similarity index 100%
rename from tutorials/09 - Image Captioning/requirements.txt
rename to tutorials/03-advanced/image_captioning/requirements.txt
diff --git a/tutorials/09 - Image Captioning/resize.py b/tutorials/03-advanced/image_captioning/resize.py
similarity index 76%
rename from tutorials/09 - Image Captioning/resize.py
rename to tutorials/03-advanced/image_captioning/resize.py
index 783a8245..5620b0d4 100644
--- a/tutorials/09 - Image Captioning/resize.py
+++ b/tutorials/03-advanced/image_captioning/resize.py
@@ -19,17 +19,15 @@ def resize_images(image_dir, output_dir, size):
with Image.open(f) as img:
img = resize_image(img, size)
img.save(os.path.join(output_dir, image), img.format)
- if i % 100 == 0:
- print ("[%d/%d] Resized the images and saved into '%s'."
- %(i, num_images, output_dir))
+ if (i+1) % 100 == 0:
+ print ("[{}/{}] Resized the images and saved into '{}'."
+ .format(i+1, num_images, output_dir))
def main(args):
- splits = ['train', 'val']
- for split in splits:
- image_dir = args.image_dir
- output_dir = args.output_dir
- image_size = [args.image_size, args.image_size]
- resize_images(image_dir, output_dir, image_size)
+ image_dir = args.image_dir
+ output_dir = args.output_dir
+ image_size = [args.image_size, args.image_size]
+ resize_images(image_dir, output_dir, image_size)
if __name__ == '__main__':
diff --git a/tutorials/03-advanced/image_captioning/sample.py b/tutorials/03-advanced/image_captioning/sample.py
new file mode 100644
index 00000000..74ff40fe
--- /dev/null
+++ b/tutorials/03-advanced/image_captioning/sample.py
@@ -0,0 +1,81 @@
+import torch
+import matplotlib.pyplot as plt
+import numpy as np
+import argparse
+import pickle
+import os
+from torchvision import transforms
+from build_vocab import Vocabulary
+from model import EncoderCNN, DecoderRNN
+from PIL import Image
+
+
+# Device configuration
+device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+
+def load_image(image_path, transform=None):
+ image = Image.open(image_path).convert('RGB')
+ image = image.resize([224, 224], Image.LANCZOS)
+
+ if transform is not None:
+ image = transform(image).unsqueeze(0)
+
+ return image
+
+def main(args):
+ # Image preprocessing
+ transform = transforms.Compose([
+ transforms.ToTensor(),
+ transforms.Normalize((0.485, 0.456, 0.406),
+ (0.229, 0.224, 0.225))])
+
+ # Load vocabulary wrapper
+ with open(args.vocab_path, 'rb') as f:
+ vocab = pickle.load(f)
+
+ # Build models
+ encoder = EncoderCNN(args.embed_size).eval() # eval mode (batchnorm uses moving mean/variance)
+ decoder = DecoderRNN(args.embed_size, args.hidden_size, len(vocab), args.num_layers)
+ encoder = encoder.to(device)
+ decoder = decoder.to(device)
+
+ # Load the trained model parameters
+ encoder.load_state_dict(torch.load(args.encoder_path))
+ decoder.load_state_dict(torch.load(args.decoder_path))
+
+ # Prepare an image
+ image = load_image(args.image, transform)
+ image_tensor = image.to(device)
+
+ # Generate an caption from the image
+ feature = encoder(image_tensor)
+ sampled_ids = decoder.sample(feature)
+ sampled_ids = sampled_ids[0].cpu().numpy() # (1, max_seq_length) -> (max_seq_length)
+
+ # Convert word_ids to words
+ sampled_caption = []
+ for word_id in sampled_ids:
+ word = vocab.idx2word[word_id]
+ sampled_caption.append(word)
+ if word == '':
+ break
+ sentence = ' '.join(sampled_caption)
+
+ # Print out the image and the generated caption
+ print (sentence)
+ image = Image.open(args.image)
+ plt.imshow(np.asarray(image))
+
+if __name__ == '__main__':
+ parser = argparse.ArgumentParser()
+ parser.add_argument('--image', type=str, required=True, help='input image for generating caption')
+ parser.add_argument('--encoder_path', type=str, default='models/encoder-5-3000.pkl', help='path for trained encoder')
+ parser.add_argument('--decoder_path', type=str, default='models/decoder-5-3000.pkl', help='path for trained decoder')
+ parser.add_argument('--vocab_path', type=str, default='data/vocab.pkl', help='path for vocabulary wrapper')
+
+ # Model parameters (should be same as paramters in train.py)
+ parser.add_argument('--embed_size', type=int , default=256, help='dimension of word embedding vectors')
+ parser.add_argument('--hidden_size', type=int , default=512, help='dimension of lstm hidden states')
+ parser.add_argument('--num_layers', type=int , default=1, help='number of layers in lstm')
+ args = parser.parse_args()
+ main(args)
diff --git a/tutorials/03-advanced/image_captioning/train.py b/tutorials/03-advanced/image_captioning/train.py
new file mode 100644
index 00000000..73007637
--- /dev/null
+++ b/tutorials/03-advanced/image_captioning/train.py
@@ -0,0 +1,101 @@
+import argparse
+import torch
+import torch.nn as nn
+import numpy as np
+import os
+import pickle
+from data_loader import get_loader
+from build_vocab import Vocabulary
+from model import EncoderCNN, DecoderRNN
+from torch.nn.utils.rnn import pack_padded_sequence
+from torchvision import transforms
+
+
+# Device configuration
+device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+
+def main(args):
+ # Create model directory
+ if not os.path.exists(args.model_path):
+ os.makedirs(args.model_path)
+
+ # Image preprocessing, normalization for the pretrained resnet
+ transform = transforms.Compose([
+ transforms.RandomCrop(args.crop_size),
+ transforms.RandomHorizontalFlip(),
+ transforms.ToTensor(),
+ transforms.Normalize((0.485, 0.456, 0.406),
+ (0.229, 0.224, 0.225))])
+
+ # Load vocabulary wrapper
+ with open(args.vocab_path, 'rb') as f:
+ vocab = pickle.load(f)
+
+ # Build data loader
+ data_loader = get_loader(args.image_dir, args.caption_path, vocab,
+ transform, args.batch_size,
+ shuffle=True, num_workers=args.num_workers)
+
+ # Build the models
+ encoder = EncoderCNN(args.embed_size).to(device)
+ decoder = DecoderRNN(args.embed_size, args.hidden_size, len(vocab), args.num_layers).to(device)
+
+ # Loss and optimizer
+ criterion = nn.CrossEntropyLoss()
+ params = list(decoder.parameters()) + list(encoder.linear.parameters()) + list(encoder.bn.parameters())
+ optimizer = torch.optim.Adam(params, lr=args.learning_rate)
+
+ # Train the models
+ total_step = len(data_loader)
+ for epoch in range(args.num_epochs):
+ for i, (images, captions, lengths) in enumerate(data_loader):
+
+ # Set mini-batch dataset
+ images = images.to(device)
+ captions = captions.to(device)
+ targets = pack_padded_sequence(captions, lengths, batch_first=True)[0]
+
+ # Forward, backward and optimize
+ features = encoder(images)
+ outputs = decoder(features, captions, lengths)
+ loss = criterion(outputs, targets)
+ decoder.zero_grad()
+ encoder.zero_grad()
+ loss.backward()
+ optimizer.step()
+
+ # Print log info
+ if i % args.log_step == 0:
+ print('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}, Perplexity: {:5.4f}'
+ .format(epoch, args.num_epochs, i, total_step, loss.item(), np.exp(loss.item())))
+
+ # Save the model checkpoints
+ if (i+1) % args.save_step == 0:
+ torch.save(decoder.state_dict(), os.path.join(
+ args.model_path, 'decoder-{}-{}.ckpt'.format(epoch+1, i+1)))
+ torch.save(encoder.state_dict(), os.path.join(
+ args.model_path, 'encoder-{}-{}.ckpt'.format(epoch+1, i+1)))
+
+
+if __name__ == '__main__':
+ parser = argparse.ArgumentParser()
+ parser.add_argument('--model_path', type=str, default='models/' , help='path for saving trained models')
+ parser.add_argument('--crop_size', type=int, default=224 , help='size for randomly cropping images')
+ parser.add_argument('--vocab_path', type=str, default='data/vocab.pkl', help='path for vocabulary wrapper')
+ parser.add_argument('--image_dir', type=str, default='data/resized2014', help='directory for resized images')
+ parser.add_argument('--caption_path', type=str, default='data/annotations/captions_train2014.json', help='path for train annotation json file')
+ parser.add_argument('--log_step', type=int , default=10, help='step size for prining log info')
+ parser.add_argument('--save_step', type=int , default=1000, help='step size for saving trained models')
+
+ # Model parameters
+ parser.add_argument('--embed_size', type=int , default=256, help='dimension of word embedding vectors')
+ parser.add_argument('--hidden_size', type=int , default=512, help='dimension of lstm hidden states')
+ parser.add_argument('--num_layers', type=int , default=1, help='number of layers in lstm')
+
+ parser.add_argument('--num_epochs', type=int, default=5)
+ parser.add_argument('--batch_size', type=int, default=128)
+ parser.add_argument('--num_workers', type=int, default=2)
+ parser.add_argument('--learning_rate', type=float, default=0.001)
+ args = parser.parse_args()
+ print(args)
+ main(args)
\ No newline at end of file
diff --git a/tutorials/03-advanced/neural_style_transfer/README.md b/tutorials/03-advanced/neural_style_transfer/README.md
new file mode 100644
index 00000000..579a6d22
--- /dev/null
+++ b/tutorials/03-advanced/neural_style_transfer/README.md
@@ -0,0 +1,33 @@
+# Neural Style Transfer
+
+[Neural style transfer](https://arxiv.org/abs/1508.06576) is an algorithm that combines the content of one image with the style of another image using CNN. Given a content image and a style image, the goal is to generate a target image that minimizes the content difference with the content image and the style difference with the style image.
+
+
+
+
+#### Content loss
+
+To minimize the content difference, we forward propagate the content image and the target image to pretrained [VGGNet](https://arxiv.org/abs/1409.1556) respectively, and extract feature maps from multiple convolutional layers. Then, the target image is updated to minimize the [mean-squared error](https://github.com/yunjey/pytorch-tutorial/blob/master/tutorials/03-advanced/neural_style_transfer/main.py#L81-L82) between the feature maps of the content image and its feature maps.
+
+#### Style loss
+
+As in computing the content loss, we forward propagate the style image and the target image to the VGGNet and extract convolutional feature maps. To generate a texture that matches the style of the style image, we update the target image by minimizing the mean-squared error between the Gram matrix of the style image and the Gram matrix of the target image (feature correlation minimization). See [here](https://github.com/yunjey/pytorch-tutorial/blob/master/tutorials/03-advanced/neural_style_transfer/main.py#L84-L94) for how to compute the style loss.
+
+
+
+
+
+
+## Usage
+
+```bash
+$ pip install -r requirements.txt
+$ python main.py --content='png/content.png' --style='png/style.png'
+```
+
+
+
+## Results
+The following is the result of applying variaous styles of artwork to Anne Hathaway's photograph.
+
+
diff --git a/tutorials/03-advanced/neural_style_transfer/main.py b/tutorials/03-advanced/neural_style_transfer/main.py
new file mode 100644
index 00000000..99153ee7
--- /dev/null
+++ b/tutorials/03-advanced/neural_style_transfer/main.py
@@ -0,0 +1,126 @@
+from __future__ import division
+from torchvision import models
+from torchvision import transforms
+from PIL import Image
+import argparse
+import torch
+import torchvision
+import torch.nn as nn
+import numpy as np
+
+
+# Device configuration
+device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+
+def load_image(image_path, transform=None, max_size=None, shape=None):
+ """Load an image and convert it to a torch tensor."""
+ image = Image.open(image_path)
+
+ if max_size:
+ scale = max_size / max(image.size)
+ size = np.array(image.size) * scale
+ image = image.resize(size.astype(int), Image.ANTIALIAS)
+
+ if shape:
+ image = image.resize(shape, Image.LANCZOS)
+
+ if transform:
+ image = transform(image).unsqueeze(0)
+
+ return image.to(device)
+
+
+class VGGNet(nn.Module):
+ def __init__(self):
+ """Select conv1_1 ~ conv5_1 activation maps."""
+ super(VGGNet, self).__init__()
+ self.select = ['0', '5', '10', '19', '28']
+ self.vgg = models.vgg19(pretrained=True).features
+
+ def forward(self, x):
+ """Extract multiple convolutional feature maps."""
+ features = []
+ for name, layer in self.vgg._modules.items():
+ x = layer(x)
+ if name in self.select:
+ features.append(x)
+ return features
+
+
+def main(config):
+
+ # Image preprocessing
+ # VGGNet was trained on ImageNet where images are normalized by mean=[0.485, 0.456, 0.406] and std=[0.229, 0.224, 0.225].
+ # We use the same normalization statistics here.
+ transform = transforms.Compose([
+ transforms.ToTensor(),
+ transforms.Normalize(mean=(0.485, 0.456, 0.406),
+ std=(0.229, 0.224, 0.225))])
+
+ # Load content and style images
+ # Make the style image same size as the content image
+ content = load_image(config.content, transform, max_size=config.max_size)
+ style = load_image(config.style, transform, shape=[content.size(2), content.size(3)])
+
+ # Initialize a target image with the content image
+ target = content.clone().requires_grad_(True)
+
+ optimizer = torch.optim.Adam([target], lr=config.lr, betas=[0.5, 0.999])
+ vgg = VGGNet().to(device).eval()
+
+ for step in range(config.total_step):
+
+ # Extract multiple(5) conv feature vectors
+ target_features = vgg(target)
+ content_features = vgg(content)
+ style_features = vgg(style)
+
+ style_loss = 0
+ content_loss = 0
+ for f1, f2, f3 in zip(target_features, content_features, style_features):
+ # Compute content loss with target and content images
+ content_loss += torch.mean((f1 - f2)**2)
+
+ # Reshape convolutional feature maps
+ _, c, h, w = f1.size()
+ f1 = f1.view(c, h * w)
+ f3 = f3.view(c, h * w)
+
+ # Compute gram matrix
+ f1 = torch.mm(f1, f1.t())
+ f3 = torch.mm(f3, f3.t())
+
+ # Compute style loss with target and style images
+ style_loss += torch.mean((f1 - f3)**2) / (c * h * w)
+
+ # Compute total loss, backprop and optimize
+ loss = content_loss + config.style_weight * style_loss
+ optimizer.zero_grad()
+ loss.backward()
+ optimizer.step()
+
+ if (step+1) % config.log_step == 0:
+ print ('Step [{}/{}], Content Loss: {:.4f}, Style Loss: {:.4f}'
+ .format(step+1, config.total_step, content_loss.item(), style_loss.item()))
+
+ if (step+1) % config.sample_step == 0:
+ # Save the generated image
+ denorm = transforms.Normalize((-2.12, -2.04, -1.80), (4.37, 4.46, 4.44))
+ img = target.clone().squeeze()
+ img = denorm(img).clamp_(0, 1)
+ torchvision.utils.save_image(img, 'output-{}.png'.format(step+1))
+
+
+if __name__ == "__main__":
+ parser = argparse.ArgumentParser()
+ parser.add_argument('--content', type=str, default='png/content.png')
+ parser.add_argument('--style', type=str, default='png/style.png')
+ parser.add_argument('--max_size', type=int, default=400)
+ parser.add_argument('--total_step', type=int, default=2000)
+ parser.add_argument('--log_step', type=int, default=10)
+ parser.add_argument('--sample_step', type=int, default=500)
+ parser.add_argument('--style_weight', type=float, default=100)
+ parser.add_argument('--lr', type=float, default=0.003)
+ config = parser.parse_args()
+ print(config)
+ main(config)
\ No newline at end of file
diff --git a/tutorials/03-advanced/neural_style_transfer/png/content.png b/tutorials/03-advanced/neural_style_transfer/png/content.png
new file mode 100644
index 00000000..96889a0a
Binary files /dev/null and b/tutorials/03-advanced/neural_style_transfer/png/content.png differ
diff --git a/tutorials/03-advanced/neural_style_transfer/png/neural_style.png b/tutorials/03-advanced/neural_style_transfer/png/neural_style.png
new file mode 100644
index 00000000..0f5eacd3
Binary files /dev/null and b/tutorials/03-advanced/neural_style_transfer/png/neural_style.png differ
diff --git a/tutorials/03-advanced/neural_style_transfer/png/neural_style2.png b/tutorials/03-advanced/neural_style_transfer/png/neural_style2.png
new file mode 100644
index 00000000..92bfe817
Binary files /dev/null and b/tutorials/03-advanced/neural_style_transfer/png/neural_style2.png differ
diff --git a/tutorials/03-advanced/neural_style_transfer/png/style.png b/tutorials/03-advanced/neural_style_transfer/png/style.png
new file mode 100644
index 00000000..e7d9b4cb
Binary files /dev/null and b/tutorials/03-advanced/neural_style_transfer/png/style.png differ
diff --git a/tutorials/03-advanced/neural_style_transfer/png/style2.png b/tutorials/03-advanced/neural_style_transfer/png/style2.png
new file mode 100644
index 00000000..eb7df210
Binary files /dev/null and b/tutorials/03-advanced/neural_style_transfer/png/style2.png differ
diff --git a/tutorials/03-advanced/neural_style_transfer/png/style3.png b/tutorials/03-advanced/neural_style_transfer/png/style3.png
new file mode 100644
index 00000000..0260be25
Binary files /dev/null and b/tutorials/03-advanced/neural_style_transfer/png/style3.png differ
diff --git a/tutorials/03-advanced/neural_style_transfer/png/style4.png b/tutorials/03-advanced/neural_style_transfer/png/style4.png
new file mode 100644
index 00000000..c62fdb35
Binary files /dev/null and b/tutorials/03-advanced/neural_style_transfer/png/style4.png differ
diff --git a/tutorials/03-advanced/neural_style_transfer/requirements.txt b/tutorials/03-advanced/neural_style_transfer/requirements.txt
new file mode 100644
index 00000000..131621d9
--- /dev/null
+++ b/tutorials/03-advanced/neural_style_transfer/requirements.txt
@@ -0,0 +1,4 @@
+argparse
+torch
+torchvision
+Pillow
diff --git a/tutorials/03-advanced/variational_autoencoder/main.py b/tutorials/03-advanced/variational_autoencoder/main.py
new file mode 100644
index 00000000..fe476d83
--- /dev/null
+++ b/tutorials/03-advanced/variational_autoencoder/main.py
@@ -0,0 +1,101 @@
+import os
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+import torchvision
+from torchvision import transforms
+from torchvision.utils import save_image
+
+
+# Device configuration
+device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+
+# Create a directory if not exists
+sample_dir = 'samples'
+if not os.path.exists(sample_dir):
+ os.makedirs(sample_dir)
+
+# Hyper-parameters
+image_size = 784
+h_dim = 400
+z_dim = 20
+num_epochs = 15
+batch_size = 128
+learning_rate = 1e-3
+
+# MNIST dataset
+dataset = torchvision.datasets.MNIST(root='../../data',
+ train=True,
+ transform=transforms.ToTensor(),
+ download=True)
+
+# Data loader
+data_loader = torch.utils.data.DataLoader(dataset=dataset,
+ batch_size=batch_size,
+ shuffle=True)
+
+
+# VAE model
+class VAE(nn.Module):
+ def __init__(self, image_size=784, h_dim=400, z_dim=20):
+ super(VAE, self).__init__()
+ self.fc1 = nn.Linear(image_size, h_dim)
+ self.fc2 = nn.Linear(h_dim, z_dim)
+ self.fc3 = nn.Linear(h_dim, z_dim)
+ self.fc4 = nn.Linear(z_dim, h_dim)
+ self.fc5 = nn.Linear(h_dim, image_size)
+
+ def encode(self, x):
+ h = F.relu(self.fc1(x))
+ return self.fc2(h), self.fc3(h)
+
+ def reparameterize(self, mu, log_var):
+ std = torch.exp(log_var/2)
+ eps = torch.randn_like(std)
+ return mu + eps * std
+
+ def decode(self, z):
+ h = F.relu(self.fc4(z))
+ return F.sigmoid(self.fc5(h))
+
+ def forward(self, x):
+ mu, log_var = self.encode(x)
+ z = self.reparameterize(mu, log_var)
+ x_reconst = self.decode(z)
+ return x_reconst, mu, log_var
+
+model = VAE().to(device)
+optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
+
+# Start training
+for epoch in range(num_epochs):
+ for i, (x, _) in enumerate(data_loader):
+ # Forward pass
+ x = x.to(device).view(-1, image_size)
+ x_reconst, mu, log_var = model(x)
+
+ # Compute reconstruction loss and kl divergence
+ # For KL divergence, see Appendix B in VAE paper or http://yunjey47.tistory.com/43
+ reconst_loss = F.binary_cross_entropy(x_reconst, x, size_average=False)
+ kl_div = - 0.5 * torch.sum(1 + log_var - mu.pow(2) - log_var.exp())
+
+ # Backprop and optimize
+ loss = reconst_loss + kl_div
+ optimizer.zero_grad()
+ loss.backward()
+ optimizer.step()
+
+ if (i+1) % 10 == 0:
+ print ("Epoch[{}/{}], Step [{}/{}], Reconst Loss: {:.4f}, KL Div: {:.4f}"
+ .format(epoch+1, num_epochs, i+1, len(data_loader), reconst_loss.item(), kl_div.item()))
+
+ with torch.no_grad():
+ # Save the sampled images
+ z = torch.randn(batch_size, z_dim).to(device)
+ out = model.decode(z).view(-1, 1, 28, 28)
+ save_image(out, os.path.join(sample_dir, 'sampled-{}.png'.format(epoch+1)))
+
+ # Save the reconstructed images
+ out, _, _ = model(x)
+ x_concat = torch.cat([x.view(-1, 1, 28, 28), out.view(-1, 1, 28, 28)], dim=3)
+ save_image(x_concat, os.path.join(sample_dir, 'reconst-{}.png'.format(epoch+1)))
\ No newline at end of file
diff --git a/tutorials/04 - Convolutional Neural Network/main-gpu.py b/tutorials/04 - Convolutional Neural Network/main-gpu.py
deleted file mode 100644
index 25b434a0..00000000
--- a/tutorials/04 - Convolutional Neural Network/main-gpu.py
+++ /dev/null
@@ -1,93 +0,0 @@
-import torch
-import torch.nn as nn
-import torchvision.datasets as dsets
-import torchvision.transforms as transforms
-from torch.autograd import Variable
-
-
-# Hyper Parameters
-num_epochs = 5
-batch_size = 100
-learning_rate = 0.001
-
-# MNIST Dataset
-train_dataset = dsets.MNIST(root='../data/',
- train=True,
- transform=transforms.ToTensor(),
- download=True)
-
-test_dataset = dsets.MNIST(root='../data/',
- train=False,
- transform=transforms.ToTensor())
-
-# Data Loader (Input Pipeline)
-train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
- batch_size=batch_size,
- shuffle=True)
-
-test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
- batch_size=batch_size,
- shuffle=False)
-
-# CNN Model (2 conv layer)
-class CNN(nn.Module):
- def __init__(self):
- super(CNN, self).__init__()
- self.layer1 = nn.Sequential(
- nn.Conv2d(1, 16, kernel_size=5, padding=2),
- nn.BatchNorm2d(16),
- nn.ReLU(),
- nn.MaxPool2d(2))
- self.layer2 = nn.Sequential(
- nn.Conv2d(16, 32, kernel_size=5, padding=2),
- nn.BatchNorm2d(32),
- nn.ReLU(),
- nn.MaxPool2d(2))
- self.fc = nn.Linear(7*7*32, 10)
-
- def forward(self, x):
- out = self.layer1(x)
- out = self.layer2(out)
- out = out.view(out.size(0), -1)
- out = self.fc(out)
- return out
-
-cnn = CNN()
-cnn.cuda()
-
-# Loss and Optimizer
-criterion = nn.CrossEntropyLoss()
-optimizer = torch.optim.Adam(cnn.parameters(), lr=learning_rate)
-
-# Train the Model
-for epoch in range(num_epochs):
- for i, (images, labels) in enumerate(train_loader):
- images = Variable(images).cuda()
- labels = Variable(labels).cuda()
-
- # Forward + Backward + Optimize
- optimizer.zero_grad()
- outputs = cnn(images)
- loss = criterion(outputs, labels)
- loss.backward()
- optimizer.step()
-
- if (i+1) % 100 == 0:
- print ('Epoch [%d/%d], Iter [%d/%d] Loss: %.4f'
- %(epoch+1, num_epochs, i+1, len(train_dataset)//batch_size, loss.data[0]))
-
-# Test the Model
-cnn.eval() # Change model to 'eval' mode (BN uses moving mean/var).
-correct = 0
-total = 0
-for images, labels in test_loader:
- images = Variable(images).cuda()
- outputs = cnn(images)
- _, predicted = torch.max(outputs.data, 1)
- total += labels.size(0)
- correct += (predicted.cpu() == labels).sum()
-
-print('Test Accuracy of the model on the 10000 test images: %d %%' % (100 * correct / total))
-
-# Save the Trained Model
-torch.save(cnn.state_dict(), 'cnn.pkl')
\ No newline at end of file
diff --git a/tutorials/04 - Convolutional Neural Network/main.py b/tutorials/04 - Convolutional Neural Network/main.py
deleted file mode 100644
index 070e4fce..00000000
--- a/tutorials/04 - Convolutional Neural Network/main.py
+++ /dev/null
@@ -1,93 +0,0 @@
-import torch
-import torch.nn as nn
-import torchvision.datasets as dsets
-import torchvision.transforms as transforms
-from torch.autograd import Variable
-
-
-# Hyper Parameters
-num_epochs = 5
-batch_size = 100
-learning_rate = 0.001
-
-# MNIST Dataset
-train_dataset = dsets.MNIST(root='../data/',
- train=True,
- transform=transforms.ToTensor(),
- download=True)
-
-test_dataset = dsets.MNIST(root='../data/',
- train=False,
- transform=transforms.ToTensor())
-
-# Data Loader (Input Pipeline)
-train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
- batch_size=batch_size,
- shuffle=True)
-
-test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
- batch_size=batch_size,
- shuffle=False)
-
-# CNN Model (2 conv layer)
-class CNN(nn.Module):
- def __init__(self):
- super(CNN, self).__init__()
- self.layer1 = nn.Sequential(
- nn.Conv2d(1, 16, kernel_size=5, padding=2),
- nn.BatchNorm2d(16),
- nn.ReLU(),
- nn.MaxPool2d(2))
- self.layer2 = nn.Sequential(
- nn.Conv2d(16, 32, kernel_size=5, padding=2),
- nn.BatchNorm2d(32),
- nn.ReLU(),
- nn.MaxPool2d(2))
- self.fc = nn.Linear(7*7*32, 10)
-
- def forward(self, x):
- out = self.layer1(x)
- out = self.layer2(out)
- out = out.view(out.size(0), -1)
- out = self.fc(out)
- return out
-
-cnn = CNN()
-
-
-# Loss and Optimizer
-criterion = nn.CrossEntropyLoss()
-optimizer = torch.optim.Adam(cnn.parameters(), lr=learning_rate)
-
-# Train the Model
-for epoch in range(num_epochs):
- for i, (images, labels) in enumerate(train_loader):
- images = Variable(images)
- labels = Variable(labels)
-
- # Forward + Backward + Optimize
- optimizer.zero_grad()
- outputs = cnn(images)
- loss = criterion(outputs, labels)
- loss.backward()
- optimizer.step()
-
- if (i+1) % 100 == 0:
- print ('Epoch [%d/%d], Iter [%d/%d] Loss: %.4f'
- %(epoch+1, num_epochs, i+1, len(train_dataset)//batch_size, loss.data[0]))
-
-# Test the Model
-cnn.eval() # Change model to 'eval' mode (BN uses moving mean/var).
-correct = 0
-total = 0
-for images, labels in test_loader:
- images = Variable(images)
- outputs = cnn(images)
- _, predicted = torch.max(outputs.data, 1)
- total += labels.size(0)
- correct += (predicted == labels).sum()
-
-print('Test Accuracy of the model on the 10000 test images: %d %%' % (100 * correct / total))
-
-# Save the Trained Model
-torch.save(cnn.state_dict(), 'cnn.pkl')
\ No newline at end of file
diff --git a/tutorials/04-utils/tensorboard/README.md b/tutorials/04-utils/tensorboard/README.md
new file mode 100644
index 00000000..90781485
--- /dev/null
+++ b/tutorials/04-utils/tensorboard/README.md
@@ -0,0 +1,25 @@
+# TensorBoard in PyTorch
+
+In this tutorial, we implement a MNIST classifier using a simple neural network and visualize the training process using [TensorBoard](https://www.tensorflow.org/get_started/summaries_and_tensorboard). In training phase, we plot the loss and accuracy functions through `scalar_summary` and visualize the training images through `image_summary`. In addition, we visualize the weight and gradient values of the parameters of the neural network using `histogram_summary`. PyTorch code for handling these summary functions can be found [here](https://github.com/yunjey/pytorch-tutorial/blob/master/tutorials/04-utils/tensorboard/main.py#L81-L97).
+
+
+
+
+
+## Usage
+
+#### 1. Install the dependencies
+```bash
+$ pip install -r requirements.txt
+```
+
+#### 2. Train the model
+```bash
+$ python main.py
+```
+
+#### 3. Open the TensorBoard
+To run the TensorBoard, open a new terminal and run the command below. Then, open http://localhost:6006/ on your web browser.
+```bash
+$ tensorboard --logdir='./logs' --port=6006
+```
diff --git a/tutorials/04-utils/tensorboard/gif/tensorboard.gif b/tutorials/04-utils/tensorboard/gif/tensorboard.gif
new file mode 100644
index 00000000..d6ac6099
Binary files /dev/null and b/tutorials/04-utils/tensorboard/gif/tensorboard.gif differ
diff --git a/tutorials/04-utils/tensorboard/logger.py b/tutorials/04-utils/tensorboard/logger.py
new file mode 100644
index 00000000..d872817e
--- /dev/null
+++ b/tutorials/04-utils/tensorboard/logger.py
@@ -0,0 +1,71 @@
+# Code referenced from https://gist.github.com/gyglim/1f8dfb1b5c82627ae3efcfbbadb9f514
+import tensorflow as tf
+import numpy as np
+import scipy.misc
+try:
+ from StringIO import StringIO # Python 2.7
+except ImportError:
+ from io import BytesIO # Python 3.x
+
+
+class Logger(object):
+
+ def __init__(self, log_dir):
+ """Create a summary writer logging to log_dir."""
+ self.writer = tf.summary.FileWriter(log_dir)
+
+ def scalar_summary(self, tag, value, step):
+ """Log a scalar variable."""
+ summary = tf.Summary(value=[tf.Summary.Value(tag=tag, simple_value=value)])
+ self.writer.add_summary(summary, step)
+
+ def image_summary(self, tag, images, step):
+ """Log a list of images."""
+
+ img_summaries = []
+ for i, img in enumerate(images):
+ # Write the image to a string
+ try:
+ s = StringIO()
+ except:
+ s = BytesIO()
+ scipy.misc.toimage(img).save(s, format="png")
+
+ # Create an Image object
+ img_sum = tf.Summary.Image(encoded_image_string=s.getvalue(),
+ height=img.shape[0],
+ width=img.shape[1])
+ # Create a Summary value
+ img_summaries.append(tf.Summary.Value(tag='%s/%d' % (tag, i), image=img_sum))
+
+ # Create and write Summary
+ summary = tf.Summary(value=img_summaries)
+ self.writer.add_summary(summary, step)
+
+ def histo_summary(self, tag, values, step, bins=1000):
+ """Log a histogram of the tensor of values."""
+
+ # Create a histogram using numpy
+ counts, bin_edges = np.histogram(values, bins=bins)
+
+ # Fill the fields of the histogram proto
+ hist = tf.HistogramProto()
+ hist.min = float(np.min(values))
+ hist.max = float(np.max(values))
+ hist.num = int(np.prod(values.shape))
+ hist.sum = float(np.sum(values))
+ hist.sum_squares = float(np.sum(values**2))
+
+ # Drop the start of the first bin
+ bin_edges = bin_edges[1:]
+
+ # Add bin edges and counts
+ for edge in bin_edges:
+ hist.bucket_limit.append(edge)
+ for c in counts:
+ hist.bucket.append(c)
+
+ # Create and write Summary
+ summary = tf.Summary(value=[tf.Summary.Value(tag=tag, histo=hist)])
+ self.writer.add_summary(summary, step)
+ self.writer.flush()
\ No newline at end of file
diff --git a/tutorials/04-utils/tensorboard/main.py b/tutorials/04-utils/tensorboard/main.py
new file mode 100644
index 00000000..b72f6292
--- /dev/null
+++ b/tutorials/04-utils/tensorboard/main.py
@@ -0,0 +1,97 @@
+import torch
+import torch.nn as nn
+import torchvision
+from torchvision import transforms
+from logger import Logger
+
+
+# Device configuration
+device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+
+# MNIST dataset
+dataset = torchvision.datasets.MNIST(root='../../data',
+ train=True,
+ transform=transforms.ToTensor(),
+ download=True)
+
+# Data loader
+data_loader = torch.utils.data.DataLoader(dataset=dataset,
+ batch_size=100,
+ shuffle=True)
+
+
+# Fully connected neural network with one hidden layer
+class NeuralNet(nn.Module):
+ def __init__(self, input_size=784, hidden_size=500, num_classes=10):
+ super(NeuralNet, self).__init__()
+ self.fc1 = nn.Linear(input_size, hidden_size)
+ self.relu = nn.ReLU()
+ self.fc2 = nn.Linear(hidden_size, num_classes)
+
+ def forward(self, x):
+ out = self.fc1(x)
+ out = self.relu(out)
+ out = self.fc2(out)
+ return out
+
+model = NeuralNet().to(device)
+
+logger = Logger('./logs')
+
+# Loss and optimizer
+criterion = nn.CrossEntropyLoss()
+optimizer = torch.optim.Adam(model.parameters(), lr=0.00001)
+
+data_iter = iter(data_loader)
+iter_per_epoch = len(data_loader)
+total_step = 50000
+
+# Start training
+for step in range(total_step):
+
+ # Reset the data_iter
+ if (step+1) % iter_per_epoch == 0:
+ data_iter = iter(data_loader)
+
+ # Fetch images and labels
+ images, labels = next(data_iter)
+ images, labels = images.view(images.size(0), -1).to(device), labels.to(device)
+
+ # Forward pass
+ outputs = model(images)
+ loss = criterion(outputs, labels)
+
+ # Backward and optimize
+ optimizer.zero_grad()
+ loss.backward()
+ optimizer.step()
+
+ # Compute accuracy
+ _, argmax = torch.max(outputs, 1)
+ accuracy = (labels == argmax.squeeze()).float().mean()
+
+ if (step+1) % 100 == 0:
+ print ('Step [{}/{}], Loss: {:.4f}, Acc: {:.2f}'
+ .format(step+1, total_step, loss.item(), accuracy.item()))
+
+ # ================================================================== #
+ # Tensorboard Logging #
+ # ================================================================== #
+
+ # 1. Log scalar values (scalar summary)
+ info = { 'loss': loss.item(), 'accuracy': accuracy.item() }
+
+ for tag, value in info.items():
+ logger.scalar_summary(tag, value, step+1)
+
+ # 2. Log values and gradients of the parameters (histogram summary)
+ for tag, value in model.named_parameters():
+ tag = tag.replace('.', '/')
+ logger.histo_summary(tag, value.data.cpu().numpy(), step+1)
+ logger.histo_summary(tag+'/grad', value.grad.data.cpu().numpy(), step+1)
+
+ # 3. Log training images (image summary)
+ info = { 'images': images.view(-1, 28, 28)[:10].cpu().numpy() }
+
+ for tag, images in info.items():
+ logger.image_summary(tag, images, step+1)
\ No newline at end of file
diff --git a/tutorials/04-utils/tensorboard/requirements.txt b/tutorials/04-utils/tensorboard/requirements.txt
new file mode 100644
index 00000000..e74a2c9a
--- /dev/null
+++ b/tutorials/04-utils/tensorboard/requirements.txt
@@ -0,0 +1,5 @@
+tensorflow
+torch
+torchvision
+scipy
+numpy
diff --git a/tutorials/05 - Deep Residual Network/main.py b/tutorials/05 - Deep Residual Network/main.py
deleted file mode 100644
index 8b0a9496..00000000
--- a/tutorials/05 - Deep Residual Network/main.py
+++ /dev/null
@@ -1,147 +0,0 @@
-# Implementation of https://arxiv.org/pdf/1512.03385.pdf.
-# See section 4.2 for model architecture on CIFAR-10.
-# Some part of the code was referenced below.
-# https://github.com/pytorch/vision/blob/master/torchvision/models/resnet.py
-import torch
-import torch.nn as nn
-import torchvision.datasets as dsets
-import torchvision.transforms as transforms
-from torch.autograd import Variable
-
-# Image Preprocessing
-transform = transforms.Compose([
- transforms.Scale(40),
- transforms.RandomHorizontalFlip(),
- transforms.RandomCrop(32),
- transforms.ToTensor()])
-
-# CIFAR-10 Dataset
-train_dataset = dsets.CIFAR10(root='../data/',
- train=True,
- transform=transform,
- download=True)
-
-test_dataset = dsets.CIFAR10(root='../data/',
- train=False,
- transform=transforms.ToTensor())
-
-# Data Loader (Input Pipeline)
-train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
- batch_size=100,
- shuffle=True)
-
-test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
- batch_size=100,
- shuffle=False)
-
-# 3x3 Convolution
-def conv3x3(in_channels, out_channels, stride=1):
- return nn.Conv2d(in_channels, out_channels, kernel_size=3,
- stride=stride, padding=1, bias=False)
-
-# Residual Block
-class ResidualBlock(nn.Module):
- def __init__(self, in_channels, out_channels, stride=1, downsample=None):
- super(ResidualBlock, self).__init__()
- self.conv1 = conv3x3(in_channels, out_channels, stride)
- self.bn1 = nn.BatchNorm2d(out_channels)
- self.relu = nn.ReLU(inplace=True)
- self.conv2 = conv3x3(out_channels, out_channels)
- self.bn2 = nn.BatchNorm2d(out_channels)
- self.downsample = downsample
-
- def forward(self, x):
- residual = x
- out = self.conv1(x)
- out = self.bn1(out)
- out = self.relu(out)
- out = self.conv2(out)
- out = self.bn2(out)
- if self.downsample:
- residual = self.downsample(x)
- out += residual
- out = self.relu(out)
- return out
-
-# ResNet Module
-class ResNet(nn.Module):
- def __init__(self, block, layers, num_classes=10):
- super(ResNet, self).__init__()
- self.in_channels = 16
- self.conv = conv3x3(3, 16)
- self.bn = nn.BatchNorm2d(16)
- self.relu = nn.ReLU(inplace=True)
- self.layer1 = self.make_layer(block, 16, layers[0])
- self.layer2 = self.make_layer(block, 32, layers[0], 2)
- self.layer3 = self.make_layer(block, 64, layers[1], 2)
- self.avg_pool = nn.AvgPool2d(8)
- self.fc = nn.Linear(64, num_classes)
-
- def make_layer(self, block, out_channels, blocks, stride=1):
- downsample = None
- if (stride != 1) or (self.in_channels != out_channels):
- downsample = nn.Sequential(
- conv3x3(self.in_channels, out_channels, stride=stride),
- nn.BatchNorm2d(out_channels))
- layers = []
- layers.append(block(self.in_channels, out_channels, stride, downsample))
- self.in_channels = out_channels
- for i in range(1, blocks):
- layers.append(block(out_channels, out_channels))
- return nn.Sequential(*layers)
-
- def forward(self, x):
- out = self.conv(x)
- out = self.bn(out)
- out = self.relu(out)
- out = self.layer1(out)
- out = self.layer2(out)
- out = self.layer3(out)
- out = self.avg_pool(out)
- out = out.view(out.size(0), -1)
- out = self.fc(out)
- return out
-
-resnet = ResNet(ResidualBlock, [2, 2, 2, 2])
-
-
-# Loss and Optimizer
-criterion = nn.CrossEntropyLoss()
-lr = 0.001
-optimizer = torch.optim.Adam(resnet.parameters(), lr=lr)
-
-# Training
-for epoch in range(80):
- for i, (images, labels) in enumerate(train_loader):
- images = Variable(images)
- labels = Variable(labels)
-
- # Forward + Backward + Optimize
- optimizer.zero_grad()
- outputs = resnet(images)
- loss = criterion(outputs, labels)
- loss.backward()
- optimizer.step()
-
- if (i+1) % 100 == 0:
- print ("Epoch [%d/%d], Iter [%d/%d] Loss: %.4f" %(epoch+1, 80, i+1, 500, loss.data[0]))
-
- # Decaying Learning Rate
- if (epoch+1) % 20 == 0:
- lr /= 3
- optimizer = torch.optim.Adam(resnet.parameters(), lr=lr)
-
-# Test
-correct = 0
-total = 0
-for images, labels in test_loader:
- images = Variable(images)
- outputs = resnet(images)
- _, predicted = torch.max(outputs.data, 1)
- total += labels.size(0)
- correct += (predicted == labels).sum()
-
-print('Accuracy of the model on the test images: %d %%' % (100 * correct / total))
-
-# Save the Model
-torch.save(resnet.state_dict(), 'resnet.pkl')
\ No newline at end of file
diff --git a/tutorials/06 - Recurrent Neural Network/main-gpu.py b/tutorials/06 - Recurrent Neural Network/main-gpu.py
deleted file mode 100644
index cef2a95d..00000000
--- a/tutorials/06 - Recurrent Neural Network/main-gpu.py
+++ /dev/null
@@ -1,95 +0,0 @@
-import torch
-import torch.nn as nn
-import torchvision.datasets as dsets
-import torchvision.transforms as transforms
-from torch.autograd import Variable
-
-
-# Hyper Parameters
-sequence_length = 28
-input_size = 28
-hidden_size = 128
-num_layers = 2
-num_classes = 10
-batch_size = 100
-num_epochs = 2
-learning_rate = 0.01
-
-# MNIST Dataset
-train_dataset = dsets.MNIST(root='../data/',
- train=True,
- transform=transforms.ToTensor(),
- download=True)
-
-test_dataset = dsets.MNIST(root='../data/',
- train=False,
- transform=transforms.ToTensor())
-
-# Data Loader (Input Pipeline)
-train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
- batch_size=batch_size,
- shuffle=True)
-
-test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
- batch_size=batch_size,
- shuffle=False)
-
-# RNN Model (Many-to-One)
-class RNN(nn.Module):
- def __init__(self, input_size, hidden_size, num_layers, num_classes):
- super(RNN, self).__init__()
- self.hidden_size = hidden_size
- self.num_layers = num_layers
- self.lstm = nn.LSTM(input_size, hidden_size, num_layers, batch_first=True)
- self.fc = nn.Linear(hidden_size, num_classes)
-
- def forward(self, x):
- # Set initial states
- h0 = Variable(torch.zeros(self.num_layers, x.size(0), self.hidden_size).cuda())
- c0 = Variable(torch.zeros(self.num_layers, x.size(0), self.hidden_size).cuda())
-
- # Forward propagate RNN
- out, _ = self.lstm(x, (h0, c0))
-
- # Decode hidden state of last time step
- out = self.fc(out[:, -1, :])
- return out
-
-rnn = RNN(input_size, hidden_size, num_layers, num_classes)
-rnn.cuda()
-
-# Loss and Optimizer
-criterion = nn.CrossEntropyLoss()
-optimizer = torch.optim.Adam(rnn.parameters(), lr=learning_rate)
-
-# Train the Model
-for epoch in range(num_epochs):
- for i, (images, labels) in enumerate(train_loader):
- images = Variable(images.view(-1, sequence_length, input_size)).cuda()
- labels = Variable(labels).cuda()
-
- # Forward + Backward + Optimize
- optimizer.zero_grad()
- outputs = rnn(images)
- loss = criterion(outputs, labels)
- loss.backward()
- optimizer.step()
-
- if (i+1) % 100 == 0:
- print ('Epoch [%d/%d], Step [%d/%d], Loss: %.4f'
- %(epoch+1, num_epochs, i+1, len(train_dataset)//batch_size, loss.data[0]))
-
-# Test the Model
-correct = 0
-total = 0
-for images, labels in test_loader:
- images = Variable(images.view(-1, sequence_length, input_size)).cuda()
- outputs = rnn(images)
- _, predicted = torch.max(outputs.data, 1)
- total += labels.size(0)
- correct += (predicted.cpu() == labels).sum()
-
-print('Test Accuracy of the model on the 10000 test images: %d %%' % (100 * correct / total))
-
-# Save the Model
-torch.save(rnn.state_dict(), 'rnn.pkl')
\ No newline at end of file
diff --git a/tutorials/06 - Recurrent Neural Network/main.py b/tutorials/06 - Recurrent Neural Network/main.py
deleted file mode 100644
index a9cc1deb..00000000
--- a/tutorials/06 - Recurrent Neural Network/main.py
+++ /dev/null
@@ -1,95 +0,0 @@
-import torch
-import torch.nn as nn
-import torchvision.datasets as dsets
-import torchvision.transforms as transforms
-from torch.autograd import Variable
-
-
-# Hyper Parameters
-sequence_length = 28
-input_size = 28
-hidden_size = 128
-num_layers = 2
-num_classes = 10
-batch_size = 100
-num_epochs = 2
-learning_rate = 0.01
-
-# MNIST Dataset
-train_dataset = dsets.MNIST(root='../data/',
- train=True,
- transform=transforms.ToTensor(),
- download=True)
-
-test_dataset = dsets.MNIST(root='../data/',
- train=False,
- transform=transforms.ToTensor())
-
-# Data Loader (Input Pipeline)
-train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
- batch_size=batch_size,
- shuffle=True)
-
-test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
- batch_size=batch_size,
- shuffle=False)
-
-# RNN Model (Many-to-One)
-class RNN(nn.Module):
- def __init__(self, input_size, hidden_size, num_layers, num_classes):
- super(RNN, self).__init__()
- self.hidden_size = hidden_size
- self.num_layers = num_layers
- self.lstm = nn.LSTM(input_size, hidden_size, num_layers, batch_first=True)
- self.fc = nn.Linear(hidden_size, num_classes)
-
- def forward(self, x):
- # Set initial states
- h0 = Variable(torch.zeros(self.num_layers, x.size(0), self.hidden_size))
- c0 = Variable(torch.zeros(self.num_layers, x.size(0), self.hidden_size))
-
- # Forward propagate RNN
- out, _ = self.lstm(x, (h0, c0))
-
- # Decode hidden state of last time step
- out = self.fc(out[:, -1, :])
- return out
-
-rnn = RNN(input_size, hidden_size, num_layers, num_classes)
-
-
-# Loss and Optimizer
-criterion = nn.CrossEntropyLoss()
-optimizer = torch.optim.Adam(rnn.parameters(), lr=learning_rate)
-
-# Train the Model
-for epoch in range(num_epochs):
- for i, (images, labels) in enumerate(train_loader):
- images = Variable(images.view(-1, sequence_length, input_size))
- labels = Variable(labels)
-
- # Forward + Backward + Optimize
- optimizer.zero_grad()
- outputs = rnn(images)
- loss = criterion(outputs, labels)
- loss.backward()
- optimizer.step()
-
- if (i+1) % 100 == 0:
- print ('Epoch [%d/%d], Step [%d/%d], Loss: %.4f'
- %(epoch+1, num_epochs, i+1, len(train_dataset)//batch_size, loss.data[0]))
-
-# Test the Model
-correct = 0
-total = 0
-for images, labels in test_loader:
- images = Variable(images.view(-1, sequence_length, input_size))
- outputs = rnn(images)
- _, predicted = torch.max(outputs.data, 1)
- total += labels.size(0)
- correct += (predicted == labels).sum()
-
-print('Test Accuracy of the model on the 10000 test images: %d %%' % (100 * correct / total))
-
-# Save the Model
-torch.save(rnn.state_dict(), 'rnn.pkl')
\ No newline at end of file
diff --git a/tutorials/07 - Bidirectional Recurrent Neural Network/main-gpu.py b/tutorials/07 - Bidirectional Recurrent Neural Network/main-gpu.py
deleted file mode 100644
index ae7560a5..00000000
--- a/tutorials/07 - Bidirectional Recurrent Neural Network/main-gpu.py
+++ /dev/null
@@ -1,96 +0,0 @@
-import torch
-import torch.nn as nn
-import torchvision.datasets as dsets
-import torchvision.transforms as transforms
-from torch.autograd import Variable
-
-
-# Hyper Parameters
-sequence_length = 28
-input_size = 28
-hidden_size = 128
-num_layers = 2
-num_classes = 10
-batch_size = 100
-num_epochs = 2
-learning_rate = 0.003
-
-# MNIST Dataset
-train_dataset = dsets.MNIST(root='../data/',
- train=True,
- transform=transforms.ToTensor(),
- download=True)
-
-test_dataset = dsets.MNIST(root='../data/',
- train=False,
- transform=transforms.ToTensor())
-
-# Data Loader (Input Pipeline)
-train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
- batch_size=batch_size,
- shuffle=True)
-
-test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
- batch_size=batch_size,
- shuffle=False)
-
-# BiRNN Model (Many-to-One)
-class BiRNN(nn.Module):
- def __init__(self, input_size, hidden_size, num_layers, num_classes):
- super(BiRNN, self).__init__()
- self.hidden_size = hidden_size
- self.num_layers = num_layers
- self.lstm = nn.LSTM(input_size, hidden_size, num_layers,
- batch_first=True, bidirectional=True)
- self.fc = nn.Linear(hidden_size*2, num_classes) # 2 for bidirection
-
- def forward(self, x):
- # Set initial states
- h0 = Variable(torch.zeros(self.num_layers*2, x.size(0), self.hidden_size)).cuda() # 2 for bidirection
- c0 = Variable(torch.zeros(self.num_layers*2, x.size(0), self.hidden_size)).cuda()
-
- # Forward propagate RNN
- out, _ = self.lstm(x, (h0, c0))
-
- # Decode hidden state of last time step
- out = self.fc(out[:, -1, :])
- return out
-
-rnn = BiRNN(input_size, hidden_size, num_layers, num_classes)
-rnn.cuda()
-
-# Loss and Optimizer
-criterion = nn.CrossEntropyLoss()
-optimizer = torch.optim.Adam(rnn.parameters(), lr=learning_rate)
-
-# Train the Model
-for epoch in range(num_epochs):
- for i, (images, labels) in enumerate(train_loader):
- images = Variable(images.view(-1, sequence_length, input_size)).cuda()
- labels = Variable(labels).cuda()
-
- # Forward + Backward + Optimize
- optimizer.zero_grad()
- outputs = rnn(images)
- loss = criterion(outputs, labels)
- loss.backward()
- optimizer.step()
-
- if (i+1) % 100 == 0:
- print ('Epoch [%d/%d], Step [%d/%d], Loss: %.4f'
- %(epoch+1, num_epochs, i+1, len(train_dataset)//batch_size, loss.data[0]))
-
-# Test the Model
-correct = 0
-total = 0
-for images, labels in test_loader:
- images = Variable(images.view(-1, sequence_length, input_size)).cuda()
- outputs = rnn(images)
- _, predicted = torch.max(outputs.data, 1)
- total += labels.size(0)
- correct += (predicted.cpu() == labels).sum()
-
-print('Test Accuracy of the model on the 10000 test images: %d %%' % (100 * correct / total))
-
-# Save the Model
-torch.save(rnn.state_dict(), 'rnn.pkl')
\ No newline at end of file
diff --git a/tutorials/07 - Bidirectional Recurrent Neural Network/main.py b/tutorials/07 - Bidirectional Recurrent Neural Network/main.py
deleted file mode 100644
index 916184bb..00000000
--- a/tutorials/07 - Bidirectional Recurrent Neural Network/main.py
+++ /dev/null
@@ -1,96 +0,0 @@
-import torch
-import torch.nn as nn
-import torchvision.datasets as dsets
-import torchvision.transforms as transforms
-from torch.autograd import Variable
-
-
-# Hyper Parameters
-sequence_length = 28
-input_size = 28
-hidden_size = 128
-num_layers = 2
-num_classes = 10
-batch_size = 100
-num_epochs = 2
-learning_rate = 0.003
-
-# MNIST Dataset
-train_dataset = dsets.MNIST(root='../data/',
- train=True,
- transform=transforms.ToTensor(),
- download=True)
-
-test_dataset = dsets.MNIST(root='../data/',
- train=False,
- transform=transforms.ToTensor())
-
-# Data Loader (Input Pipeline)
-train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
- batch_size=batch_size,
- shuffle=True)
-
-test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
- batch_size=batch_size,
- shuffle=False)
-
-# BiRNN Model (Many-to-One)
-class BiRNN(nn.Module):
- def __init__(self, input_size, hidden_size, num_layers, num_classes):
- super(BiRNN, self).__init__()
- self.hidden_size = hidden_size
- self.num_layers = num_layers
- self.lstm = nn.LSTM(input_size, hidden_size, num_layers,
- batch_first=True, bidirectional=True)
- self.fc = nn.Linear(hidden_size*2, num_classes) # 2 for bidirection
-
- def forward(self, x):
- # Set initial states
- h0 = Variable(torch.zeros(self.num_layers*2, x.size(0), self.hidden_size)) # 2 for bidirection
- c0 = Variable(torch.zeros(self.num_layers*2, x.size(0), self.hidden_size))
-
- # Forward propagate RNN
- out, _ = self.lstm(x, (h0, c0))
-
- # Decode hidden state of last time step
- out = self.fc(out[:, -1, :])
- return out
-
-rnn = BiRNN(input_size, hidden_size, num_layers, num_classes)
-
-
-# Loss and Optimizer
-criterion = nn.CrossEntropyLoss()
-optimizer = torch.optim.Adam(rnn.parameters(), lr=learning_rate)
-
-# Train the Model
-for epoch in range(num_epochs):
- for i, (images, labels) in enumerate(train_loader):
- images = Variable(images.view(-1, sequence_length, input_size))
- labels = Variable(labels)
-
- # Forward + Backward + Optimize
- optimizer.zero_grad()
- outputs = rnn(images)
- loss = criterion(outputs, labels)
- loss.backward()
- optimizer.step()
-
- if (i+1) % 100 == 0:
- print ('Epoch [%d/%d], Step [%d/%d], Loss: %.4f'
- %(epoch+1, num_epochs, i+1, len(train_dataset)//batch_size, loss.data[0]))
-
-# Test the Model
-correct = 0
-total = 0
-for images, labels in test_loader:
- images = Variable(images.view(-1, sequence_length, input_size))
- outputs = rnn(images)
- _, predicted = torch.max(outputs.data, 1)
- total += labels.size(0)
- correct += (predicted == labels).sum()
-
-print('Test Accuracy of the model on the 10000 test images: %d %%' % (100 * correct / total))
-
-# Save the Model
-torch.save(rnn.state_dict(), 'rnn.pkl')
\ No newline at end of file
diff --git a/tutorials/08 - Language Model/main-gpu.py b/tutorials/08 - Language Model/main-gpu.py
deleted file mode 100644
index 3ee804ed..00000000
--- a/tutorials/08 - Language Model/main-gpu.py
+++ /dev/null
@@ -1,122 +0,0 @@
-# Some part of the code was referenced from below.
-# https://github.com/pytorch/examples/tree/master/word_language_model
-import torch
-import torch.nn as nn
-import numpy as np
-from torch.autograd import Variable
-from data_utils import Dictionary, Corpus
-
-# Hyper Parameters
-embed_size = 128
-hidden_size = 1024
-num_layers = 1
-num_epochs = 5
-num_samples = 1000 # number of words to be sampled
-batch_size = 20
-seq_length = 30
-learning_rate = 0.002
-
-# Load Penn Treebank Dataset
-train_path = './data/train.txt'
-sample_path = './sample.txt'
-corpus = Corpus()
-ids = corpus.get_data(train_path, batch_size)
-vocab_size = len(corpus.dictionary)
-num_batches = ids.size(1) // seq_length
-
-# RNN Based Language Model
-class RNNLM(nn.Module):
- def __init__(self, vocab_size, embed_size, hidden_size, num_layers):
- super(RNNLM, self).__init__()
- self.embed = nn.Embedding(vocab_size, embed_size)
- self.lstm = nn.LSTM(embed_size, hidden_size, num_layers, batch_first=True)
- self.linear = nn.Linear(hidden_size, vocab_size)
- self.init_weights()
-
- def init_weights(self):
- self.embed.weight.data.uniform_(-0.1, 0.1)
- self.linear.bias.data.fill_(0)
- self.linear.weight.data.uniform_(-0.1, 0.1)
-
- def forward(self, x, h):
- # Embed word ids to vectors
- x = self.embed(x)
-
- # Forward propagate RNN
- out, h = self.lstm(x, h)
-
- # Reshape output to (batch_size*sequence_length, hidden_size)
- out = out.contiguous().view(out.size(0)*out.size(1), out.size(2))
-
- # Decode hidden states of all time step
- out = self.linear(out)
- return out, h
-
-model = RNNLM(vocab_size, embed_size, hidden_size, num_layers)
-model.cuda()
-
-# Loss and Optimizer
-criterion = nn.CrossEntropyLoss()
-optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
-
-# Truncated Backpropagation
-def detach(states):
- return [state.detach() for state in states]
-
-# Training
-for epoch in range(num_epochs):
- # Initial hidden and memory states
- states = (Variable(torch.zeros(num_layers, batch_size, hidden_size)).cuda(),
- Variable(torch.zeros(num_layers, batch_size, hidden_size)).cuda())
-
- for i in range(0, ids.size(1) - seq_length, seq_length):
- # Get batch inputs and targets
- inputs = Variable(ids[:, i:i+seq_length]).cuda()
- targets = Variable(ids[:, (i+1):(i+1)+seq_length].contiguous()).cuda()
-
- # Forward + Backward + Optimize
- model.zero_grad()
- states = detach(states)
- outputs, states = model(inputs, states)
- loss = criterion(outputs, targets.view(-1))
- loss.backward()
- torch.nn.utils.clip_grad_norm(model.parameters(), 0.5)
- optimizer.step()
-
- step = (i+1) // seq_length
- if step % 100 == 0:
- print ('Epoch [%d/%d], Step[%d/%d], Loss: %.3f, Perplexity: %5.2f' %
- (epoch+1, num_epochs, step, num_batches, loss.data[0], np.exp(loss.data[0])))
-
-# Sampling
-with open(sample_path, 'w') as f:
- # Set intial hidden ane memory states
- state = (Variable(torch.zeros(num_layers, 1, hidden_size)).cuda(),
- Variable(torch.zeros(num_layers, 1, hidden_size)).cuda())
-
- # Select one word id randomly
- prob = torch.ones(vocab_size)
- input = Variable(torch.multinomial(prob, num_samples=1).unsqueeze(1),
- volatile=True).cuda()
-
- for i in range(num_samples):
- # Forward propagate rnn
- output, state = model(input, state)
-
- # Sample a word id
- prob = output.squeeze().data.exp().cpu()
- word_id = torch.multinomial(prob, 1)[0]
-
- # Feed sampled word id to next time step
- input.data.fill_(word_id)
-
- # File write
- word = corpus.dictionary.idx2word[word_id]
- word = '\n' if word == '' else word + ' '
- f.write(word)
-
- if (i+1) % 100 == 0:
- print('Sampled [%d/%d] words and save to %s'%(i+1, num_samples, sample_path))
-
-# Save the Trained Model
-torch.save(model.state_dict(), 'model.pkl')
diff --git a/tutorials/08 - Language Model/main.py b/tutorials/08 - Language Model/main.py
deleted file mode 100644
index 77941986..00000000
--- a/tutorials/08 - Language Model/main.py
+++ /dev/null
@@ -1,122 +0,0 @@
-# Some part of the code was referenced from below.
-# https://github.com/pytorch/examples/tree/master/word_language_model
-import torch
-import torch.nn as nn
-import numpy as np
-from torch.autograd import Variable
-from data_utils import Dictionary, Corpus
-
-# Hyper Parameters
-embed_size = 128
-hidden_size = 1024
-num_layers = 1
-num_epochs = 5
-num_samples = 1000 # number of words to be sampled
-batch_size = 20
-seq_length = 30
-learning_rate = 0.002
-
-# Load Penn Treebank Dataset
-train_path = './data/train.txt'
-sample_path = './sample.txt'
-corpus = Corpus()
-ids = corpus.get_data(train_path, batch_size)
-vocab_size = len(corpus.dictionary)
-num_batches = ids.size(1) // seq_length
-
-# RNN Based Language Model
-class RNNLM(nn.Module):
- def __init__(self, vocab_size, embed_size, hidden_size, num_layers):
- super(RNNLM, self).__init__()
- self.embed = nn.Embedding(vocab_size, embed_size)
- self.lstm = nn.LSTM(embed_size, hidden_size, num_layers, batch_first=True)
- self.linear = nn.Linear(hidden_size, vocab_size)
- self.init_weights()
-
- def init_weights(self):
- self.embed.weight.data.uniform_(-0.1, 0.1)
- self.linear.bias.data.fill_(0)
- self.linear.weight.data.uniform_(-0.1, 0.1)
-
- def forward(self, x, h):
- # Embed word ids to vectors
- x = self.embed(x)
-
- # Forward propagate RNN
- out, h = self.lstm(x, h)
-
- # Reshape output to (batch_size*sequence_length, hidden_size)
- out = out.contiguous().view(out.size(0)*out.size(1), out.size(2))
-
- # Decode hidden states of all time step
- out = self.linear(out)
- return out, h
-
-model = RNNLM(vocab_size, embed_size, hidden_size, num_layers)
-
-
-# Loss and Optimizer
-criterion = nn.CrossEntropyLoss()
-optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
-
-# Truncated Backpropagation
-def detach(states):
- return [state.detach() for state in states]
-
-# Training
-for epoch in range(num_epochs):
- # Initial hidden and memory states
- states = (Variable(torch.zeros(num_layers, batch_size, hidden_size)),
- Variable(torch.zeros(num_layers, batch_size, hidden_size)))
-
- for i in range(0, ids.size(1) - seq_length, seq_length):
- # Get batch inputs and targets
- inputs = Variable(ids[:, i:i+seq_length])
- targets = Variable(ids[:, (i+1):(i+1)+seq_length].contiguous())
-
- # Forward + Backward + Optimize
- model.zero_grad()
- states = detach(states)
- outputs, states = model(inputs, states)
- loss = criterion(outputs, targets.view(-1))
- loss.backward()
- torch.nn.utils.clip_grad_norm(model.parameters(), 0.5)
- optimizer.step()
-
- step = (i+1) // seq_length
- if step % 100 == 0:
- print ('Epoch [%d/%d], Step[%d/%d], Loss: %.3f, Perplexity: %5.2f' %
- (epoch+1, num_epochs, step, num_batches, loss.data[0], np.exp(loss.data[0])))
-
-# Sampling
-with open(sample_path, 'w') as f:
- # Set intial hidden ane memory states
- state = (Variable(torch.zeros(num_layers, 1, hidden_size)),
- Variable(torch.zeros(num_layers, 1, hidden_size)))
-
- # Select one word id randomly
- prob = torch.ones(vocab_size)
- input = Variable(torch.multinomial(prob, num_samples=1).unsqueeze(1),
- volatile=True)
-
- for i in range(num_samples):
- # Forward propagate rnn
- output, state = model(input, state)
-
- # Sample a word id
- prob = output.squeeze().data.exp()
- word_id = torch.multinomial(prob, 1)[0]
-
- # Feed sampled word id to next time step
- input.data.fill_(word_id)
-
- # File write
- word = corpus.dictionary.idx2word[word_id]
- word = '\n' if word == '' else word + ' '
- f.write(word)
-
- if (i+1) % 100 == 0:
- print('Sampled [%d/%d] words and save to %s'%(i+1, num_samples, sample_path))
-
-# Save the Trained Model
-torch.save(model.state_dict(), 'model.pkl')
diff --git a/tutorials/09 - Image Captioning/README.md b/tutorials/09 - Image Captioning/README.md
deleted file mode 100644
index dc594a9f..00000000
--- a/tutorials/09 - Image Captioning/README.md
+++ /dev/null
@@ -1,48 +0,0 @@
-## Usage
-
-
-#### 1. Clone the repositories
-```bash
-$ git clone https://github.com/pdollar/coco.git
-$ cd coco/PythonAPI/
-$ make
-$ python setup.py build
-$ python setup.py install
-$ cd ../../
-$ git clone https://github.com/yunjey/pytorch-tutorial.git
-$ cd pytorch-tutorial/tutorials/09\ -\ Image\ Captioning
-```
-
-#### 2. Download the dataset
-
-```bash
-$ pip install -r requirements
-$ chmod +x download.sh
-$ ./download.sh
-```
-
-#### 3. Preprocessing
-
-```bash
-$ python build_vocab.py
-$ python resize.py
-```
-
-#### 4. Train the model
-
-```bash
-$ python train.py
-```
-
-#### 5. Generate captions
-
-
-```bash
-$ python sample.py --image='path_for_image'
-```
-
-
-
-## Pretrained model
-
-If you do not want to train the model yourself, you can use a pretrained model. I have provided the pretrained model as a zip file. You can download the file [here](https://www.dropbox.com/s/b7gyo15as6m6s7x/train_model.zip?dl=0) and extract it to `./models/` directory.
diff --git a/tutorials/09 - Image Captioning/sample.py b/tutorials/09 - Image Captioning/sample.py
deleted file mode 100644
index be8ee713..00000000
--- a/tutorials/09 - Image Captioning/sample.py
+++ /dev/null
@@ -1,91 +0,0 @@
-import torch
-import matplotlib.pyplot as plt
-import numpy as np
-import argparse
-import pickle
-import os
-from torch.autograd import Variable
-from torchvision import transforms
-from build_vocab import Vocabulary
-from model import EncoderCNN, DecoderRNN
-from PIL import Image
-
-
-def main(args):
- # Image preprocessing
- transform = transforms.Compose([
- transforms.Scale(args.crop_size),
- transforms.CenterCrop(args.crop_size),
- transforms.ToTensor(),
- transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])
-
- # Load vocabulary wrapper
- with open(args.vocab_path, 'rb') as f:
- vocab = pickle.load(f)
-
- # Build Models
- encoder = EncoderCNN(args.embed_size)
- encoder.eval() # evaluation mode (BN uses moving mean/variance)
- decoder = DecoderRNN(args.embed_size, args.hidden_size,
- len(vocab), args.num_layers)
-
-
- # Load the trained model parameters
- encoder.load_state_dict(torch.load(args.encoder_path))
- decoder.load_state_dict(torch.load(args.decoder_path))
-
- # Prepare Image
- image = Image.open(args.image)
- image_tensor = Variable(transform(image).unsqueeze(0))
-
- # Set initial states
- state = (Variable(torch.zeros(args.num_layers, 1, args.hidden_size)),
- Variable(torch.zeros(args.num_layers, 1, args.hidden_size)))
-
- # If use gpu
- if torch.cuda.is_available():
- encoder.cuda()
- decoder.cuda()
- state = [s.cuda() for s in state]
- image_tensor = image_tensor.cuda()
-
- # Generate caption from image
- feature = encoder(image_tensor)
- sampled_ids = decoder.sample(feature, state)
- sampled_ids = sampled_ids.cpu().data.numpy()
-
- # Decode word_ids to words
- sampled_caption = []
- for word_id in sampled_ids:
- word = vocab.idx2word[word_id]
- sampled_caption.append(word)
- if word == '':
- break
- sentence = ' '.join(sampled_caption)
-
- # Print out image and generated caption.
- print (sentence)
- plt.imshow(np.asarray(image))
-
-if __name__ == '__main__':
- parser = argparse.ArgumentParser()
- parser.add_argument('--image', type=str, required=True,
- help='input image for generating caption')
- parser.add_argument('--encoder_path', type=str, default='./models/encoder-5-3000.pkl',
- help='path for trained encoder')
- parser.add_argument('--decoder_path', type=str, default='./models/decoder-5-3000.pkl',
- help='path for trained decoder')
- parser.add_argument('--vocab_path', type=str, default='./data/vocab.pkl',
- help='path for vocabulary wrapper')
- parser.add_argument('--crop_size', type=int, default=224,
- help='size for center cropping images')
-
- # Model parameters (should be same as paramters in train.py)
- parser.add_argument('--embed_size', type=int , default=256,
- help='dimension of word embedding vectors')
- parser.add_argument('--hidden_size', type=int , default=512,
- help='dimension of lstm hidden states')
- parser.add_argument('--num_layers', type=int , default=1 ,
- help='number of layers in lstm')
- args = parser.parse_args()
- main(args)
\ No newline at end of file
diff --git a/tutorials/09 - Image Captioning/train.py b/tutorials/09 - Image Captioning/train.py
deleted file mode 100644
index 05578f5b..00000000
--- a/tutorials/09 - Image Captioning/train.py
+++ /dev/null
@@ -1,118 +0,0 @@
-import argparse
-import torch
-import torch.nn as nn
-import numpy as np
-import os
-from data_loader import get_loader
-from build_vocab import Vocabulary
-from model import EncoderCNN, DecoderRNN
-from torch.autograd import Variable
-from torch.nn.utils.rnn import pack_padded_sequence
-from torchvision import transforms
-
-
-def main(args):
- # Create model directory
- if not os.path.exists(args.model_path):
- os.makedirs(args.model_path)
-
- # Image preprocessing
- transform = transforms.Compose([
- transforms.RandomCrop(args.crop_size),
- transforms.RandomHorizontalFlip(),
- transforms.ToTensor(),
- transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])
-
- # Load vocabulary wrapper.
- with open(vocab_path, 'rb') as f:
- vocab = pickle.load(f)
-
- # Build data loader
- data_loader = get_loader(args.image_dir, args.caption_path, vocab,
- transform, args.batch_size,
- shuffle=True, num_workers=args.num_workers)
-
- # Build the models
- encoder = EncoderCNN(args.embed_size)
- decoder = DecoderRNN(args.embed_size, args.hidden_size,
- len(vocab), args.num_layers)
-
- if torch.cuda.is_available():
- encoder.cuda()
- decoder.cuda()
-
- # Loss and Optimizer
- criterion = nn.CrossEntropyLoss()
- params = list(decoder.parameters()) + list(encoder.resnet.fc.parameters())
- optimizer = torch.optim.Adam(params, lr=args.learning_rate)
-
- # Train the Models
- total_step = len(data_loader)
- for epoch in range(args.num_epochs):
- for i, (images, captions, lengths) in enumerate(data_loader):
-
- # Set mini-batch dataset
- images = Variable(images)
- captions = Variable(captions)
- if torch.cuda.is_available():
- images = images.cuda()
- captions = captions.cuda()
- targets = pack_padded_sequence(captions, lengths, batch_first=True)[0]
-
- # Forward, Backward and Optimize
- decoder.zero_grad()
- encoder.zero_grad()
- features = encoder(images)
- outputs = decoder(features, captions, lengths)
- loss = criterion(outputs, targets)
- loss.backward()
- optimizer.step()
-
- # Print log info
- if i % args.log_step == 0:
- print('Epoch [%d/%d], Step [%d/%d], Loss: %.4f, Perplexity: %5.4f'
- %(epoch, args.num_epochs, i, total_step,
- loss.data[0], np.exp(loss.data[0])))
-
- # Save the models
- if (i+1) % args.save_step == 0:
- torch.save(decoder.state_dict(),
- os.path.join(args.model_path,
- 'decoder-%d-%d.pkl' %(epoch+1, i+1)))
- torch.save(encoder.state_dict(),
- os.path.join(args.model_path,
- 'encoder-%d-%d.pkl' %(epoch+1, i+1)))
-
-if __name__ == '__main__':
- parser = argparse.ArgumentParser()
- parser.add_argument('--model_path', type=str, default='./models/' ,
- help='path for saving trained models')
- parser.add_argument('--crop_size', type=int, default=224 ,
- help='size for randomly cropping images')
- parser.add_argument('--vocab_path', type=str, default='./data/vocab.pkl',
- help='path for vocabulary wrapper')
- parser.add_argument('--image_dir', type=str, default='./data/resized2014' ,
- help='directory for resized images')
- parser.add_argument('--caption_path', type=str,
- default='./data/annotations/captions_train2014.json',
- help='path for train annotation json file')
- parser.add_argument('--log_step', type=int , default=10,
- help='step size for prining log info')
- parser.add_argument('--save_step', type=int , default=1000,
- help='step size for saving trained models')
-
- # Model parameters
- parser.add_argument('--embed_size', type=int , default=256 ,
- help='dimension of word embedding vectors')
- parser.add_argument('--hidden_size', type=int , default=512 ,
- help='dimension of lstm hidden states')
- parser.add_argument('--num_layers', type=int , default=1 ,
- help='number of layers in lstm')
-
- parser.add_argument('--num_epochs', type=int, default=5)
- parser.add_argument('--batch_size', type=int, default=128)
- parser.add_argument('--num_workers', type=int, default=2)
- parser.add_argument('--learning_rate', type=float, default=0.001)
- args = parser.parse_args()
- print(args)
- main(args)
\ No newline at end of file
diff --git a/tutorials/10 - Generative Adversarial Network/main-gpu.py b/tutorials/10 - Generative Adversarial Network/main-gpu.py
deleted file mode 100644
index bdb50ab0..00000000
--- a/tutorials/10 - Generative Adversarial Network/main-gpu.py
+++ /dev/null
@@ -1,110 +0,0 @@
-import torch
-import torchvision
-import torch.nn as nn
-import torch.nn.functional as F
-import torchvision.datasets as dsets
-import torchvision.transforms as transforms
-from torch.autograd import Variable
-
-# Image Preprocessing
-transform = transforms.Compose([
- transforms.ToTensor(),
- transforms.Normalize(mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5))])
-
-# MNIST Dataset
-train_dataset = dsets.MNIST(root='../data/',
- train=True,
- transform=transform,
- download=True)
-
-# Data Loader (Input Pipeline)
-train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
- batch_size=100,
- shuffle=True)
-
-# Discriminator Model
-class Discriminator(nn.Module):
- def __init__(self):
- super(Discriminator, self).__init__()
- self.fc1 = nn.Linear(784, 256)
- self.fc2 = nn.Linear(256, 256)
- self.fc3 = nn.Linear(256, 1)
-
- def forward(self, x):
- h = F.relu(self.fc1(x))
- h = F.relu(self.fc2(h))
- out = F.sigmoid(self.fc3(h))
- return out
-
-# Generator Model
-class Generator(nn.Module):
- def __init__(self):
- super(Generator, self).__init__()
- self.fc1 = nn.Linear(128, 256)
- self.fc2 = nn.Linear(256, 256)
- self.fc3 = nn.Linear(256, 784)
-
- def forward(self, x):
- h = F.leaky_relu(self.fc1(x))
- h = F.leaky_relu(self.fc2(h))
- out = F.tanh(self.fc3(h))
- return out
-
-discriminator = Discriminator()
-generator = Generator()
-discriminator.cuda()
-generator.cuda()
-
-# Loss and Optimizer
-criterion = nn.BCELoss()
-d_optimizer = torch.optim.Adam(discriminator.parameters(), lr=0.0005)
-g_optimizer = torch.optim.Adam(generator.parameters(), lr=0.0005)
-
-# Training
-for epoch in range(200):
- for i, (images, _) in enumerate(train_loader):
- # Build mini-batch dataset
- images = images.view(images.size(0), -1)
- images = Variable(images.cuda())
- real_labels = Variable(torch.ones(images.size(0))).cuda()
- fake_labels = Variable(torch.zeros(images.size(0))).cuda()
-
- # Train the discriminator
- discriminator.zero_grad()
- outputs = discriminator(images)
- real_loss = criterion(outputs, real_labels)
- real_score = outputs
-
- noise = Variable(torch.randn(images.size(0), 128)).cuda()
- fake_images = generator(noise)
- outputs = discriminator(fake_images.detach())
- fake_loss = criterion(outputs, fake_labels)
- fake_score = outputs
-
- d_loss = real_loss + fake_loss
- d_loss.backward()
- d_optimizer.step()
-
- # Train the generator
- generator.zero_grad()
- noise = Variable(torch.randn(images.size(0), 128)).cuda()
- fake_images = generator(noise)
- outputs = discriminator(fake_images)
- g_loss = criterion(outputs, real_labels)
- g_loss.backward()
- g_optimizer.step()
-
- if (i+1) % 300 == 0:
- print('Epoch [%d/%d], Step[%d/%d], d_loss: %.4f, g_loss: %.4f, '
- 'D(x): %.2f, D(G(z)): %.2f'
- %(epoch, 200, i+1, 600, d_loss.data[0], g_loss.data[0],
- real_score.cpu().data.mean(), fake_score.cpu().data.mean()))
-
- # Save the sampled images
- fake_images = fake_images.view(fake_images.size(0), 1, 28, 28)
- torchvision.utils.save_image(fake_images.data,
- './data/fake_samples_%d.png' %(epoch+1))
-
-# Save the Models
-torch.save(generator.state_dict(), './generator.pkl')
-torch.save(discriminator.state_dict(), './discriminator.pkl')
diff --git a/tutorials/10 - Generative Adversarial Network/main.py b/tutorials/10 - Generative Adversarial Network/main.py
deleted file mode 100644
index d1ceb27e..00000000
--- a/tutorials/10 - Generative Adversarial Network/main.py
+++ /dev/null
@@ -1,110 +0,0 @@
-import torch
-import torchvision
-import torch.nn as nn
-import torch.nn.functional as F
-import torchvision.datasets as dsets
-import torchvision.transforms as transforms
-from torch.autograd import Variable
-
-# Image Preprocessing
-transform = transforms.Compose([
- transforms.ToTensor(),
- transforms.Normalize(mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5))])
-
-# MNIST Dataset
-train_dataset = dsets.MNIST(root='../data/',
- train=True,
- transform=transform,
- download=True)
-
-# Data Loader (Input Pipeline)
-train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
- batch_size=100,
- shuffle=True)
-
-# Discriminator Model
-class Discriminator(nn.Module):
- def __init__(self):
- super(Discriminator, self).__init__()
- self.fc1 = nn.Linear(784, 256)
- self.fc2 = nn.Linear(256, 256)
- self.fc3 = nn.Linear(256, 1)
-
- def forward(self, x):
- h = F.relu(self.fc1(x))
- h = F.relu(self.fc2(h))
- out = F.sigmoid(self.fc3(h))
- return out
-
-# Generator Model
-class Generator(nn.Module):
- def __init__(self):
- super(Generator, self).__init__()
- self.fc1 = nn.Linear(128, 256)
- self.fc2 = nn.Linear(256, 256)
- self.fc3 = nn.Linear(256, 784)
-
- def forward(self, x):
- h = F.leaky_relu(self.fc1(x))
- h = F.leaky_relu(self.fc2(h))
- out = F.tanh(self.fc3(h))
- return out
-
-discriminator = Discriminator()
-generator = Generator()
-
-
-
-# Loss and Optimizer
-criterion = nn.BCELoss()
-d_optimizer = torch.optim.Adam(discriminator.parameters(), lr=0.0005)
-g_optimizer = torch.optim.Adam(generator.parameters(), lr=0.0005)
-
-# Training
-for epoch in range(200):
- for i, (images, _) in enumerate(train_loader):
- # Build mini-batch dataset
- images = images.view(images.size(0), -1)
- images = Variable(images)
- real_labels = Variable(torch.ones(images.size(0)))
- fake_labels = Variable(torch.zeros(images.size(0)))
-
- # Train the discriminator
- discriminator.zero_grad()
- outputs = discriminator(images)
- real_loss = criterion(outputs, real_labels)
- real_score = outputs
-
- noise = Variable(torch.randn(images.size(0), 128))
- fake_images = generator(noise)
- outputs = discriminator(fake_images.detach())
- fake_loss = criterion(outputs, fake_labels)
- fake_score = outputs
-
- d_loss = real_loss + fake_loss
- d_loss.backward()
- d_optimizer.step()
-
- # Train the generator
- generator.zero_grad()
- noise = Variable(torch.randn(images.size(0), 128))
- fake_images = generator(noise)
- outputs = discriminator(fake_images)
- g_loss = criterion(outputs, real_labels)
- g_loss.backward()
- g_optimizer.step()
-
- if (i+1) % 300 == 0:
- print('Epoch [%d/%d], Step[%d/%d], d_loss: %.4f, g_loss: %.4f, '
- 'D(x): %.2f, D(G(z)): %.2f'
- %(epoch, 200, i+1, 600, d_loss.data[0], g_loss.data[0],
- real_score.data.mean(), fake_score.cpu().data.mean()))
-
- # Save the sampled images
- fake_images = fake_images.view(fake_images.size(0), 1, 28, 28)
- torchvision.utils.save_image(fake_images.data,
- './data/fake_samples_%d.png' %(epoch+1))
-
-# Save the Models
-torch.save(generator.state_dict(), './generator.pkl')
-torch.save(discriminator.state_dict(), './discriminator.pkl')
diff --git a/tutorials/11 - Deep Convolutional Generative Adversarial Network/main-gpu.py b/tutorials/11 - Deep Convolutional Generative Adversarial Network/main-gpu.py
deleted file mode 100644
index ec31ba30..00000000
--- a/tutorials/11 - Deep Convolutional Generative Adversarial Network/main-gpu.py
+++ /dev/null
@@ -1,134 +0,0 @@
-import torch
-import torchvision
-import torch.nn as nn
-import torchvision.datasets as dsets
-import torchvision.transforms as transforms
-from torch.autograd import Variable
-
-# Image Preprocessing
-transform = transforms.Compose([
- transforms.Scale(36),
- transforms.RandomCrop(32),
- transforms.ToTensor(),
- transforms.Normalize(mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5))])
-
-# CIFAR-10 Dataset
-train_dataset = dsets.CIFAR10(root='../data/',
- train=True,
- transform=transform,
- download=True)
-
-# Data Loader (Input Pipeline)
-train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
- batch_size=100,
- shuffle=True)
-
-# 4x4 Convolution
-def conv4x4(in_channels, out_channels, stride):
- return nn.Conv2d(in_channels, out_channels, kernel_size=4,
- stride=stride, padding=1, bias=False)
-
-# Discriminator Model
-class Discriminator(nn.Module):
- def __init__(self):
- super(Discriminator, self).__init__()
- self.model = nn.Sequential(
- conv4x4(3, 16, 2),
- nn.LeakyReLU(0.2, inplace=True),
- conv4x4(16, 32, 2),
- nn.BatchNorm2d(32),
- nn.LeakyReLU(0.2, inplace=True),
- conv4x4(32, 64, 2),
- nn.BatchNorm2d(64),
- nn.LeakyReLU(0.2, inplace=True),
- nn.Conv2d(64, 1, kernel_size=4),
- nn.Sigmoid())
-
- def forward(self, x):
- out = self.model(x)
- out = out.view(out.size(0), -1)
- return out
-
-# 4x4 Transpose convolution
-def conv_transpose4x4(in_channels, out_channels, stride=1, padding=1, bias=False):
- return nn.ConvTranspose2d(in_channels, out_channels, kernel_size=4,
- stride=stride, padding=padding, bias=bias)
-
-# Generator Model
-class Generator(nn.Module):
- def __init__(self):
- super(Generator, self).__init__()
- self.model = nn.Sequential(
- conv_transpose4x4(128, 64, padding=0),
- nn.BatchNorm2d(64),
- nn.ReLU(inplace=True),
- conv_transpose4x4(64, 32, 2),
- nn.BatchNorm2d(32),
- nn.ReLU(inplace=True),
- conv_transpose4x4(32, 16, 2),
- nn.BatchNorm2d(16),
- nn.ReLU(inplace=True),
- conv_transpose4x4(16, 3, 2, bias=True),
- nn.Tanh())
-
- def forward(self, x):
- x = x.view(x.size(0), 128, 1, 1)
- out = self.model(x)
- return out
-
-discriminator = Discriminator()
-generator = Generator()
-discriminator.cuda()
-generator.cuda()
-
-# Loss and Optimizer
-criterion = nn.BCELoss()
-lr = 0.002
-d_optimizer = torch.optim.Adam(discriminator.parameters(), lr=lr)
-g_optimizer = torch.optim.Adam(generator.parameters(), lr=lr)
-
-# Training
-for epoch in range(50):
- for i, (images, _) in enumerate(train_loader):
- images = Variable(images.cuda())
- real_labels = Variable(torch.ones(images.size(0))).cuda()
- fake_labels = Variable(torch.zeros(images.size(0))).cuda()
-
- # Train the discriminator
- discriminator.zero_grad()
- outputs = discriminator(images)
- real_loss = criterion(outputs, real_labels)
- real_score = outputs
-
- noise = Variable(torch.randn(images.size(0), 128)).cuda()
- fake_images = generator(noise)
- outputs = discriminator(fake_images.detach())
- fake_loss = criterion(outputs, fake_labels)
- fake_score = outputs
-
- d_loss = real_loss + fake_loss
- d_loss.backward()
- d_optimizer.step()
-
- # Train the generator
- generator.zero_grad()
- noise = Variable(torch.randn(images.size(0), 128)).cuda()
- fake_images = generator(noise)
- outputs = discriminator(fake_images)
- g_loss = criterion(outputs, real_labels)
- g_loss.backward()
- g_optimizer.step()
-
- if (i+1) % 100 == 0:
- print('Epoch [%d/%d], Step[%d/%d], d_loss: %.4f, g_loss: %.4f, '
- 'D(x): %.2f, D(G(z)): %.2f'
- %(epoch, 50, i+1, 500, d_loss.data[0], g_loss.data[0],
- real_score.cpu().data.mean(), fake_score.cpu().data.mean()))
-
- # Save the sampled images
- torchvision.utils.save_image(fake_images.data,
- './data/fake_samples_%d_%d.png' %(epoch+1, i+1))
-
-# Save the Models
-torch.save(generator.state_dict(), './generator.pkl')
-torch.save(discriminator.state_dict(), './discriminator.pkl')
diff --git a/tutorials/11 - Deep Convolutional Generative Adversarial Network/main.py b/tutorials/11 - Deep Convolutional Generative Adversarial Network/main.py
deleted file mode 100644
index 101ef8f3..00000000
--- a/tutorials/11 - Deep Convolutional Generative Adversarial Network/main.py
+++ /dev/null
@@ -1,134 +0,0 @@
-import torch
-import torchvision
-import torch.nn as nn
-import torchvision.datasets as dsets
-import torchvision.transforms as transforms
-from torch.autograd import Variable
-
-# Image Preprocessing
-transform = transforms.Compose([
- transforms.Scale(36),
- transforms.RandomCrop(32),
- transforms.ToTensor(),
- transforms.Normalize(mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5))])
-
-# CIFAR-10 Dataset
-train_dataset = dsets.CIFAR10(root='../data/',
- train=True,
- transform=transform,
- download=True)
-
-# Data Loader (Input Pipeline)
-train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
- batch_size=100,
- shuffle=True)
-
-# 4x4 Convolution
-def conv4x4(in_channels, out_channels, stride):
- return nn.Conv2d(in_channels, out_channels, kernel_size=4,
- stride=stride, padding=1, bias=False)
-
-# Discriminator Model
-class Discriminator(nn.Module):
- def __init__(self):
- super(Discriminator, self).__init__()
- self.model = nn.Sequential(
- conv4x4(3, 16, 2),
- nn.LeakyReLU(0.2, inplace=True),
- conv4x4(16, 32, 2),
- nn.BatchNorm2d(32),
- nn.LeakyReLU(0.2, inplace=True),
- conv4x4(32, 64, 2),
- nn.BatchNorm2d(64),
- nn.LeakyReLU(0.2, inplace=True),
- nn.Conv2d(64, 1, kernel_size=4),
- nn.Sigmoid())
-
- def forward(self, x):
- out = self.model(x)
- out = out.view(out.size(0), -1)
- return out
-
-# 4x4 Transpose convolution
-def conv_transpose4x4(in_channels, out_channels, stride=1, padding=1, bias=False):
- return nn.ConvTranspose2d(in_channels, out_channels, kernel_size=4,
- stride=stride, padding=padding, bias=bias)
-
-# Generator Model
-class Generator(nn.Module):
- def __init__(self):
- super(Generator, self).__init__()
- self.model = nn.Sequential(
- conv_transpose4x4(128, 64, padding=0),
- nn.BatchNorm2d(64),
- nn.ReLU(inplace=True),
- conv_transpose4x4(64, 32, 2),
- nn.BatchNorm2d(32),
- nn.ReLU(inplace=True),
- conv_transpose4x4(32, 16, 2),
- nn.BatchNorm2d(16),
- nn.ReLU(inplace=True),
- conv_transpose4x4(16, 3, 2, bias=True),
- nn.Tanh())
-
- def forward(self, x):
- x = x.view(x.size(0), 128, 1, 1)
- out = self.model(x)
- return out
-
-discriminator = Discriminator()
-generator = Generator()
-
-
-
-# Loss and Optimizer
-criterion = nn.BCELoss()
-lr = 0.0002
-d_optimizer = torch.optim.Adam(discriminator.parameters(), lr=lr)
-g_optimizer = torch.optim.Adam(generator.parameters(), lr=lr)
-
-# Training
-for epoch in range(50):
- for i, (images, _) in enumerate(train_loader):
- images = Variable(images)
- real_labels = Variable(torch.ones(images.size(0)))
- fake_labels = Variable(torch.zeros(images.size(0)))
-
- # Train the discriminator
- discriminator.zero_grad()
- outputs = discriminator(images)
- real_loss = criterion(outputs, real_labels)
- real_score = outputs
-
- noise = Variable(torch.randn(images.size(0), 128))
- fake_images = generator(noise)
- outputs = discriminator(fake_images.detch())
- fake_loss = criterion(outputs, fake_labels)
- fake_score = outputs
-
- d_loss = real_loss + fake_loss
- d_loss.backward()
- d_optimizer.step()
-
- # Train the generator
- generator.zero_grad()
- noise = Variable(torch.randn(images.size(0), 128))
- fake_images = generator(noise)
- outputs = discriminator(fake_images)
- g_loss = criterion(outputs, real_labels)
- g_loss.backward()
- g_optimizer.step()
-
- if (i+1) % 100 == 0:
- print('Epoch [%d/%d], Step[%d/%d], d_loss: %.4f, g_loss: %.4f, '
- 'D(x): %.2f, D(G(z)): %.2f'
- %(epoch, 50, i+1, 500, d_loss.data[0], g_loss.data[0],
- real_score.data.mean(), fake_score.data.mean()))
-
- # Save the sampled images
- torchvision.utils.save_image(fake_images.data,
- './data/fake_samples_%d_%d.png' %(epoch+1, i+1))
-
-# Save the Models
-torch.save(generator.state_dict(), './generator.pkl')
-torch.save(discriminator.state_dict(), './discriminator.pkl')
diff --git a/tutorials/12 - Deep Q Network/dqn13.py b/tutorials/12 - Deep Q Network/dqn13.py
deleted file mode 100644
index 442b6099..00000000
--- a/tutorials/12 - Deep Q Network/dqn13.py
+++ /dev/null
@@ -1,124 +0,0 @@
-%matplotlib inline
-
-import torch
-import torch.nn as nn
-import gym
-import random
-import numpy as np
-import torchvision.transforms as transforms
-import matplotlib.pyplot as plt
-from torch.autograd import Variable
-from collections import deque, namedtuple
-
-env = gym.envs.make("CartPole-v0")
-
-class Net(nn.Module):
- def __init__(self):
- super(Net, self).__init__()
- self.fc1 = nn.Linear(4, 128)
- self.tanh = nn.Tanh()
- self.fc2 = nn.Linear(128, 2)
- self.init_weights()
-
- def init_weights(self):
- self.fc1.weight.data.uniform_(-0.1, 0.1)
- self.fc2.weight.data.uniform_(-0.1, 0.1)
-
- def forward(self, x):
- out = self.fc1(x)
- out = self.tanh(out)
- out = self.fc2(out)
- return out
-
-def make_epsilon_greedy_policy(network, epsilon, nA):
- def policy(state):
- sample = random.random()
- if sample < (1-epsilon) + (epsilon/nA):
- q_values = network(state.view(1, -1))
- action = q_values.data.max(1)[1][0, 0]
- else:
- action = random.randrange(nA)
- return action
- return policy
-
-class ReplayMemory(object):
-
- def __init__(self, capacity):
- self.memory = deque()
- self.capacity = capacity
-
- def push(self, transition):
- if len(self.memory) > self.capacity:
- self.memory.popleft()
- self.memory.append(transition)
-
- def sample(self, batch_size):
- return random.sample(self.memory, batch_size)
-
- def __len__(self):
- return len(self.memory)
-
-def to_tensor(ndarray, volatile=False):
- return Variable(torch.from_numpy(ndarray), volatile=volatile).float()
-
-def deep_q_learning(num_episodes=10, batch_size=100,
- discount_factor=0.95, epsilon=0.1, epsilon_decay=0.95):
-
- # Q-Network and memory
- net = Net()
- memory = ReplayMemory(10000)
-
- # Loss and Optimizer
- criterion = nn.MSELoss()
- optimizer = torch.optim.Adam(net.parameters(), lr=0.001)
-
- for i_episode in range(num_episodes):
-
- # Set policy (TODO: decaying epsilon)
- #if (i_episode+1) % 100 == 0:
- # epsilon *= 0.9
-
- policy = make_epsilon_greedy_policy(
- net, epsilon, env.action_space.n)
-
- # Start an episode
- state = env.reset()
-
- for t in range(10000):
-
- # Sample action from epsilon greed policy
- action = policy(to_tensor(state))
- next_state, reward, done, _ = env.step(action)
-
-
- # Restore transition in memory
- memory.push([state, action, reward, next_state])
-
-
- if len(memory) >= batch_size:
- # Sample mini-batch transitions from memory
- batch = memory.sample(batch_size)
- state_batch = np.vstack([trans[0] for trans in batch])
- action_batch =np.vstack([trans[1] for trans in batch])
- reward_batch = np.vstack([trans[2] for trans in batch])
- next_state_batch = np.vstack([trans[3] for trans in batch])
-
- # Forward + Backward + Opimize
- net.zero_grad()
- q_values = net(to_tensor(state_batch))
- next_q_values = net(to_tensor(next_state_batch, volatile=True))
- next_q_values.volatile = False
-
- td_target = to_tensor(reward_batch) + discount_factor * (next_q_values).max(1)[0]
- loss = criterion(q_values.gather(1,
- to_tensor(action_batch).long().view(-1, 1)), td_target)
- loss.backward()
- optimizer.step()
-
- if done:
- break
-
- state = next_state
-
- if len(memory) >= batch_size and (i_episode+1) % 10 == 0:
- print ('episode: %d, time: %d, loss: %.4f' %(i_episode, t, loss.data[0]))
\ No newline at end of file