diff --git a/.gitignore b/.gitignore
new file mode 100644
index 00000000..b6797577
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,4 @@
+.idea/
+*.pkl
+tutorials/data
+*__pycache__*
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/my-tutorials/cifar100.py b/my-tutorials/cifar100.py
new file mode 100644
index 00000000..5029f1bc
--- /dev/null
+++ b/my-tutorials/cifar100.py
@@ -0,0 +1,78 @@
+"""
+CIFAR100 dataset playground, url: https://www.cs.toronto.edu/~kriz/cifar.html
+
+Couldn't now figure out labels mapping. some images showed wrong labels,
+like keyboard was labeled as kangaroo, and cups and crocodile had to be swapped
+"""
+import time
+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
+import matplotlib.pyplot as plt
+
+from common.pytorch_helpers import DATA_PATH
+
+
+LABELS = [
+    ("aquatic mammals", "beaver, dolphin, otter, seal, whale"),
+    ("fish", "aquarium fish, flatfish, ray, shark, trout"),
+    ("flowers", "orchids, poppies, roses, sunflowers, tulips"),
+    ("food containers", "bottles, bowls, cans, cups, plates"),
+    ("fruit and vegetables", "apples, mushrooms, oranges, pears, sweet peppers"),
+    ("household electrical devices", "clock, computer keyboard, lamp, telephone, television"),
+    ("household furniture", "bed, chair, couch, table, wardrobe"),
+    ("insects", "bee, beetle, butterfly, caterpillar, cockroach"),
+    ("large carnivores", "bear, leopard, lion, tiger, wolf"),
+    ("large man-made outdoor things", "bridge, castle, house, road, skyscraper"),
+    ("large natural outdoor scenes", "cloud, forest, mountain, plain, sea"),
+    ("large omnivores and herbivores", "camel, cattle, chimpanzee, elephant, kangaroo"),
+    ("medium-sized mammals", "fox, porcupine, possum, raccoon, skunk"),
+    ("non-insect invertebrates", "crab, lobster, snail, spider, worm"),
+    ("people", "baby, boy, girl, man, woman"),
+    ("reptiles", "crocodile, dinosaur, lizard, snake, turtle"),
+    ("small mammals", "hamster, mouse, rabbit, shrew, squirrel"),
+    ("trees", "maple, oak, palm, pine, willow"),
+    ("vehicles 1", "bicycle, bus, motorcycle, pickup truck, train"),
+    ("vehicles 2", "lawn-mower, rocket, streetcar, tank, tractor")
+]
+
+
+def create_fine_labels():
+    res = []
+    for l in LABELS:
+        for a in l[1].split(','):
+            res.append(a.strip())
+    res = sorted(res)
+    # swap cups and crocodile
+    res[28], res[29] = res[29], res[28]
+    return res
+
+
+def print_fine_labels(fine_labels):
+    i = 0
+    for f in fine_labels:
+        print i, f
+        i += 1
+    print
+
+
+fine_labels = create_fine_labels()
+print_fine_labels(fine_labels)
+
+train_dataset = dsets.CIFAR100(root=DATA_PATH,
+                               train=True,
+                               transform=transforms.ToTensor(),
+                               download=False)
+plt.show()
+for i in range(len(train_dataset)):
+    # i = np.random.choice(range(len(train_dataset)))
+    image, label = train_dataset[i]
+    if True:
+        plt.imshow(image.numpy().transpose(1,2,0))
+        print label, fine_labels[label]
+        pass
diff --git a/my-tutorials/common/__init__.py b/my-tutorials/common/__init__.py
new file mode 100644
index 00000000..e69de29b
diff --git a/my-tutorials/common/__init__.pyc b/my-tutorials/common/__init__.pyc
new file mode 100644
index 00000000..feb59a9a
Binary files /dev/null and b/my-tutorials/common/__init__.pyc differ
diff --git a/my-tutorials/common/pytorch_helpers.py b/my-tutorials/common/pytorch_helpers.py
new file mode 100644
index 00000000..7dc7b6db
--- /dev/null
+++ b/my-tutorials/common/pytorch_helpers.py
@@ -0,0 +1,30 @@
+import torch.nn as nn
+
+DATA_PATH = '../tutorials/data/'
+
+
+class LinearRegression(nn.Module):
+    def __init__(self, in_size, out_size):
+        super(LinearRegression, self).__init__()
+        self.linear = nn.Linear(in_size, out_size)
+
+    def forward(self, x):
+        return self.linear(x)
+
+    def __call__(self, *args, **kwargs):
+        return super(LinearRegression, self).__call__(*args, **kwargs)
+
+
+# Neural Network Model (1 hidden layer)
+class Net1(nn.Module):
+    def __init__(self, in_size, hidden_size, out_size):
+        super(Net1, self).__init__()
+        self.fc1 = nn.Linear(in_size, hidden_size)
+        self.relu = nn.ReLU()
+        self.fc2 = nn.Linear(hidden_size, out_size)
+
+    def forward(self, x):
+        out = self.fc1(x)
+        out = self.relu(out)
+        out = self.fc2(out)
+        return out
\ No newline at end of file
diff --git a/my-tutorials/common/pytorch_helpers.pyc b/my-tutorials/common/pytorch_helpers.pyc
new file mode 100644
index 00000000..75d47b12
Binary files /dev/null and b/my-tutorials/common/pytorch_helpers.pyc differ
diff --git a/my-tutorials/linear_regression.py b/my-tutorials/linear_regression.py
new file mode 100644
index 00000000..5496194f
--- /dev/null
+++ b/my-tutorials/linear_regression.py
@@ -0,0 +1,102 @@
+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
+import matplotlib.pyplot as plt
+import random
+from common.pytorch_helpers import LinearRegression
+# define a line with (0,0), (1,1)
+def line45(x):
+    return x
+
+
+def randomize_point(x, y, dx_max, dy_max):
+    dx = 2 * random.random() - 1
+    dx *= dx_max
+    dy = 2 * random.random() - 1
+    dy *= dy_max
+    return x + dx, y + dy
+
+
+def generate_points(x_min, x_max, f, N):
+    assert N > 1, 'number of points should be > 1'
+    dx = (x_max - x_min) / float(N-1)
+    x = x_min
+    points = []
+    while x <= x_max:
+        y = f(x)
+        points.append((x, y))
+        x += dx
+    return points
+
+
+def randomize_points(points, dx_max, dy_max):
+    res = []
+    for x, y in points:
+        res.append(randomize_point(x, y, dx_max, dy_max))
+    return res
+
+
+def split_x_y(points):
+    x = []
+    y = []
+    for p in points:
+        x.append(p[0])
+        y.append(p[1])
+    return x, y
+
+
+def list_to_numpy(l, t=np.float32):
+    return np.array([[x] for x in l], dtype=t)
+
+
+points = generate_points(0, 1, line45, 100)
+# print points
+x_p, y_p = split_x_y(points)
+
+points_rand = randomize_points(points, .2, .2)
+# print points_rand
+x_pr, y_pr = split_x_y(points_rand)
+
+
+############ LINEAR REGRESSION #################
+# let's create linear regression for the randomized points
+x_train = list_to_numpy(x_p)
+print("X shape" + str(x_train.shape)) # (100, 1)
+y_train = list_to_numpy(y_pr)
+
+# Linear (1 -> 1)
+model = LinearRegression(x_train.shape[1], y_train.shape[1])
+
+# define loss and optimizer
+criterion = nn.MSELoss()
+# stochastic gradient descent
+learning_rate = 0.1
+optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate)
+
+# train
+num_epochs = 300
+inputs = Variable(torch.from_numpy(x_train))
+targets = Variable(torch.from_numpy(y_train))
+for epoch in range(num_epochs):
+    # vars: epoch, outputs loss
+    optimizer.zero_grad() # why do we have to clear grads from last step?
+    outputs = model(inputs) # this call self.forward
+    loss = criterion(outputs, targets)
+    loss.backward()
+    optimizer.step()
+
+    if (epoch+1) % 10 == 0:
+        print('Epoch [%d/%d], Loss: %.5f' % (epoch+1, num_epochs, loss.data[0]))
+
+
+predicted = model(Variable(torch.from_numpy(x_train))).data.numpy()
+plt.plot(x_train, y_train, 'ro', label='Original data')
+plt.plot(x_train, predicted, label='Fitted line')
+plt.plot(x_train, y_p, label='Expected line')
+plt.legend()
+plt.show()
diff --git a/my-tutorials/mnist_feedforward.py b/my-tutorials/mnist_feedforward.py
new file mode 100644
index 00000000..bcca3da9
--- /dev/null
+++ b/my-tutorials/mnist_feedforward.py
@@ -0,0 +1,86 @@
+import torch
+import torch.nn as nn
+import torchvision.datasets as dsets
+import torchvision.transforms as transforms
+from torch.autograd import Variable
+from common.pytorch_helpers import DATA_PATH, Net1
+
+
+# Hyper Parameters
+input_size = 784
+hidden_size = 500
+num_classes = 10
+num_epochs = 5
+batch_size = 100
+learning_rate = 0.001
+model_state_dict_filename = 'models/mnist_feedforward-params.pkl'
+
+# MNIST Dataset
+train_dataset = dsets.MNIST(root=DATA_PATH,
+                            train=True,
+                            transform=transforms.ToTensor(),
+                            download=True)
+
+test_dataset = dsets.MNIST(root=DATA_PATH,
+                           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)
+
+
+model = Net1(input_size, hidden_size, num_classes)
+if torch.cuda.is_available():
+    model.cuda()
+
+# Loss and optimizer
+criterion = nn.CrossEntropyLoss()
+optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
+
+# Train
+training = True
+if training:
+    for epoch in range(num_epochs):
+        for i, (images, labels) in enumerate(train_loader):
+            images = Variable(images.view(-1, 28*28))
+            if torch.cuda.is_available():
+                images = images.cuda()
+            labels = Variable(labels)
+            if torch.cuda.is_available():
+                labels = labels.cuda()
+
+            # forward bacward 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]))
+    # Save the Model
+    torch.save(model.state_dict(), model_state_dict_filename)
+else:
+    model.load_state_dict(torch.load(model_state_dict_filename))
+
+# Test model
+correct = total = 0
+for images, labels in test_loader:
+    images = Variable(images.view(-1, 28*28))
+    if torch.cuda.is_available():
+        images = images.cuda()
+    outputs = model(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))
+
+
diff --git a/my-tutorials/mnist_logistic.py b/my-tutorials/mnist_logistic.py
new file mode 100644
index 00000000..17a1ef12
--- /dev/null
+++ b/my-tutorials/mnist_logistic.py
@@ -0,0 +1,80 @@
+"""
+logistic regression (or logit) is a regression where output is categorical
+"""
+import torch
+import torch.nn as nn
+import torchvision.datasets as dsets
+import torchvision.transforms as transforms
+from torch.autograd import Variable
+from common.pytorch_helpers import DATA_PATH, LinearRegression
+
+# Hyper Parameters
+input_size = 784 # 28 * 28
+num_classes = 10
+num_epochs = 5
+batch_size = 100
+
+# MNIST Dataset (Images and Labels)
+train_dataset = dsets.MNIST(root=DATA_PATH,
+                            train=True,
+                            transform=transforms.ToTensor(),
+                            download=True)
+
+test_dataset = dsets.MNIST(root=DATA_PATH,
+                           train=False,
+                           transform=transforms.ToTensor(),
+                           download=False)
+
+# 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 = LinearRegression(input_size, num_classes)
+
+training = not True
+model_state_dict_filename = "models/mnist_logistic-params.pkl"
+
+if training:
+    criterion = nn.CrossEntropyLoss()
+    learning_rate = 0.1
+
+    optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate)
+
+    # Train 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]))
+
+    # Save model
+    torch.save(model.state_dict(), model_state_dict_filename)
+else:
+    model.load_state_dict(torch.load(model_state_dict_filename))
+
+# Test model
+correct = 0
+total = 0
+for images, labels in test_loader:
+    images = Variable(images.view(-1, 28 * 28)) # size [100, 784]
+    outputs = model(images) # size [100, 10]
+    _, 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))
\ No newline at end of file
diff --git a/my-tutorials/models/README.txt b/my-tutorials/models/README.txt
new file mode 100644
index 00000000..703b59a7
--- /dev/null
+++ b/my-tutorials/models/README.txt
@@ -0,0 +1,2 @@
+all pkl models will be placed here
+
diff --git a/tutorials/00 - PyTorch Basics/basics.ipynb b/tutorials/00_PyTorch_Basics/basics.ipynb
similarity index 100%
rename from tutorials/00 - PyTorch Basics/basics.ipynb
rename to tutorials/00_PyTorch_Basics/basics.ipynb
diff --git a/tutorials/00 - PyTorch Basics/main.py b/tutorials/00_PyTorch_Basics/main.py
similarity index 87%
rename from tutorials/00 - PyTorch Basics/main.py
rename to tutorials/00_PyTorch_Basics/main.py
index 17a50707..bf45845e 100644
--- a/tutorials/00 - PyTorch Basics/main.py	
+++ b/tutorials/00_PyTorch_Basics/main.py
@@ -6,6 +6,7 @@
 import torchvision.transforms as transforms
 import torchvision.datasets as dsets
 from torch.autograd import Variable
+import matplotlib.pyplot as plt
 
 
 #========================== Table of Contents ==========================#
@@ -20,20 +21,26 @@
 
 #======================= Basic autograd example 1 =======================#
 # Create tensors.
-x = Variable(torch.Tensor([1]), requires_grad=True)
+x = Variable(torch.Tensor([3]), 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.
+# Compute all gradients and store them in Variable.grad
+# computes: x.grad = dy/dx, w.grad = dy/dw, b.grad = dy/db
 y.backward()
 
 # Print out the gradients.
-print(x.grad)    # x.grad = 2 
-print(w.grad)    # w.grad = 1 
-print(b.grad)    # b.grad = 1 
+print("dy/dx = w")
+print(x.grad)
+
+print("dy/dw = x")
+print(w.grad)
+
+print("dy/db = 1")
+print(b.grad)
 
 
 #======================== Basic autograd example 2 =======================#
@@ -85,7 +92,23 @@
 
 #===================== Implementing the input pipline =====================#
 # Download and construct dataset.
-train_dataset = dsets.CIFAR10(root='../data/',
+"""
+https://www.cs.toronto.edu/~kriz/cifar.html
+The CIFAR-10 dataset consists of 60000 32x32 colour images in 10 classes, 
+with 6000 images per class. 
+There are 50000 training images and 10000 test images. 10 classes:
+0 - airplaine
+1 - automobile
+2 - bird
+3 - cat
+4 - deer
+5 - dog
+6 - frog
+7 - horse
+8 - ship
+9 - truck
+"""
+train_dataset = dsets.CIFAR100(root='../data/',
                                train=True, 
                                transform=transforms.ToTensor(),
                                download=True)
@@ -108,7 +131,7 @@
 images, labels = data_iter.next()
 
 # Actual usage of data loader is as below.
-for images, labels in train_loader:
+for image, label in train_loader:
     # Your training code will be written here
     pass
 
diff --git a/tutorials/01 - Linear Regression/main.py b/tutorials/01_Linear_Regression/main.py
similarity index 100%
rename from tutorials/01 - Linear Regression/main.py
rename to tutorials/01_Linear_Regression/main.py
diff --git a/tutorials/02 - Logistic Regression/main.py b/tutorials/02_Logistic_Regression/main.py
similarity index 100%
rename from tutorials/02 - Logistic Regression/main.py
rename to tutorials/02_Logistic_Regression/main.py
diff --git a/tutorials/03 - Feedforward Neural Network/main-gpu.py b/tutorials/03_Feedforward_Neural_Network/main-gpu.py
similarity index 100%
rename from tutorials/03 - Feedforward Neural Network/main-gpu.py
rename to tutorials/03_Feedforward_Neural_Network/main-gpu.py
diff --git a/tutorials/03 - Feedforward Neural Network/main.py b/tutorials/03_Feedforward_Neural_Network/main.py
similarity index 100%
rename from tutorials/03 - Feedforward Neural Network/main.py
rename to tutorials/03_Feedforward_Neural_Network/main.py
diff --git a/tutorials/04 - Convolutional Neural Network/main-gpu.py b/tutorials/04_Convolutional_Neural_Network/main-gpu.py
similarity index 100%
rename from tutorials/04 - Convolutional Neural Network/main-gpu.py
rename to tutorials/04_Convolutional_Neural_Network/main-gpu.py
diff --git a/tutorials/04 - Convolutional Neural Network/main.py b/tutorials/04_Convolutional_Neural_Network/main.py
similarity index 100%
rename from tutorials/04 - Convolutional Neural Network/main.py
rename to tutorials/04_Convolutional_Neural_Network/main.py
diff --git a/tutorials/05 - Deep Residual Network/main-gpu.py b/tutorials/05_Deep_Residual_Network/main-gpu.py
similarity index 100%
rename from tutorials/05 - Deep Residual Network/main-gpu.py
rename to tutorials/05_Deep_Residual_Network/main-gpu.py
diff --git a/tutorials/05 - Deep Residual Network/main.py b/tutorials/05_Deep_Residual_Network/main.py
similarity index 100%
rename from tutorials/05 - Deep Residual Network/main.py
rename to tutorials/05_Deep_Residual_Network/main.py
diff --git a/tutorials/06 - Recurrent Neural Network/main-gpu.py b/tutorials/06_Recurrent_Neural_Network/main-gpu.py
similarity index 100%
rename from tutorials/06 - Recurrent Neural Network/main-gpu.py
rename to tutorials/06_Recurrent_Neural_Network/main-gpu.py
diff --git a/tutorials/06 - Recurrent Neural Network/main.py b/tutorials/06_Recurrent_Neural_Network/main.py
similarity index 100%
rename from tutorials/06 - Recurrent Neural Network/main.py
rename to tutorials/06_Recurrent_Neural_Network/main.py
diff --git a/tutorials/07 - Bidirectional Recurrent Neural Network/main-gpu.py b/tutorials/07_Bidirectional_Recurrent_Neural_Network/main-gpu.py
similarity index 100%
rename from tutorials/07 - Bidirectional Recurrent Neural Network/main-gpu.py
rename to tutorials/07_Bidirectional_Recurrent_Neural_Network/main-gpu.py
diff --git a/tutorials/07 - Bidirectional Recurrent Neural Network/main.py b/tutorials/07_Bidirectional_Recurrent_Neural_Network/main.py
similarity index 100%
rename from tutorials/07 - Bidirectional Recurrent Neural Network/main.py
rename to tutorials/07_Bidirectional_Recurrent_Neural_Network/main.py
diff --git a/tutorials/08 - Language Model/data/train.txt b/tutorials/08_Language_Model/data/train.txt
similarity index 100%
rename from tutorials/08 - Language Model/data/train.txt
rename to tutorials/08_Language_Model/data/train.txt
diff --git a/tutorials/08 - Language Model/data_utils.py b/tutorials/08_Language_Model/data_utils.py
similarity index 100%
rename from tutorials/08 - Language Model/data_utils.py
rename to tutorials/08_Language_Model/data_utils.py
diff --git a/tutorials/08 - Language Model/main-gpu.py b/tutorials/08_Language_Model/main-gpu.py
similarity index 100%
rename from tutorials/08 - Language Model/main-gpu.py
rename to tutorials/08_Language_Model/main-gpu.py
diff --git a/tutorials/08 - Language Model/main.py b/tutorials/08_Language_Model/main.py
similarity index 100%
rename from tutorials/08 - Language Model/main.py
rename to tutorials/08_Language_Model/main.py
diff --git a/tutorials/09 - Image Captioning/README.md b/tutorials/09_Image_Captioning/README.md
similarity index 100%
rename from tutorials/09 - Image Captioning/README.md
rename to tutorials/09_Image_Captioning/README.md
diff --git a/tutorials/09 - Image Captioning/build_vocab.py b/tutorials/09_Image_Captioning/build_vocab.py
similarity index 100%
rename from tutorials/09 - Image Captioning/build_vocab.py
rename to tutorials/09_Image_Captioning/build_vocab.py
diff --git a/tutorials/09 - Image Captioning/data_loader.py b/tutorials/09_Image_Captioning/data_loader.py
similarity index 100%
rename from tutorials/09 - Image Captioning/data_loader.py
rename to tutorials/09_Image_Captioning/data_loader.py
diff --git a/tutorials/09 - Image Captioning/download.sh b/tutorials/09_Image_Captioning/download.sh
similarity index 100%
rename from tutorials/09 - Image Captioning/download.sh
rename to tutorials/09_Image_Captioning/download.sh
diff --git a/tutorials/09 - Image Captioning/model.py b/tutorials/09_Image_Captioning/model.py
similarity index 100%
rename from tutorials/09 - Image Captioning/model.py
rename to tutorials/09_Image_Captioning/model.py
diff --git a/tutorials/09 - Image Captioning/requirements.txt b/tutorials/09_Image_Captioning/requirements.txt
similarity index 100%
rename from tutorials/09 - Image Captioning/requirements.txt
rename to tutorials/09_Image_Captioning/requirements.txt
diff --git a/tutorials/09 - Image Captioning/resize.py b/tutorials/09_Image_Captioning/resize.py
similarity index 100%
rename from tutorials/09 - Image Captioning/resize.py
rename to tutorials/09_Image_Captioning/resize.py
diff --git a/tutorials/09 - Image Captioning/sample.py b/tutorials/09_Image_Captioning/sample.py
similarity index 100%
rename from tutorials/09 - Image Captioning/sample.py
rename to tutorials/09_Image_Captioning/sample.py
diff --git a/tutorials/09 - Image Captioning/train.py b/tutorials/09_Image_Captioning/train.py
similarity index 100%
rename from tutorials/09 - Image Captioning/train.py
rename to tutorials/09_Image_Captioning/train.py
diff --git a/tutorials/10 - Generative Adversarial Network/main-gpu.py b/tutorials/10_Generative_Adversarial_Network/main-gpu.py
similarity index 100%
rename from tutorials/10 - Generative Adversarial Network/main-gpu.py
rename to tutorials/10_Generative_Adversarial_Network/main-gpu.py
diff --git a/tutorials/10 - Generative Adversarial Network/main.py b/tutorials/10_Generative_Adversarial_Network/main.py
similarity index 100%
rename from tutorials/10 - Generative Adversarial Network/main.py
rename to tutorials/10_Generative_Adversarial_Network/main.py
diff --git a/tutorials/11 - Deep Convolutional Generative Adversarial Network/main-gpu.py b/tutorials/11_Deep_Convolutional_Generative_Adversarial_Network/main-gpu.py
similarity index 100%
rename from tutorials/11 - Deep Convolutional Generative Adversarial Network/main-gpu.py
rename to tutorials/11_Deep_Convolutional_Generative_Adversarial_Network/main-gpu.py
diff --git a/tutorials/11 - Deep Convolutional Generative Adversarial Network/main.py b/tutorials/11_Deep_Convolutional_Generative_Adversarial_Network/main.py
similarity index 100%
rename from tutorials/11 - Deep Convolutional Generative Adversarial Network/main.py
rename to tutorials/11_Deep_Convolutional_Generative_Adversarial_Network/main.py
diff --git a/tutorials/12 - Deep Q Network/dqn13.py b/tutorials/12_Deep_Q_Network/dqn13.py
similarity index 100%
rename from tutorials/12 - Deep Q Network/dqn13.py
rename to tutorials/12_Deep_Q_Network/dqn13.py