Hendra Bayu - 12419795 - Robot M3

10/15/22, 2:41 PM TEKREK M3 - Jupyter Notebook
1) Importing Python Packages for GAN

In [1]: from keras.datasets import cifar10, mnist
from keras.models import Sequential
from keras.layers import Reshape
from keras.layers import Dense
from keras.layers import Flatten
from keras.layers import Conv2D
from keras.layers import Conv2DTranspose
from keras.layers import Dropout
from keras.layers.advanced_activations import LeakyReLU
from tensorflow.keras.optimizers import Adam
import numpy as np
!mkdir generated_images
mkdir: cannot create directory ‘generated_images’: Permission denied
2) Parameters for Neural Networks & Data

In [2]: img_width = 32
img_height = 32
channels = 3
img_shape = (img_width, img_height, channels)
latent_dim = 100
adam = Adam(learning_rate=0.0002)
3) Building Generator
https://hypercomputation-hub.gunadarma.ac.id/fti/user/13419274/notebooks/Praktikum-Tingkat-4-Tekrek/TEKREK M3.ipynb 1/5

In [3]: def build_generator():

model = Sequential()

# Create first layer, to receive the input
model.add(Dense(256 * 4 * 4, input_dim = latent_dim))
# 256 * 8 * 8; for upscaling the layers,
# initial shape to construct into final shape

# Create default activation function
model.add(LeakyReLU(alpha = 0.2))

# Create reshape layer
model.add(Reshape((4, 4,256)))
# 8,8,256 ; reffers to first layer

# Adding more layers for neurons and better result
model.add(Conv2DTranspose(128, (4,4), strides = (2,2), padding = 'same'))
model.add(LeakyReLU(alpha= 0.2))
# (4,4) >> filter size
# strides = (2,2) >> Convolutional layers, that how NN understand images

# Create Final output layer and forming image shape
# the shape (3, (3,3)) reffers to image shape :
# >>> img_shape = (img_width, img_height, channels)
model.add(Conv2D(3, (3,3), activation= 'tanh', padding = 'same'))

#
model.summary()
return model

generator = build_generator()
Model: "sequential"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
dense (Dense) (None, 4096) 413696
_________________________________________________________________
leaky_re_lu (LeakyReLU) (None, 4096) 0
_________________________________________________________________
reshape (Reshape) (None, 4, 4, 256) 0
_________________________________________________________________
conv2d_transpose (Conv2DTran (None, 8, 8, 128) 524416
_________________________________________________________________
leaky_re_lu_1 (LeakyReLU) (None, 8, 8, 128) 0
_________________________________________________________________
conv2d_transpose_1 (Conv2DTr (None, 16, 16, 128) 262272
_________________________________________________________________
_________________________________________________________________
conv2d_transpose_2 (Conv2DTr (None, 32, 32, 128) 262272
_________________________________________________________________

_________________________________________________________________
conv2d (Conv2D) (None, 32, 32, 3) 3459
=================================================================
Total params: 1,466,115
Trainable params: 1,466,115
Non-trainable params: 0
_________________________________________________________________
4) Building Discriminator

In [4]: def build_discriminator():

model = Sequential()

# Create input layer and filter and stride layer. That makes NN understand im
model.add(Conv2D(64, (3,3), padding = 'same', input_shape = img_shape))

# Adding activation function
model.add(Conv2D(128, (3,3), padding = 'same'))
model.add(Flatten())

model.add(Dropout(0.4))

# Create output layer
model.add(Dense(1, activation = 'sigmoid'))

model.summary()
return model

discriminator = build_discriminator()
discriminator.compile(loss='binary_crossentropy', optimizer=adam, metrics=['accur
Model: "sequential_1"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
conv2d_1 (Conv2D) (None, 32, 32, 64) 1792
_________________________________________________________________
_________________________________________________________________
conv2d_2 (Conv2D) (None, 32, 32, 128) 73856
_________________________________________________________________
_________________________________________________________________
conv2d_3 (Conv2D) (None, 32, 32, 128) 147584
_________________________________________________________________
_________________________________________________________________
conv2d_4 (Conv2D) (None, 32, 32, 256) 295168
_________________________________________________________________
_________________________________________________________________
flatten (Flatten) (None, 262144) 0
_________________________________________________________________
dropout (Dropout) (None, 262144) 0
_________________________________________________________________
dense_1 (Dense) (None, 1) 262145
=================================================================
Total params: 780,545
Trainable params: 780,545
Non-trainable params: 0
_________________________________________________________________

5) Connecting Neural Networks to build GAN

In [5]: GAN = Sequential()
discriminator.trainable = False
GAN.add(generator)
GAN.add(discriminator)

GAN.compile(loss='binary_crossentropy', optimizer=adam)
In [6]: #GAN.summary()
6) Outputting Images
In [ ]:
7) Training GAN
In [ ]:
In [ ]:
In [ ]:
8) Making GIF
In [ ]:

Hendra Bayu - 12419795 - Robot M3

Uploaded by

Copyright:

Available Formats

Hendra Bayu - 12419795 - Robot M3

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Hendra Bayu - 12419795 - Robot M3

Uploaded by

Copyright:

Available Formats

10/15/22, 2:41 PM TEKREK M3 - Jupyter Notebook

1) Importing Python Packages for GAN

mkdir: cannot create directory ‘generated_images’: Permission denied

2) Parameters for Neural Networks & Data

https://hypercomputation-hub.gunadarma.ac.id/fti/user/13419274/notebooks/Praktikum-Tingkat-4-Tekrek/TEKREK M3.ipynb 1/5

In [3]: def build_generator():

Layer (type) Output Shape Param #

dense (Dense) (None, 4096) 413696

leaky_re_lu (LeakyReLU) (None, 4096) 0

reshape (Reshape) (None, 4, 4, 256) 0

conv2d_transpose (Conv2DTran (None, 8, 8, 128) 524416

leaky_re_lu_1 (LeakyReLU) (None, 8, 8, 128) 0

conv2d_transpose_1 (Conv2DTr (None, 16, 16, 128) 262272

leaky_re_lu_2 (LeakyReLU) (None, 16, 16, 128) 0

conv2d_transpose_2 (Conv2DTr (None, 32, 32, 128) 262272

https://hypercomputation-hub.gunadarma.ac.id/fti/user/13419274/notebooks/Praktikum-Tingkat-4-Tekrek/TEKREK M3.ipynb 2/5

leaky_re_lu_3 (LeakyReLU) (None, 32, 32, 128) 0

conv2d (Conv2D) (None, 32, 32, 3) 3459

Total params: 1,466,115

Trainable params: 1,466,115

https://hypercomputation-hub.gunadarma.ac.id/fti/user/13419274/notebooks/Praktikum-Tingkat-4-Tekrek/TEKREK M3.ipynb 3/5

In [4]: def build_discriminator():

Layer (type) Output Shape Param #

conv2d_1 (Conv2D) (None, 32, 32, 64) 1792

leaky_re_lu_4 (LeakyReLU) (None, 32, 32, 64) 0

conv2d_2 (Conv2D) (None, 32, 32, 128) 73856

leaky_re_lu_5 (LeakyReLU) (None, 32, 32, 128) 0

conv2d_3 (Conv2D) (None, 32, 32, 128) 147584

leaky_re_lu_6 (LeakyReLU) (None, 32, 32, 128) 0

conv2d_4 (Conv2D) (None, 32, 32, 256) 295168

leaky_re_lu_7 (LeakyReLU) (None, 32, 32, 256) 0

flatten (Flatten) (None, 262144) 0

dropout (Dropout) (None, 262144) 0

dense_1 (Dense) (None, 1) 262145

Total params: 780,545

Trainable params: 780,545

https://hypercomputation-hub.gunadarma.ac.id/fti/user/13419274/notebooks/Praktikum-Tingkat-4-Tekrek/TEKREK M3.ipynb 4/5

5) Connecting Neural Networks to build GAN

https://hypercomputation-hub.gunadarma.ac.id/fti/user/13419274/notebooks/Praktikum-Tingkat-4-Tekrek/TEKREK M3.ipynb 5/5

You might also like