10/10/24, 4:48 PM Untitled14.

ipynb - Colab

from keras.datasets import mnist from keras.models import

Sequential from keras.layers import BatchNormalization from
keras.layers import Dense, Reshape, Flatten, LeakyReLU from
tensorflow.keras.optimizers import Adam import numpy as np
!mkdir generated_images

img_width = 28 img_height = 28 channels = 1

img_shape = (img_width, img_height, channels)
latent_dim = 100 adam =
Adam(learning_rate=0.0001)

def build_generator():
model = Sequential()

model.add(Dense(256, input_dim=latent_dim))
model.add(LeakyReLU(alpha=0.2))
model.add(BatchNormalization(momentum=0.8))

model.add(Dense(256))
model.add(LeakyReLU(alpha=0.2))
model.add(BatchNormalization(momentum=0.8))

model.add(Dense(256))
model.add(LeakyReLU(alpha=0.2))
model.add(BatchNormalization(momentum=0.8))

model.add(Dense(np.prod(img_shape), activation='tanh'))
model.add(Reshape(img_shape))

model.summary() return

model generator =

build_generator()

/usr/local/lib/python3.10/dist-packages/keras/src/layers/core/dense.py:87: UserWarning: Do not pass an `input_shape`/`input_dim` arg

super().__init__(activity_regularizer=activity_regularizer, **kwargs)
/usr/local/lib/python3.10/dist-packages/keras/src/layers/activations/leaky_relu.py:41: UserWarning: Argument `alpha` is deprecated.
warnings.warn(
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┓
┃ Layer (type) ┃ Output Shape ┃ Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━┩
│ dense (Dense) │ (None, 256) │ 25,856 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ leaky_re_lu (LeakyReLU) │ (None, 256) │ 0 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ batch_normalization │ (None, 256) │ 1,024 │
│ (BatchNormalization) │ │ │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ dense_1 (Dense) │ (None, 256) │ 65,792 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ leaky_re_lu_1 (LeakyReLU) │ (None, 256) │ 0 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ batch_normalization_1 │ (None, 256) │ 1,024 │
│ (BatchNormalization) │ │ │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ dense_2 (Dense) │ (None, 256) │ 65,792 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ leaky_re_lu_2 (LeakyReLU) │ (None, 256) │ 0 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ batch_normalization_2 │ (None, 256) │ 1,024 │
│ (BatchNormalization) │ │ │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ dense_3 (Dense) │ (None, 784) │ 201,488 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ reshape (Reshape) │ (None, 28, 28, 1) │ 0 │
└──────────────────────────────────────┴─────────────────────────────┴─────────────────┘
Total params: 362,000 (1.38 MB)
Trainable params: 360,464 (1.38 MB)
( )
def build_discriminator():
model = Sequential()

model.add(Flatten(input_shape=img_shape))
model.add(Dense(512))
model.add(LeakyReLU(alpha=0.2))
model.add(Dense(256)) model.add(Dense(1,
activation='sigmoid'))

model.summary()
return model

https://colab.research.google.com/drive/1wLkoofVmDXV2y_9zyorrvMDhay4CTsx_#scrollTo=nr3ZG_uF0sEu&printMode=true 1/4
10/10/24, 4:48 PM Untitled14.ipynb - Colab
discriminator = build_discriminator() discriminator.compile(loss='binary_crossentropy',
optimizer=adam, metrics=['accuracy'])

/usr/local/lib/python3.10/dist-packages/keras/src/layers/reshaping/flatten.py:37: UserWarning: Do not pass an `input_shape`/`input_d

super().__init__(**kwargs)
Model: "sequential_1"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┓
┃ Layer (type) ┃ Output Shape ┃ Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━┩
│ flatten (Flatten) │ (None, 784) │ 0 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ dense_4 (Dense) │ (None, 512) │ 401,920 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ leaky_re_lu_3 (LeakyReLU) │ (None, 512) │ 0 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ dense_5 (Dense) │ (None, 256) │ 131,328 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ dense_6 (Dense) │ (None, 1) │ 257 │
└──────────────────────────────────────┴─────────────────────────────┴─────────────────┘
Total params: 533,505 (2.04 MB)
Trainable params: 533,505 (2.04 MB) Non-
trainable params: 0 (0.00 B)

GAN = Sequential()
discriminator.trainable = False
GAN.add(generator)
GAN.add(discriminator)

GAN.compile(loss='binary_crossentropy', optimizer=adam)
GAN.summary()

Model: "sequential_2"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┓
┃ Layer (type) ┃ Output Shape ┃ Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━┩
│ sequential (Sequential) │ (None, 28, 28, 1) │ 362,000 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ sequential_1 (Sequential) │ (None, 1) │ 533,505 │
└──────────────────────────────────────┴─────────────────────────────┴─────────────────┘
Total params: 895,505 (3.42 MB)
Trainable params: 360,464 (1.38 MB)
Non-trainable params: 535,041 (2.04 MB)

#@title ## **7) Outputting

Images** import
matplotlib.pyplot as plt import
glob import imageio import PIL
save_name = 0.00000000

def save_imgs(epoch):
r, c = 5, 5 noise = np.random.normal(0, 1, (r *
c, latent_dim)) gen_imgs = generator.predict(noise)
global save_name save_name += 0.00000001
print("%.8f" % save_name)

# Rescale images 0 - 1
gen_imgs = 0.5 * gen_imgs + 0.5

fig, axs = plt.subplots(r, c)

cnt = 0 for i in range(r):
for j in range(c):
axs[i,j].imshow(gen_imgs[cnt, :,:,0], cmap='gray')
# axs[i,j].imshow(gen_imgs[cnt])
axs[i,j].axis('off') cnt += 1

fig.savefig("generated_images/%.8f.png" % save_name)
print('saved') plt.close()

def train(epochs, batch_size=64, save_interval=200):

(X_train, _), (_, _) = mnist.load_data()

# Rescale data between -1 and 1

X_train = X_train / 127.5 - 1.

# Create our Y for our Neural Networks

valid = np.ones((batch_size, 1)) fakes
= np.zeros((batch_size, 1))

for epoch in range(epochs): # Get Random Batch

idx = np.random.randint(0, X_train.shape[0], batch_size)
imgs = X_train[idx]

https://colab.research.google.com/drive/1wLkoofVmDXV2y_9zyorrvMDhay4CTsx_#scrollTo=nr3ZG_uF0sEu&printMode=true 2/4
10/10/24, 4:48 PM Untitled14.ipynb - Colab
# Generate Fake Images noise =
np.random.normal(0, 1, (batch_size, latent_dim))
gen_imgs = generator.predict(noise)

# Train discriminator d_loss_real =

discriminator.train_on_batch(imgs, valid) d_loss_fake =
discriminator.train_on_batch(gen_imgs, fakes) d_loss = 0.5
* np.add(d_loss_real, d_loss_fake) noise =
np.random.normal(0, 1, (batch_size, latent_dim))

# Inverse y label g_loss = GAN.train_on_batch(noise, valid) print("******* %d [D loss: %f,

acc: %.2f%%] [G loss: %f]" % (epoch, d_loss[0], 100 * d_loss[1], g_loss[0]))

if (epoch % save_interval) == 0:
save_imgs(epoch)
train(950 , batch_size= 64, save_interval= 200)

https://colab.research.google.com/drive/1wLkoofVmDXV2y_9zyorrvMDhay4CTsx_#scrollTo=nr3ZG_uF0sEu&printMode=true 3/4
10/10/24, 4:48 PM Untitled14.ipynb - Colab
/ / p
******* 948 [D loss: 2.605092, acc: 29.91%] [G loss : 2.606087]
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 9ms/step
******* 949 [D loss: 2.606057, acc: 29.91%] [G loss : 2.607045]

# Display a single image using the epoch number

# def display_image(epoch_no):
# return PIL.Image.open('generated_images/%.8f.p ng'.format(epoch_no))

anim_file = 'dcgan.gif'

with imageio.get_writer (anim_file, mode='I') as writer:

filenames = glob.glob('generated_images/*.png' )
filenames = sorted(filenames)
for filename in filenames:
image = imageio.imread(filename)
writer.append_data (image)
image = imageio.imread(filename)
writer.append_data (image)

<ipython-input-8-5d911b6b7554>:11: DeprecationWarning: Starting with ImageIO v3 the behavior of this function will switch to that of
image = imageio.imread(filename)
<ipython-input-8-5d911b6b7554>:13: DeprecationWarning: Starting with ImageIO v3 the behavior of this function will switch to that of
image = imageio.imread(filename)

https://colab.research.google.com/drive/1wLkoofVmDXV2y_9zyorrvMDhay4CTsx_#scrollTo=nr3ZG_uF0sEu&printMode=true 4/4