vivekpadia70

model = Sequential()
model.add(Flatten(input_shape=(1,) + env.observation_space.shape))
model.add(Dense(16))
model.add(Activation('relu'))
model.add(Dense(nb_actions))
model.add(Activation('linear'))
print(model.summary())

vivekpadia70

# Using Epsilon Greedy Policy
policy = EpsGreedyQPolicy()

# Using Sequential memory with limit of 50000
memory = SequentialMemory(limit=50000, window_length=1)

# Initializing DQNAgent
dqn = DQNAgent(model=model, nb_actions=nb_actions, memory=memory, nb_steps_warmup=10, target_model_update=1e-2, policy=policy)
dqn.compile(Adam(lr=1e-3), metrics=['mae'])

vivekpadia70

env.close()

vivekpadia70

import tensorflow as tf
import matplotlib.pyplot as plt
import numpy as np
import os
from tensorflow.keras import layers
import time

from IPython import display

vivekpadia70

(train_images, train_labels), (test_images, test_labels) = tf.keras.datasets.mnist.load_data()
train_images = train_images.reshape(train_images.shape[0], 28, 28, 1).astype('float32')
train_images = (train_images - 127.5) / 127.5
train_dataset = tf.data.Dataset.from_tensor_slices(train_images).shuffle(60000).batch(256)

vivekpadia70

def create_generator():
    model = tf.keras.Sequential()
    
    # creating Dense layer with units 7*7*256(batch_size) and input_shape of (100,)
    model.add(layers.Dense(7*7*256, use_bias=False, input_shape=(100,)))
    model.add(layers.BatchNormalization())
    model.add(layers.LeakyReLU())

    model.add(layers.Reshape((7, 7, 256)))

vivekpadia70

def create_discriminator():
    model = tf.keras.Sequential()
    model.add(layers.Conv2D(64, (5, 5), strides=(2, 2), padding='same', input_shape=[28, 28, 1]))
    model.add(layers.LeakyReLU())
    model.add(layers.Dropout(0.3))

    model.add(layers.Conv2D(128, (5, 5), strides=(2, 2), padding='same'))
    model.add(layers.LeakyReLU())
    model.add(layers.Dropout(0.3))

vivekpadia70

cross_entropy = tf.keras.losses.BinaryCrossentropy(from_logits=True)

def D_loss(real_output, fake_output):
    real_loss = cross_entropy(tf.ones_like(real_output), real_output)
    fake_loss = cross_entropy(tf.zeros_like(fake_output), fake_output)
    total_loss = real_loss + fake_loss
    return total_loss
  
def G_loss(fake_output):
    return cross_entropy(tf.ones_like(fake_output), fake_output)

vivekpadia70

generator_optimizer = tf.keras.optimizers.Adam(1e-4)
discriminator_optimizer = tf.keras.optimizers.Adam(1e-4)

vivekpadia70

noise_dim = 100
num_of_generated_examples = 16

seed = tf.random.normal([num_of_generated_examples, noise_dim])