Tathagatd96

tf.reset_default_graph()

real_images=tf.placeholder(tf.float32,shape=[None,784])
z=tf.placeholder(tf.float32,shape=[None,100])

G=generator(z)
D_output_real,D_logits_real=discriminator(real_images)
D_output_fake,D_logits_fake=discriminator(G,reuse=True)

Tathagatd96

def generator(z,reuse=None):
    with tf.variable_scope('gen',reuse=reuse):
        hidden1=tf.layers.dense(inputs=z,units=128,activation=tf.nn.leaky_relu)
        hidden2=tf.layers.dense(inputs=hidden1,units=128,activation=tf.nn.leaky_relu)
        output=tf.layers.dense(inputs=hidden2,units=784,activation=tf.nn.tanh)
        
        return output
    
def discriminator(X,reuse=None):
    with tf.variable_scope('dis',reuse=reuse):

Tathagatd96

import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
from tensorflow.examples.tutorials.mnist import input_data

mnist=input_data.read_data_sets("MNIST_data")

Tathagatd96

results=output_layer.eval(feed_dict={X:mnist.test.images[:num_test_images]})
    
    #Comparing original images with reconstructions
    f,a=plt.subplots(2,10,figsize=(20,4))
    for i in range(num_test_images):
        a[0][i].imshow(np.reshape(mnist.test.images[i],(28,28)))
        a[1][i].imshow(np.reshape(results[i],(28,28)))

Tathagatd96

num_epoch=5
batch_size=150
num_test_images=10

with tf.Session() as sess:
    sess.run(init)
    for epoch in range(num_epoch):
        
        num_batches=mnist.train.num_examples//batch_size
        for iteration in range(num_batches):

Tathagatd96

loss=tf.reduce_mean(tf.square(output_layer-X))

optimizer=tf.train.AdamOptimizer(lr)
train=optimizer.minimize(loss)

init=tf.global_variables_initializer()

Tathagatd96

X=tf.placeholder(tf.float32,shape=[None,num_inputs])
initializer=tf.variance_scaling_initializer()

w1=tf.Variable(initializer([num_inputs,num_hid1]),dtype=tf.float32)
w2=tf.Variable(initializer([num_hid1,num_hid2]),dtype=tf.float32)
w3=tf.Variable(initializer([num_hid2,num_hid3]),dtype=tf.float32)
w4=tf.Variable(initializer([num_hid3,num_output]),dtype=tf.float32)

b1=tf.Variable(tf.zeros(num_hid1))
b2=tf.Variable(tf.zeros(num_hid2))

Tathagatd96

num_inputs=784    #28x28 pixels
num_hid1=392
num_hid2=196
num_hid3=num_hid1
num_output=num_inputs
lr=0.01
actf=tf.nn.relu

Tathagatd96

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
from tensorflow.contrib.layers import fully_connected

mnist=input_data.read_data_sets("/MNIST_data/",one_hot=True)

Tathagatd96

plt.title("TESTING THE MODEL")

#TRAINING INSTANCE
plt.plot(train_inst[:-1],np.sin(train_inst[:-1]),"bo",markersize=15,alpha=0.5,label="TRAINING INST")

#TARGET TO PREDICT 
plt.plot(train_inst[1:],np.sin(train_inst[1:]),"ko",markersize=8,label="TARGET")

#MODEL PREDCTION
plt.plot(train_inst[1:],y_pred[0,:,0],"r.",markersize=7,label="PREDICTIONS")