NiloyPurkait

def discriminator_loss(real_output, fake_output):
  
    loss_object = tf.keras.losses.BinaryCrossentropy(from_logits=True)
    
    real_loss = loss_object(tf.ones_like(real_output), real_output)
    
    fake_loss = loss_object(tf.zeros_like(fake_output), fake_output)
    
    total_loss = real_loss + fake_loss
    

NiloyPurkait

def generator_loss(preds):
  
    loss_object = tf.keras.losses.BinaryCrossentropy(from_logits=True)
    
    preds = tf.convert_to_tensor(preds, dtype=tf.float32)
    
    loss = loss_object(tf.ones_like(preds, dtype=tf.float32), preds)
    
    return  loss

NiloyPurkait

def train_step(inp, tar):
    # targets shifted by 1 index position
    tar_inp = tar[:, :-1]
    tar_real = tar[:, 1:]
    #Get encoding, combined and decoding masks
    enc_padding_mask, combined_mask, dec_padding_mask = create_masks(inp, tar_inp)

    # Initialize Generator and Discriminator gradient tapes
    with tf.GradientTape() as gen_tape, tf.GradientTape() as disc_tape:

NiloyPurkait

################################### Keras2DML: Parallely training neural network with SystemML####################################### 
import tensorflow as tf
import keras
from keras.models import Sequential
from keras.layers import Input, Dense, Conv1D, Conv2D, MaxPooling2D, Dropout,Flatten
from keras import backend as K
from keras.models import Model
import numpy as np
import matplotlib.pyplot as plt