Varational autoencoder using tf.GradientTape

293 views Asked by At

Here is an example of tensorflow GradientTape provided by keras for a typical variotional autoencoder:

VAE-keras-example

The train_step function is implemented inside the model and it is trained with the "model.fit()". The example performs great and no problem at all.

However, for another application, I need to implement the train_step function outside of the model definition. In the beginning, I started with above mentioned example as the target application is also a kind of VAE. Accordingly, I applied some modifications and tried to train the same model structure; please find the whole code in the next; however, I get very weird numbers for the loss values comparing to the original code; even after a couple of iterations it gets nan values for losses. Could you please let me know what's the mistake and why this happens?

Thanks in advance

#!/usr/bin/env python3
# -*- coding: utf-8 -*-

import tensorflow as tf
from tensorflow.keras import layers
from tensorflow.keras import backend as K
from tensorflow import keras
import numpy as np
print(tf.test.is_gpu_available()) # prints True
print(tf.__version__) # prints '2.0.0-beta1'

class Sampling(layers.Layer):
    """Uses (z_mean, z_log_var) to sample z, the vector encoding a digit."""

    def call(self, inputs):
        z_mean, z_log_var = inputs
        batch = tf.shape(z_mean)[0]
        dim = tf.shape(z_mean)[1]
        epsilon = tf.keras.backend.random_normal(shape=(batch, dim))
        return z_mean + tf.exp(0.5 * z_log_var) * epsilon

latent_dim = 2
encoder_inputs = keras.Input(shape=(28, 28, 1))
x = layers.Conv2D(32, 3, activation="relu", strides=2, padding="same")(encoder_inputs)
x = layers.Conv2D(64, 3, activation="relu", strides=2, padding="same")(x)
x = layers.Flatten()(x)
x = layers.Dense(16, activation="relu")(x)
z_mean = layers.Dense(latent_dim, name="z_mean")(x)
z_log_var = layers.Dense(latent_dim, name="z_log_var")(x)
z = Sampling()([z_mean, z_log_var])
x = layers.Dense(7 * 7 * 64, activation="relu")(z)
x = layers.Reshape((7, 7, 64))(x)
x = layers.Conv2DTranspose(64, 3, activation="relu", strides=2, padding="same")(x)
x = layers.Conv2DTranspose(32, 3, activation="relu", strides=2, padding="same")(x)
decoder_outputs = layers.Conv2DTranspose(1, 3, activation="sigmoid", padding="same")(x)
model = keras.Model(encoder_inputs, [decoder_outputs, z_mean, z_log_var] , name="decoder")
model.summary()




optimizer = tf.keras.optimizers.Adam(lr=0.001)
objective = tf.keras.losses.SparseCategoricalCrossentropy()

(x_train, _), (x_test, _) = keras.datasets.mnist.load_data()
num_samples = x_train.shape[0]
epochs=1
batch_size=128

@tf.function
def train_step(data):
  with tf.GradientTape() as tape:
    reconstruction, z_mean, z_log_var = model(data, training=True)
    data = tf.expand_dims(data, axis=-1)
    reconstruction_loss = tf.reduce_mean(
        tf.reduce_sum(keras.losses.binary_crossentropy(data, reconstruction), axis=(1, 2)))
    kl_loss = -0.5 * (1 + z_log_var - tf.square(z_mean) - tf.exp(z_log_var))
    kl_loss = tf.reduce_mean(tf.reduce_sum(kl_loss, axis=1))
    total_loss = (reconstruction_loss + kl_loss)
  grads = tape.gradient(total_loss, model.trainable_variables)
  optimizer.apply_gradients(zip(grads, model.trainable_variables))
  return total_loss, reconstruction_loss, kl_loss


with tf.device('gpu:0'):
  for epoch in range (epochs):
    for step in range(num_samples//batch_size):
      s = step*batch_size
      e = s+batch_size
      x_batch = x_train[s:e,:,:]
      total_loss, reconstruction_loss, kl_loss = train_step(x_batch)
      print("-----------------")
      print(f"epoch: {epoch} step: {step}")
      print(f"reconstruction_loss: {reconstruction_loss} ")
      print(f"kl_loss: {kl_loss} ")
      print(f"total_loss: {total_loss}")



1

There are 1 answers

0
AloneTogether On BEST ANSWER

I think you forgot to normalize your data as shown in the tutorial you are referring to:

(x_train, _), (x_test, _) = keras.datasets.mnist.load_data()
x_train = x_train.astype("float32") / 255

Otherwise, your code seems to be running fine and the loss in not nan. Here is the code for reference:

import tensorflow as tf
from tensorflow.keras import layers
from tensorflow.keras import backend as K
from tensorflow import keras
import numpy as np
print(tf.test.is_gpu_available()) # prints True
print(tf.__version__) # prints '2.0.0-beta1'

class Sampling(layers.Layer):
    """Uses (z_mean, z_log_var) to sample z, the vector encoding a digit."""

    def call(self, inputs):
        z_mean, z_log_var = inputs
        batch = tf.shape(z_mean)[0]
        dim = tf.shape(z_mean)[1]
        epsilon = tf.keras.backend.random_normal(shape=(batch, dim))
        return z_mean + tf.exp(0.5 * z_log_var) * epsilon

latent_dim = 2
encoder_inputs = keras.Input(shape=(28, 28, 1))
x = layers.Conv2D(32, 3, activation="relu", strides=2, padding="same")(encoder_inputs)
x = layers.Conv2D(64, 3, activation="relu", strides=2, padding="same")(x)
x = layers.Flatten()(x)
x = layers.Dense(16, activation="relu")(x)
z_mean = layers.Dense(latent_dim, name="z_mean")(x)
z_log_var = layers.Dense(latent_dim, name="z_log_var")(x)
z = Sampling()([z_mean, z_log_var])
x = layers.Dense(7 * 7 * 64, activation="relu")(z)
x = layers.Reshape((7, 7, 64))(x)
x = layers.Conv2DTranspose(64, 3, activation="relu", strides=2, padding="same")(x)
x = layers.Conv2DTranspose(32, 3, activation="relu", strides=2, padding="same")(x)
decoder_outputs = layers.Conv2DTranspose(1, 3, activation="sigmoid", padding="same")(x)
model = keras.Model(encoder_inputs, [decoder_outputs, z_mean, z_log_var] , name="decoder")
model.summary()

optimizer = tf.keras.optimizers.Adam(lr=0.001)
objective = tf.keras.losses.SparseCategoricalCrossentropy()

(x_train, _), (x_test, _) = keras.datasets.mnist.load_data()
x_train = x_train.astype("float32") / 255
num_samples = x_train.shape[0]
epochs=4
batch_size=128

@tf.function
def train_step(data):
  with tf.GradientTape() as tape:
    reconstruction, z_mean, z_log_var = model(data, training=True)
    reconstruction_loss = tf.reduce_mean(
        tf.reduce_sum(keras.losses.binary_crossentropy(data, reconstruction), axis=(1, 2)))
    
    kl_loss = -0.5 * (1 + z_log_var - tf.square(z_mean) - tf.exp(z_log_var))/batch_size
    kl_loss = tf.reduce_mean(tf.reduce_sum(kl_loss, axis=1))/batch_size
    total_loss = (reconstruction_loss + kl_loss)
  grads = tape.gradient(total_loss, model.trainable_variables)
  optimizer.apply_gradients(zip(grads, model.trainable_variables))
  return total_loss, reconstruction_loss, kl_loss


with tf.device('gpu:0'):
  for epoch in range (epochs):
    for step in range(num_samples//batch_size):
      s = step*batch_size
      e = s+batch_size
      x_batch = x_train[s:e,:,:, tf.newaxis]
      print(x_batch.shape)
      total_loss, reconstruction_loss, kl_loss = train_step(x_batch)
      print("-----------------")
      print(f"epoch: {epoch} step: {step}")
      print(f"reconstruction_loss: {reconstruction_loss} ")
      print(f"kl_loss: {kl_loss} ")
      print(f"total_loss: {total_loss}")