I am trying to create a mnist gan which will use tpu. I copied the gan code from here.
Then i made some of my own modifications to run the code on tpu.for making changes i followed this tutorial which shows how to us tpu on tensorflow on tensorflow website.
but thats not working and raising an error here is my code.
# -*- coding: utf-8 -*-
"""Untitled13.ipynb
Automatically generated by Colaboratory.
Original file is located at
https://colab.research.google.com/drive/1gbHDaCeFUCGDkkNgAPjGFQIDvZ5NxVfr
"""
# Commented out IPython magic to ensure Python compatibility.
# %tensorflow_version 2.x
import tensorflow as tf
import numpy as np
resolver = tf.distribute.cluster_resolver.TPUClusterResolver(tpu='')
tf.config.experimental_connect_to_cluster(resolver)
# This is the TPU initialization code that has to be at the beginning.
tf.tpu.experimental.initialize_tpu_system(resolver)
print("All devices: ", tf.config.list_logical_devices('TPU'))
strategy = tf.distribute.TPUStrategy(resolver)
import glob
import matplotlib.pyplot as plt
import numpy as np
import os
import PIL
from tensorflow.keras import layers
import time
from IPython import display
(train_images, train_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 # Normalize the images to [-1, 1]
BUFFER_SIZE = 60000
BATCH_SIZE = 256
# Batch and shuffle the data
train_dataset = tf.data.Dataset.from_tensor_slices(train_images).shuffle(BUFFER_SIZE).batch(BATCH_SIZE)
def make_generator_model():
model = tf.keras.Sequential()
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)))
assert model.output_shape == (None, 7, 7, 256) # Note: None is the batch size
model.add(layers.Conv2DTranspose(128, (5, 5), strides=(1, 1), padding='same', use_bias=False))
assert model.output_shape == (None, 7, 7, 128)
model.add(layers.BatchNormalization())
model.add(layers.LeakyReLU())
model.add(layers.Conv2DTranspose(64, (5, 5), strides=(2, 2), padding='same', use_bias=False))
assert model.output_shape == (None, 14, 14, 64)
model.add(layers.BatchNormalization())
model.add(layers.LeakyReLU())
model.add(layers.Conv2DTranspose(1, (5, 5), strides=(2, 2), padding='same', use_bias=False, activation='tanh'))
assert model.output_shape == (None, 28, 28, 1)
return model
def make_discriminator_model():
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))
model.add(layers.Flatten())
model.add(layers.Dense(1))
return model
# This method returns a helper function to compute cross entropy loss
cross_entropy = tf.keras.losses.BinaryCrossentropy(from_logits=True, reduction=tf.keras.losses.Reduction.NONE)
EPOCHS = 50
noise_dim = 100
num_examples_to_generate = 16
# You will reuse this seed overtime (so it's easier)
# to visualize progress in the animated GIF)
seed = tf.random.normal([num_examples_to_generate, noise_dim])
def generate_and_save_images(model, epoch, test_input):
# Notice `training` is set to False.
# This is so all layers run in inference mode (batchnorm).
predictions = model(test_input, training=False)
fig = plt.figure(figsize=(4, 4))
for i in range(predictions.shape[0]):
plt.subplot(4, 4, i+1)
plt.imshow(predictions[i, :, :, 0] * 127.5 + 127.5, cmap='gray')
plt.axis('off')
plt.savefig('image_at_epoch_{:04d}.png'.format(epoch))
plt.show()
def train(dataset, epochs):
for epoch in range(epochs):
start = time.time()
for image_batch in (dataset):
strategy.run(train_step, args=(image_batch,))
# Produce images for the GIF as you go
display.clear_output(wait=True)
generate_and_save_images(generator,
epoch + 1,
seed)
# Save the model every 15 epochs
if (epoch + 1) % 15 == 0:
checkpoint.save(file_prefix = checkpoint_prefix)
print ('Time for epoch {} is {} sec'.format(epoch + 1, time.time()-start))
# Generate after the final epoch
display.clear_output(wait=True)
generate_and_save_images(generator,
epochs,
seed)
def generator_loss(fake_output):
return cross_entropy(tf.ones_like(fake_output), fake_output)
def discriminator_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
# Notice the use of `tf.function`
# This annotation causes the function to be "compiled".
@tf.function
def train_step(images):
noise = tf.random.normal([BATCH_SIZE, noise_dim])
with tf.GradientTape() as gen_tape, tf.GradientTape() as disc_tape:
generated_images = generator(noise, training=True)
real_output = discriminator(images, training=True)
fake_output = discriminator(generated_images, training=True)
fake_output_0 = discriminator(generated_images, training=True)
gen_loss = generator_loss(fake_output_0)
disc_loss = discriminator_loss(real_output, fake_output)
gradients_of_generator = gen_tape.gradient(gen_loss, generator.trainable_variables)
gradients_of_discriminator = disc_tape.gradient(disc_loss, discriminator.trainable_variables)
generator_optimizer.apply_gradients(zip(gradients_of_generator, generator.trainable_variables))
discriminator_optimizer.apply_gradients(zip(gradients_of_discriminator, discriminator.trainable_variables))
with strategy.scope():
generator = make_generator_model()
generator_optimizer = tf.keras.optimizers.Adam(1e-4)
discriminator = make_discriminator_model()
discriminator_optimizer = tf.keras.optimizers.Adam(1e-4)
checkpoint_dir = './training_checkpoints'
checkpoint_prefix = os.path.join(checkpoint_dir, "ckpt")
checkpoint = tf.train.Checkpoint(generator_optimizer=generator_optimizer,
discriminator_optimizer=discriminator_optimizer,
generator=generator,
discriminator=discriminator)
train(train_dataset, EPOCHS)
and the final output is (not showing whole output cause i am in colab and i do not want copy output pf each cell one by one)
ValueError: Dimensions must be equal, but are 96 and 256 for '{{node add}} = AddV2[T=DT_FLOAT](binary_crossentropy/weighted_loss/Mul, binary_crossentropy_1/weighted_loss/Mul)' with input shapes: [96], [256].
Advertisement
Answer
The training data has 60000 instances, if you split them into batches of size 256 you are left a smaller batch of size 60000 % 256 which is 96. Keras also assumes this as a batch if you dont drop it. So in train_step for this batch of size 96, the shape of real_output will be (96, 1) and the shape of fake_output will be (256, 1). As you set reduction to None in cross_entropy loss, the shape will be retained, so shape of real_loss will (96,) and shape of fake_loss will be (256,) then adding them will definitely result in an error.
You may solve this problem this way –
# Let reduction param be default one which is 'auto'/'sum_over_batch_size' reduction type cross_entropy = tf.keras.losses.BinaryCrossentropy(from_logits=True)
or
# Drop the remainder batch train_dataset = tf.data.Dataset.from_tensor_slices(train_images).shuffle(BUFFER_SIZE).batch(BATCH_SIZE, drop_remainder=True)