%matplotlib inline
import numpy as np
import matplotlib.pyplot as plt
from keras.layers import Input, Dense, Conv2D, Add, Dot, Conv2DTranspose, Activation, Reshape, LeakyReLU, Flatten, BatchNormalization
from SpectralNormalizationKeras import DenseSN, ConvSN2D
from keras.models import Model, Sequential
from keras.optimizers import Adam
import keras.backend as K
from keras.utils.generic_utils import Progbar
from time import time
/home/mathlab115/anaconda3/lib/python3.6/site-packages/h5py/__init__.py:34: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`. from ._conv import register_converters as _register_converters Using TensorFlow backend.
# for resist GPU memory
import tensorflow as tf
config = tf.ConfigProto()
config.gpu_options.allow_growth=True
sess = tf.Session(config=config)
K.set_session(sess)
#load Data
from keras.datasets import cifar100, cifar10
(x_train, y_train), (x_test, y_test) = cifar10.load_data()
X = np.concatenate((x_test,x_train))
X.shape
(60000, 32, 32, 3)
plt.imshow(X[9487])
<matplotlib.image.AxesImage at 0x7f67045422b0>
#Hyperperemeter
BATCHSIZE=64
LEARNING_RATE = 0.0002
TRAINING_RATIO = 1
BETA_1 = 0.0
BETA_2 = 0.9
EPOCHS = 500
BN_MIMENTUM = 0.1
BN_EPSILON = 0.00002
SAVE_DIR = 'img/generated_img_CIFAR10_DCGAN/'
GENERATE_ROW_NUM = 8
GENERATE_BATCHSIZE = GENERATE_ROW_NUM*GENERATE_ROW_NUM
def BuildGenerator(summary=True):
model = Sequential()
model.add(Dense(4*4*512, kernel_initializer='glorot_uniform' , input_dim=128))
model.add(Reshape((4,4,512)))
model.add(Conv2DTranspose(256, kernel_size=4, strides=2, padding='same', activation='relu',kernel_initializer='glorot_uniform'))
model.add(BatchNormalization(epsilon=BN_EPSILON, momentum=BN_MIMENTUM))
model.add(Conv2DTranspose(128, kernel_size=4, strides=2, padding='same', activation='relu',kernel_initializer='glorot_uniform'))
model.add(BatchNormalization(epsilon=BN_EPSILON, momentum=BN_MIMENTUM))
model.add(Conv2DTranspose(64, kernel_size=4, strides=2, padding='same', activation='relu',kernel_initializer='glorot_uniform'))
model.add(BatchNormalization(epsilon=BN_EPSILON, momentum=BN_MIMENTUM))
model.add(Conv2DTranspose(3, kernel_size=3, strides=1, padding='same', activation='tanh'))
if summary:
print("Generator")
model.summary()
return model
def BuildDiscriminator(summary=True, spectral_normalization=True):
if spectral_normalization:
model = Sequential()
model.add(ConvSN2D(64, kernel_size=3, strides=1,kernel_initializer='glorot_uniform', padding='same', input_shape=(32,32,3) ))
model.add(LeakyReLU(0.1))
model.add(ConvSN2D(64, kernel_size=4, strides=2,kernel_initializer='glorot_uniform', padding='same'))
model.add(LeakyReLU(0.1))
model.add(ConvSN2D(128, kernel_size=3, strides=1,kernel_initializer='glorot_uniform', padding='same'))
model.add(LeakyReLU(0.1))
model.add(ConvSN2D(128, kernel_size=4, strides=2,kernel_initializer='glorot_uniform', padding='same'))
model.add(LeakyReLU(0.1))
model.add(ConvSN2D(256, kernel_size=3, strides=1,kernel_initializer='glorot_uniform', padding='same'))
model.add(LeakyReLU(0.1))
model.add(ConvSN2D(256, kernel_size=4, strides=2,kernel_initializer='glorot_uniform', padding='same'))
model.add(LeakyReLU(0.1))
model.add(ConvSN2D(512, kernel_size=3, strides=1,kernel_initializer='glorot_uniform', padding='same'))
model.add(LeakyReLU(0.1))
model.add(Flatten())
model.add(DenseSN(1,kernel_initializer='glorot_uniform'))
else:
model = Sequential()
model.add(Conv2D(64, kernel_size=3, strides=1,kernel_initializer='glorot_uniform', padding='same', input_shape=(32,32,3) ))
model.add(LeakyReLU(0.1))
model.add(Conv2D(64, kernel_size=4, strides=2,kernel_initializer='glorot_uniform', padding='same'))
model.add(LeakyReLU(0.1))
model.add(Conv2D(128, kernel_size=3, strides=1,kernel_initializer='glorot_uniform', padding='same'))
model.add(LeakyReLU(0.1))
model.add(Conv2D(128, kernel_size=4, strides=2,kernel_initializer='glorot_uniform', padding='same'))
model.add(LeakyReLU(0.1))
model.add(Conv2D(256, kernel_size=3, strides=1,kernel_initializer='glorot_uniform', padding='same'))
model.add(LeakyReLU(0.1))
model.add(Conv2D(256, kernel_size=4, strides=2,kernel_initializer='glorot_uniform', padding='same'))
model.add(LeakyReLU(0.1))
model.add(Conv2D(512, kernel_size=3, strides=1,kernel_initializer='glorot_uniform', padding='same'))
model.add(LeakyReLU(0.1))
model.add(Flatten())
model.add(Dense(1,kernel_initializer='glorot_uniform'))
if summary:
print('Discriminator')
print('Spectral Normalization: {}'.format(spectral_normalization))
model.summary()
return model
def wasserstein_loss(y_true, y_pred):
return K.mean(y_true*y_pred)
generator = BuildGenerator()
discriminator = BuildDiscriminator()
Generator _________________________________________________________________ Layer (type) Output Shape Param # ================================================================= dense_1 (Dense) (None, 8192) 1056768 _________________________________________________________________ reshape_1 (Reshape) (None, 4, 4, 512) 0 _________________________________________________________________ conv2d_transpose_1 (Conv2DTr (None, 8, 8, 256) 2097408 _________________________________________________________________ batch_normalization_1 (Batch (None, 8, 8, 256) 1024 _________________________________________________________________ conv2d_transpose_2 (Conv2DTr (None, 16, 16, 128) 524416 _________________________________________________________________ batch_normalization_2 (Batch (None, 16, 16, 128) 512 _________________________________________________________________ conv2d_transpose_3 (Conv2DTr (None, 32, 32, 64) 131136 _________________________________________________________________ batch_normalization_3 (Batch (None, 32, 32, 64) 256 _________________________________________________________________ conv2d_transpose_4 (Conv2DTr (None, 32, 32, 3) 1731 ================================================================= Total params: 3,813,251 Trainable params: 3,812,355 Non-trainable params: 896 _________________________________________________________________ Discriminator Spectral Normalization: True _________________________________________________________________ Layer (type) Output Shape Param # ================================================================= conv_s_n2d_1 (ConvSN2D) (None, 32, 32, 64) 1792 _________________________________________________________________ leaky_re_lu_1 (LeakyReLU) (None, 32, 32, 64) 0 _________________________________________________________________ conv_s_n2d_2 (ConvSN2D) (None, 16, 16, 64) 65600 _________________________________________________________________ leaky_re_lu_2 (LeakyReLU) (None, 16, 16, 64) 0 _________________________________________________________________ conv_s_n2d_3 (ConvSN2D) (None, 16, 16, 128) 73856 _________________________________________________________________ leaky_re_lu_3 (LeakyReLU) (None, 16, 16, 128) 0 _________________________________________________________________ conv_s_n2d_4 (ConvSN2D) (None, 8, 8, 128) 262272 _________________________________________________________________ leaky_re_lu_4 (LeakyReLU) (None, 8, 8, 128) 0 _________________________________________________________________ conv_s_n2d_5 (ConvSN2D) (None, 8, 8, 256) 295168 _________________________________________________________________ leaky_re_lu_5 (LeakyReLU) (None, 8, 8, 256) 0 _________________________________________________________________ conv_s_n2d_6 (ConvSN2D) (None, 4, 4, 256) 1048832 _________________________________________________________________ leaky_re_lu_6 (LeakyReLU) (None, 4, 4, 256) 0 _________________________________________________________________ conv_s_n2d_7 (ConvSN2D) (None, 4, 4, 512) 1180160 _________________________________________________________________ leaky_re_lu_7 (LeakyReLU) (None, 4, 4, 512) 0 _________________________________________________________________ flatten_1 (Flatten) (None, 8192) 0 _________________________________________________________________ dense_sn_1 (DenseSN) (None, 1) 8193 ================================================================= Total params: 2,935,873 Trainable params: 2,935,873 Non-trainable params: 0 _________________________________________________________________
Noise_input_for_training_generator = Input(shape=(128,))
Generated_image = generator(Noise_input_for_training_generator)
Discriminator_output = discriminator(Generated_image)
model_for_training_generator = Model(Noise_input_for_training_generator, Discriminator_output)
print("model_for_training_generator")
model_for_training_generator.summary()
model_for_training_generator _________________________________________________________________ Layer (type) Output Shape Param # ================================================================= input_1 (InputLayer) (None, 128) 0 _________________________________________________________________ sequential_1 (Sequential) (None, 32, 32, 3) 3813251 _________________________________________________________________ sequential_2 (Sequential) (None, 1) 2935873 ================================================================= Total params: 6,749,124 Trainable params: 6,748,228 Non-trainable params: 896 _________________________________________________________________
discriminator.trainable = False
model_for_training_generator.summary()
_________________________________________________________________ Layer (type) Output Shape Param # ================================================================= input_1 (InputLayer) (None, 128) 0 _________________________________________________________________ sequential_1 (Sequential) (None, 32, 32, 3) 3813251 _________________________________________________________________ sequential_2 (Sequential) (None, 1) 2935873 ================================================================= Total params: 6,749,124 Trainable params: 3,812,355 Non-trainable params: 2,936,769 _________________________________________________________________
model_for_training_generator.compile(optimizer=Adam(LEARNING_RATE, beta_1=BETA_1, beta_2=BETA_2), loss=wasserstein_loss)
Real_image = Input(shape=(32,32,3))
Noise_input_for_training_discriminator = Input(shape=(128,))
Fake_image = generator(Noise_input_for_training_discriminator)
Discriminator_output_for_real = discriminator(Real_image)
Discriminator_output_for_fake = discriminator(Fake_image)
model_for_training_discriminator = Model([Real_image,
Noise_input_for_training_discriminator],
[Discriminator_output_for_real,
Discriminator_output_for_fake])
print("model_for_training_discriminator")
generator.trainable = False
discriminator.trainable = True
model_for_training_discriminator.compile(optimizer=Adam(LEARNING_RATE, beta_1=BETA_1, beta_2=BETA_2), loss=[wasserstein_loss, wasserstein_loss])
model_for_training_discriminator.summary()
model_for_training_discriminator ____________________________________________________________________________________________________ Layer (type) Output Shape Param # Connected to ==================================================================================================== input_3 (InputLayer) (None, 128) 0 ____________________________________________________________________________________________________ input_2 (InputLayer) (None, 32, 32, 3) 0 ____________________________________________________________________________________________________ sequential_1 (Sequential) (None, 32, 32, 3) 3813251 input_3[0][0] ____________________________________________________________________________________________________ sequential_2 (Sequential) (None, 1) 2935873 input_2[0][0] sequential_1[2][0] ==================================================================================================== Total params: 6,749,124 Trainable params: 2,935,873 Non-trainable params: 3,813,251 ____________________________________________________________________________________________________
real_y = np.ones((BATCHSIZE, 1), dtype=np.float32)
fake_y = -real_y
X = X/255*2-1
plt.imshow((X[8787]+1)/2)
<matplotlib.image.AxesImage at 0x7f66d8660710>
test_noise = np.random.randn(GENERATE_BATCHSIZE, 128)
W_loss = []
discriminator_loss = []
generator_loss = []
for epoch in range(EPOCHS):
np.random.shuffle(X)
print("epoch {} of {}".format(epoch+1, EPOCHS))
num_batches = int(X.shape[0] // BATCHSIZE)
print("number of batches: {}".format(int(X.shape[0] // (BATCHSIZE))))
progress_bar = Progbar(target=int(X.shape[0] // (BATCHSIZE * TRAINING_RATIO)))
minibatches_size = BATCHSIZE * TRAINING_RATIO
start_time = time()
for index in range(int(X.shape[0] // (BATCHSIZE * TRAINING_RATIO))):
progress_bar.update(index)
discriminator_minibatches = X[index * minibatches_size:(index + 1) * minibatches_size]
for j in range(TRAINING_RATIO):
image_batch = discriminator_minibatches[j * BATCHSIZE : (j + 1) * BATCHSIZE]
noise = np.random.randn(BATCHSIZE, 128).astype(np.float32)
discriminator.trainable = True
generator.trainable = False
discriminator_loss.append(model_for_training_discriminator.train_on_batch([image_batch, noise],
[real_y, fake_y]))
discriminator.trainable = False
generator.trainable = True
generator_loss.append(model_for_training_generator.train_on_batch(np.random.randn(BATCHSIZE, 128), real_y))
print('\nepoch time: {}'.format(time()-start_time))
W_real = model_for_training_generator.evaluate(test_noise, real_y)
print(W_real)
W_fake = model_for_training_generator.evaluate(test_noise, fake_y)
print(W_fake)
W_l = W_real+W_fake
print('wasserstein_loss: {}'.format(W_l))
W_loss.append(W_l)
#Generate image
generated_image = generator.predict(test_noise)
generated_image = (generated_image+1)/2
for i in range(GENERATE_ROW_NUM):
new = generated_image[i*GENERATE_ROW_NUM:i*GENERATE_ROW_NUM+GENERATE_ROW_NUM].reshape(32*GENERATE_ROW_NUM,32,3)
if i!=0:
old = np.concatenate((old,new),axis=1)
else:
old = new
print('plot generated_image')
plt.imsave('{}/SN_epoch_{}.png'.format(SAVE_DIR, epoch), old)
epoch 1 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 65.86544990539551 32/64 [==============>...............] - ETA: 0s570.5799560546875 32/64 [==============>...............] - ETA: 0s-570.5798645019531 wasserstein_loss: 9.1552734375e-05 plot generated_image epoch 2 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.417253255844116 32/64 [==============>...............] - ETA: 0s-1419.6844482421875 32/64 [==============>...............] - ETA: 0s1419.6845703125 wasserstein_loss: 0.0001220703125 plot generated_image epoch 3 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.60102653503418 32/64 [==============>...............] - ETA: 0s-20.736841201782227 32/64 [==============>...............] - ETA: 0s20.736845016479492 wasserstein_loss: 3.814697265625e-06 plot generated_image epoch 4 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.488672494888306 32/64 [==============>...............] - ETA: 0s-467.9405517578125 32/64 [==============>...............] - ETA: 0s467.9406433105469 wasserstein_loss: 9.1552734375e-05 plot generated_image epoch 5 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.463491439819336 32/64 [==============>...............] - ETA: 0s-2740.6065673828125 32/64 [==============>...............] - ETA: 0s2740.6065673828125 wasserstein_loss: 0.0 plot generated_image epoch 6 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.19471621513367 32/64 [==============>...............] - ETA: 0s33986.4697265625 32/64 [==============>...............] - ETA: 0s-33986.4658203125 wasserstein_loss: 0.00390625 plot generated_image epoch 7 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 120.58621335029602 32/64 [==============>...............] - ETA: 0s-143514.0390625 32/64 [==============>...............] - ETA: 0s143514.0546875 wasserstein_loss: 0.015625 plot generated_image epoch 8 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.26368141174316 32/64 [==============>...............] - ETA: 0s-6521.294677734375 32/64 [==============>...............] - ETA: 0s6521.296142578125 wasserstein_loss: 0.00146484375 plot generated_image epoch 9 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.3119397163391 32/64 [==============>...............] - ETA: 0s-646.8974304199219 32/64 [==============>...............] - ETA: 0s646.8973693847656 wasserstein_loss: -6.103515625e-05 plot generated_image epoch 10 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.54890727996826 32/64 [==============>...............] - ETA: 0s-494.1124572753906 32/64 [==============>...............] - ETA: 0s494.1125183105469 wasserstein_loss: 6.103515625e-05 plot generated_image epoch 11 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.52118825912476 32/64 [==============>...............] - ETA: 0s-221.15088653564453 32/64 [==============>...............] - ETA: 0s221.15084838867188 wasserstein_loss: -3.814697265625e-05 plot generated_image epoch 12 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.35449123382568 32/64 [==============>...............] - ETA: 0s-64775.17578125 32/64 [==============>...............] - ETA: 0s64775.1796875 wasserstein_loss: 0.00390625 plot generated_image epoch 13 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.428808927536 32/64 [==============>...............] - ETA: 0s7988.553955078125 32/64 [==============>...............] - ETA: 0s-7988.552978515625 wasserstein_loss: 0.0009765625 plot generated_image epoch 14 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.49066424369812 32/64 [==============>...............] - ETA: 0s1659.7249145507812 32/64 [==============>...............] - ETA: 0s-1659.7246704101562 wasserstein_loss: 0.000244140625 plot generated_image epoch 15 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.37134718894958 32/64 [==============>...............] - ETA: 0s-17474.830078125 32/64 [==============>...............] - ETA: 0s17474.833984375 wasserstein_loss: 0.00390625 plot generated_image epoch 16 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.81145119667053 32/64 [==============>...............] - ETA: 0s21.61222553253174 32/64 [==============>...............] - ETA: 0s-21.612226486206055 wasserstein_loss: -9.5367431640625e-07 plot generated_image epoch 17 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.52231645584106 32/64 [==============>...............] - ETA: 0s-1253.4354858398438 32/64 [==============>...............] - ETA: 0s1253.4356079101562 wasserstein_loss: 0.0001220703125 plot generated_image epoch 18 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.2138693332672 32/64 [==============>...............] - ETA: 0s1620.368408203125 32/64 [==============>...............] - ETA: 0s-1620.368408203125 wasserstein_loss: 0.0 plot generated_image epoch 19 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.3576946258545 32/64 [==============>...............] - ETA: 0s-265.8834991455078 32/64 [==============>...............] - ETA: 0s265.88329315185547 wasserstein_loss: -0.00020599365234375 plot generated_image epoch 20 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.5011055469513 32/64 [==============>...............] - ETA: 0s107.43426513671875 32/64 [==============>...............] - ETA: 0s-107.43423461914062 wasserstein_loss: 3.0517578125e-05 plot generated_image epoch 21 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.426411151886 32/64 [==============>...............] - ETA: 0s-1991.7146606445312 32/64 [==============>...............] - ETA: 0s1991.7147827148438 wasserstein_loss: 0.0001220703125 plot generated_image epoch 22 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.23574352264404 32/64 [==============>...............] - ETA: 0s-1870.8526000976562 32/64 [==============>...............] - ETA: 0s1870.8524780273438 wasserstein_loss: -0.0001220703125 plot generated_image epoch 23 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.43622708320618 32/64 [==============>...............] - ETA: 0s-2758.612060546875 32/64 [==============>...............] - ETA: 0s2758.61083984375 wasserstein_loss: -0.001220703125 plot generated_image epoch 24 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.246826171875 32/64 [==============>...............] - ETA: 0s393296.796875 32/64 [==============>...............] - ETA: 0s-393296.953125 wasserstein_loss: -0.15625 plot generated_image epoch 25 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.49978041648865 32/64 [==============>...............] - ETA: 0s-49747.916015625 32/64 [==============>...............] - ETA: 0s49747.9140625 wasserstein_loss: -0.001953125 plot generated_image epoch 26 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.6655147075653 32/64 [==============>...............] - ETA: 0s5166.06787109375 32/64 [==============>...............] - ETA: 0s-5166.06689453125 wasserstein_loss: 0.0009765625 plot generated_image epoch 27 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.58912348747253 32/64 [==============>...............] - ETA: 0s2182.495361328125 32/64 [==============>...............] - ETA: 0s-2182.4957275390625 wasserstein_loss: -0.0003662109375 plot generated_image epoch 28 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 85.38367366790771 32/64 [==============>...............] - ETA: 0s-2414.850830078125 32/64 [==============>...............] - ETA: 0s2414.850341796875 wasserstein_loss: -0.00048828125 plot generated_image epoch 29 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.76259994506836 32/64 [==============>...............] - ETA: 0s-1323.6307983398438 32/64 [==============>...............] - ETA: 0s1323.630615234375 wasserstein_loss: -0.00018310546875 plot generated_image epoch 30 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.481377363204956 32/64 [==============>...............] - ETA: 0s2133.3223876953125 32/64 [==============>...............] - ETA: 0s-2133.3224487304688 wasserstein_loss: -6.103515625e-05 plot generated_image epoch 31 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.35567259788513 32/64 [==============>...............] - ETA: 0s-27.123507499694824 32/64 [==============>...............] - ETA: 0s27.123507499694824 wasserstein_loss: 0.0 plot generated_image epoch 32 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.52164435386658 32/64 [==============>...............] - ETA: 0s-79356.1953125 32/64 [==============>...............] - ETA: 0s79356.17578125 wasserstein_loss: -0.01953125 plot generated_image epoch 33 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.481844425201416 32/64 [==============>...............] - ETA: 0s-73326.228515625 32/64 [==============>...............] - ETA: 0s73326.25390625 wasserstein_loss: 0.025390625 plot generated_image epoch 34 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.65121102333069 32/64 [==============>...............] - ETA: 0s761.7375793457031 32/64 [==============>...............] - ETA: 0s-761.7377319335938 wasserstein_loss: -0.000152587890625 plot generated_image epoch 35 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.539536476135254 32/64 [==============>...............] - ETA: 0s801.9946594238281 32/64 [==============>...............] - ETA: 0s-801.994873046875 wasserstein_loss: -0.000213623046875 plot generated_image epoch 36 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.55997920036316 32/64 [==============>...............] - ETA: 0s13857.91357421875 32/64 [==============>...............] - ETA: 0s-13857.9130859375 wasserstein_loss: 0.00048828125 plot generated_image epoch 37 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.64079022407532 32/64 [==============>...............] - ETA: 0s29769.412109375 32/64 [==============>...............] - ETA: 0s-29769.41796875 wasserstein_loss: -0.005859375 plot generated_image epoch 38 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.72667121887207 32/64 [==============>...............] - ETA: 0s1003.4847412109375 32/64 [==============>...............] - ETA: 0s-1003.4847106933594 wasserstein_loss: 3.0517578125e-05 plot generated_image epoch 39 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.60920190811157 32/64 [==============>...............] - ETA: 0s134.67667388916016 32/64 [==============>...............] - ETA: 0s-134.6766815185547 wasserstein_loss: -7.62939453125e-06 plot generated_image epoch 40 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.91673946380615 32/64 [==============>...............] - ETA: 0s4637.380615234375 32/64 [==============>...............] - ETA: 0s-4637.380126953125 wasserstein_loss: 0.00048828125 plot generated_image epoch 41 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.53546214103699 32/64 [==============>...............] - ETA: 0s139750.703125 32/64 [==============>...............] - ETA: 0s-139750.6796875 wasserstein_loss: 0.0234375 plot generated_image epoch 42 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.754098653793335 32/64 [==============>...............] - ETA: 0s18963.7978515625 32/64 [==============>...............] - ETA: 0s-18963.7978515625 wasserstein_loss: 0.0 plot generated_image epoch 43 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.697935819625854 32/64 [==============>...............] - ETA: 0s-2074.7469482421875 32/64 [==============>...............] - ETA: 0s2074.7494506835938 wasserstein_loss: 0.00250244140625 plot generated_image epoch 44 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.54356050491333 32/64 [==============>...............] - ETA: 0s-77849.2109375 32/64 [==============>...............] - ETA: 0s77849.2109375 wasserstein_loss: 0.0 plot generated_image epoch 45 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.707026720047 32/64 [==============>...............] - ETA: 0s2984.5404052734375 32/64 [==============>...............] - ETA: 0s-2984.541015625 wasserstein_loss: -0.0006103515625 plot generated_image epoch 46 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.5827214717865 32/64 [==============>...............] - ETA: 0s35988.849609375 32/64 [==============>...............] - ETA: 0s-35988.853515625 wasserstein_loss: -0.00390625 plot generated_image epoch 47 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.475356578826904 32/64 [==============>...............] - ETA: 0s5380.19921875 32/64 [==============>...............] - ETA: 0s-5380.19921875 wasserstein_loss: 0.0 plot generated_image epoch 48 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.58155703544617 32/64 [==============>...............] - ETA: 0s-460580.15625 32/64 [==============>...............] - ETA: 0s460580.15625 wasserstein_loss: 0.0 plot generated_image epoch 49 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.4945547580719 32/64 [==============>...............] - ETA: 0s3811.872314453125 32/64 [==============>...............] - ETA: 0s-3811.8720703125 wasserstein_loss: 0.000244140625 plot generated_image epoch 50 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.751960039138794 32/64 [==============>...............] - ETA: 0s9155.614501953125 32/64 [==============>...............] - ETA: 0s-9155.611206054688 wasserstein_loss: 0.0032958984375 plot generated_image epoch 51 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.37737584114075 32/64 [==============>...............] - ETA: 0s155631.9921875 32/64 [==============>...............] - ETA: 0s-155631.9921875 wasserstein_loss: 0.0 plot generated_image epoch 52 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.48959469795227 32/64 [==============>...............] - ETA: 0s-40504.81640625 32/64 [==============>...............] - ETA: 0s40504.814453125 wasserstein_loss: -0.001953125 plot generated_image epoch 53 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.5045371055603 32/64 [==============>...............] - ETA: 0s83985.1171875 32/64 [==============>...............] - ETA: 0s-83985.115234375 wasserstein_loss: 0.001953125 plot generated_image epoch 54 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.34590148925781 32/64 [==============>...............] - ETA: 0s31955.2802734375 32/64 [==============>...............] - ETA: 0s-31955.275390625 wasserstein_loss: 0.0048828125 plot generated_image epoch 55 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.92101573944092 32/64 [==============>...............] - ETA: 0s-509101.234375 32/64 [==============>...............] - ETA: 0s509101.25 wasserstein_loss: 0.015625 plot generated_image epoch 56 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.43449950218201 32/64 [==============>...............] - ETA: 0s-113165.3125 32/64 [==============>...............] - ETA: 0s113165.30859375 wasserstein_loss: -0.00390625 plot generated_image epoch 57 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.79249858856201 32/64 [==============>...............] - ETA: 0s-19227.83203125 32/64 [==============>...............] - ETA: 0s19227.8310546875 wasserstein_loss: -0.0009765625 plot generated_image epoch 58 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.47976851463318 32/64 [==============>...............] - ETA: 0s25798.8232421875 32/64 [==============>...............] - ETA: 0s-25798.8212890625 wasserstein_loss: 0.001953125 plot generated_image epoch 59 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.42741060256958 32/64 [==============>...............] - ETA: 0s357181.734375 32/64 [==============>...............] - ETA: 0s-357181.8125 wasserstein_loss: -0.078125 plot generated_image epoch 60 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.581618785858154 32/64 [==============>...............] - ETA: 0s825175.5625 32/64 [==============>...............] - ETA: 0s-825175.53125 wasserstein_loss: 0.03125 plot generated_image epoch 61 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.55902814865112 32/64 [==============>...............] - ETA: 0s229420.109375 32/64 [==============>...............] - ETA: 0s-229420.15625 wasserstein_loss: -0.046875 plot generated_image epoch 62 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.73611521720886 32/64 [==============>...............] - ETA: 0s17554.77392578125 32/64 [==============>...............] - ETA: 0s-17554.7744140625 wasserstein_loss: -0.00048828125 plot generated_image epoch 63 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.84701991081238 32/64 [==============>...............] - ETA: 0s18010.853515625 32/64 [==============>...............] - ETA: 0s-18010.853515625 wasserstein_loss: 0.0 plot generated_image epoch 64 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.68135046958923 32/64 [==============>...............] - ETA: 0s-2095280.125 32/64 [==============>...............] - ETA: 0s2095280.1875 wasserstein_loss: 0.0625 plot generated_image epoch 65 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.635685205459595 32/64 [==============>...............] - ETA: 0s2560.904052734375 32/64 [==============>...............] - ETA: 0s-2560.904296875 wasserstein_loss: -0.000244140625 plot generated_image epoch 66 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.646416425704956 32/64 [==============>...............] - ETA: 0s-121894.1640625 32/64 [==============>...............] - ETA: 0s121894.16015625 wasserstein_loss: -0.00390625 plot generated_image epoch 67 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.65143799781799 32/64 [==============>...............] - ETA: 0s2324.087158203125 32/64 [==============>...............] - ETA: 0s-2324.08740234375 wasserstein_loss: -0.000244140625 plot generated_image epoch 68 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.551685094833374 32/64 [==============>...............] - ETA: 0s8093.17822265625 32/64 [==============>...............] - ETA: 0s-8093.177734375 wasserstein_loss: 0.00048828125 plot generated_image epoch 69 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.53459882736206 32/64 [==============>...............] - ETA: 0s122.18748092651367 32/64 [==============>...............] - ETA: 0s-122.18754196166992 wasserstein_loss: -6.103515625e-05 plot generated_image epoch 70 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s E epoch time: 63.44887948036194 32/64 [==============>...............] - ETA: 0s759.5427551269531 32/64 [==============>...............] - ETA: 0s-759.5427551269531 wasserstein_loss: 0.0 plot generated_image epoch 71 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.37927746772766 32/64 [==============>...............] - ETA: 0s-26735.3671875 32/64 [==============>...............] - ETA: 0s26735.369140625 wasserstein_loss: 0.001953125 plot generated_image epoch 72 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.68051481246948 32/64 [==============>...............] - ETA: 0s-1192343.5 32/64 [==============>...............] - ETA: 0s1192343.4375 wasserstein_loss: -0.0625 plot generated_image epoch 73 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.62741732597351 32/64 [==============>...............] - ETA: 0s1120531.3125 32/64 [==============>...............] - ETA: 0s-1120531.375 wasserstein_loss: -0.0625 plot generated_image epoch 74 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.65434551239014 32/64 [==============>...............] - ETA: 0s5861.9140625 32/64 [==============>...............] - ETA: 0s-5861.91259765625 wasserstein_loss: 0.00146484375 plot generated_image epoch 75 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.684715032577515 32/64 [==============>...............] - ETA: 0s149708.99609375 32/64 [==============>...............] - ETA: 0s-149709.0 wasserstein_loss: -0.00390625 plot generated_image epoch 76 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.70629096031189 32/64 [==============>...............] - ETA: 0s156.78308868408203 32/64 [==============>...............] - ETA: 0s-156.7830352783203 wasserstein_loss: 5.340576171875e-05 plot generated_image epoch 77 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.843438148498535 32/64 [==============>...............] - ETA: 0s17462.1484375 32/64 [==============>...............] - ETA: 0s-17462.1484375 wasserstein_loss: 0.0 plot generated_image epoch 78 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.466408014297485 32/64 [==============>...............] - ETA: 0s-288689.953125 32/64 [==============>...............] - ETA: 0s288689.96875 wasserstein_loss: 0.015625 plot generated_image epoch 79 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.199339151382446 32/64 [==============>...............] - ETA: 0s21634.98046875 32/64 [==============>...............] - ETA: 0s-21634.990234375 wasserstein_loss: -0.009765625 plot generated_image epoch 80 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.56694054603577 32/64 [==============>...............] - ETA: 0s-81424.57421875 32/64 [==============>...............] - ETA: 0s81424.6640625 wasserstein_loss: 0.08984375 plot generated_image epoch 81 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.626300573349 32/64 [==============>...............] - ETA: 0s18609.5751953125 32/64 [==============>...............] - ETA: 0s-18609.5771484375 wasserstein_loss: -0.001953125 plot generated_image epoch 82 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.698270082473755 32/64 [==============>...............] - ETA: 0s2176.62255859375 32/64 [==============>...............] - ETA: 0s-2176.6207885742188 wasserstein_loss: 0.00177001953125 plot generated_image epoch 83 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.68456506729126 32/64 [==============>...............] - ETA: 0s104251.6875 32/64 [==============>...............] - ETA: 0s-104251.68359375 wasserstein_loss: 0.00390625 plot generated_image epoch 84 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.6310133934021 32/64 [==============>...............] - ETA: 0s1762311.375 32/64 [==============>...............] - ETA: 0s-1762311.4375 wasserstein_loss: -0.0625 plot generated_image epoch 85 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.635666608810425 32/64 [==============>...............] - ETA: 0s-21435.544921875 32/64 [==============>...............] - ETA: 0s21435.5458984375 wasserstein_loss: 0.0009765625 plot generated_image epoch 86 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.5364727973938 32/64 [==============>...............] - ETA: 0s676997.125 32/64 [==============>...............] - ETA: 0s-676997.0625 wasserstein_loss: 0.0625 plot generated_image epoch 87 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.358938455581665 32/64 [==============>...............] - ETA: 0s1018140.71875 32/64 [==============>...............] - ETA: 0s-1018140.90625 wasserstein_loss: -0.1875 plot generated_image epoch 88 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.66500902175903 32/64 [==============>...............] - ETA: 0s215127.15625 32/64 [==============>...............] - ETA: 0s-215127.1484375 wasserstein_loss: 0.0078125 plot generated_image epoch 89 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.558149337768555 32/64 [==============>...............] - ETA: 0s-24211.169921875 32/64 [==============>...............] - ETA: 0s24211.1796875 wasserstein_loss: 0.009765625 plot generated_image epoch 90 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.534690856933594 32/64 [==============>...............] - ETA: 0s1627779.875 32/64 [==============>...............] - ETA: 0s-1627780.0 wasserstein_loss: -0.125 plot generated_image epoch 91 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.599119424819946 32/64 [==============>...............] - ETA: 0s22809.6474609375 32/64 [==============>...............] - ETA: 0s-22809.64453125 wasserstein_loss: 0.0029296875 plot generated_image epoch 92 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.70444440841675 32/64 [==============>...............] - ETA: 0s4287.7125244140625 32/64 [==============>...............] - ETA: 0s-4287.712646484375 wasserstein_loss: -0.0001220703125 plot generated_image epoch 93 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.74416184425354 32/64 [==============>...............] - ETA: 0s2914419.75 32/64 [==============>...............] - ETA: 0s-2914419.5 wasserstein_loss: 0.25 plot generated_image epoch 94 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.65605568885803 32/64 [==============>...............] - ETA: 0s7622.52490234375 32/64 [==============>...............] - ETA: 0s-7622.5220947265625 wasserstein_loss: 0.0028076171875 plot generated_image epoch 95 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.70886588096619 32/64 [==============>...............] - ETA: 0s81940.4765625 32/64 [==============>...............] - ETA: 0s-81940.48828125 wasserstein_loss: -0.01171875 plot generated_image epoch 96 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.400141954422 32/64 [==============>...............] - ETA: 0s429118.65625 32/64 [==============>...............] - ETA: 0s-429118.65625 wasserstein_loss: 0.0 plot generated_image epoch 97 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.84165120124817 32/64 [==============>...............] - ETA: 0s-3273.0946655273438 32/64 [==============>...............] - ETA: 0s3273.0921630859375 wasserstein_loss: -0.00250244140625 plot generated_image epoch 98 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.52368187904358 32/64 [==============>...............] - ETA: 0s21534.3154296875 32/64 [==============>...............] - ETA: 0s-21534.314453125 wasserstein_loss: 0.0009765625 plot generated_image epoch 99 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.70034074783325 32/64 [==============>...............] - ETA: 0s-4465.191162109375 32/64 [==============>...............] - ETA: 0s4465.190673828125 wasserstein_loss: -0.00048828125 plot generated_image epoch 100 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.55988025665283 32/64 [==============>...............] - ETA: 0s1033263.09375 32/64 [==============>...............] - ETA: 0s-1033263.0625 wasserstein_loss: 0.03125 plot generated_image epoch 101 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.675445318222046 32/64 [==============>...............] - ETA: 0s39128.23046875 32/64 [==============>...............] - ETA: 0s-39128.22265625 wasserstein_loss: 0.0078125 plot generated_image epoch 102 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.70533084869385 32/64 [==============>...............] - ETA: 0s-785.59326171875 32/64 [==============>...............] - ETA: 0s785.5946044921875 wasserstein_loss: 0.0013427734375 plot generated_image epoch 103 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.69776153564453 32/64 [==============>...............] - ETA: 0s-3527.821533203125 32/64 [==============>...............] - ETA: 0s3527.821533203125 wasserstein_loss: 0.0 plot generated_image epoch 104 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.759361028671265 32/64 [==============>...............] - ETA: 0s55554.052734375 32/64 [==============>...............] - ETA: 0s-55554.05078125 wasserstein_loss: 0.001953125 plot generated_image epoch 105 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.66144919395447 32/64 [==============>...............] - ETA: 0s470067.7109375 32/64 [==============>...............] - ETA: 0s-470067.4921875 wasserstein_loss: 0.21875 plot generated_image epoch 106 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.60205125808716 32/64 [==============>...............] - ETA: 0s389086.5625 32/64 [==============>...............] - ETA: 0s-389086.515625 wasserstein_loss: 0.046875 plot generated_image epoch 107 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.525686740875244 32/64 [==============>...............] - ETA: 0s56568.771484375 32/64 [==============>...............] - ETA: 0s-56568.765625 wasserstein_loss: 0.005859375 plot generated_image epoch 108 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.803544759750366 32/64 [==============>...............] - ETA: 0s2044170.625 32/64 [==============>...............] - ETA: 0s-2044170.625 wasserstein_loss: 0.0 plot generated_image epoch 109 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.577022314071655 32/64 [==============>...............] - ETA: 0s2041643.375 32/64 [==============>...............] - ETA: 0s-2041643.75 wasserstein_loss: -0.375 plot generated_image epoch 110 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.80851912498474 32/64 [==============>...............] - ETA: 0s2406.21826171875 32/64 [==============>...............] - ETA: 0s-2406.2186279296875 wasserstein_loss: -0.0003662109375 plot generated_image epoch 111 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.73405742645264 32/64 [==============>...............] - ETA: 0s11256.60791015625 32/64 [==============>...............] - ETA: 0s-11256.60693359375 wasserstein_loss: 0.0009765625 plot generated_image epoch 112 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.636479139328 32/64 [==============>...............] - ETA: 0s1939063.3125 32/64 [==============>...............] - ETA: 0s-1939063.5 wasserstein_loss: -0.1875 plot generated_image epoch 113 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.68892693519592 32/64 [==============>...............] - ETA: 0s18313.0048828125 32/64 [==============>...............] - ETA: 0s-18313.0029296875 wasserstein_loss: 0.001953125 plot generated_image epoch 114 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.69321346282959 32/64 [==============>...............] - ETA: 0s-1171170.34375 32/64 [==============>...............] - ETA: 0s1171170.5625 wasserstein_loss: 0.21875 plot generated_image epoch 115 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.65535235404968 32/64 [==============>...............] - ETA: 0s44863.56640625 32/64 [==============>...............] - ETA: 0s-44863.568359375 wasserstein_loss: -0.001953125 plot generated_image epoch 116 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.7654983997345 32/64 [==============>...............] - ETA: 0s1747.3831787109375 32/64 [==============>...............] - ETA: 0s-1747.3831787109375 wasserstein_loss: 0.0 plot generated_image epoch 117 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.8717200756073 32/64 [==============>...............] - ETA: 0s401177.28125 32/64 [==============>...............] - ETA: 0s-401177.25 wasserstein_loss: 0.03125 plot generated_image epoch 118 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.72722244262695 32/64 [==============>...............] - ETA: 0s-24479.083984375 32/64 [==============>...............] - ETA: 0s24479.07421875 wasserstein_loss: -0.009765625 plot generated_image epoch 119 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.66445207595825 32/64 [==============>...............] - ETA: 0s7679.083984375 32/64 [==============>...............] - ETA: 0s-7679.083984375 wasserstein_loss: 0.0 plot generated_image epoch 120 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.912564754486084 32/64 [==============>...............] - ETA: 0s12280.7333984375 32/64 [==============>...............] - ETA: 0s-12280.7119140625 wasserstein_loss: 0.021484375 plot generated_image epoch 121 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.36395978927612 32/64 [==============>...............] - ETA: 0s21294.0947265625 32/64 [==============>...............] - ETA: 0s-21294.09375 wasserstein_loss: 0.0009765625 plot generated_image epoch 122 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 64.00698661804199 32/64 [==============>...............] - ETA: 0s-402.0682067871094 32/64 [==============>...............] - ETA: 0s402.0679931640625 wasserstein_loss: -0.000213623046875 plot generated_image epoch 123 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 62.8739447593689 32/64 [==============>...............] - ETA: 0s-151511.0234375 32/64 [==============>...............] - ETA: 0s151511.0078125 wasserstein_loss: -0.015625 plot generated_image epoch 124 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.54404354095459 32/64 [==============>...............] - ETA: 0s-932247.3125 32/64 [==============>...............] - ETA: 0s932247.375 wasserstein_loss: 0.0625 plot generated_image epoch 125 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 63.477423906326294 32/64 [==============>...............] - ETA: 0s-2966977.125 32/64 [==============>...............] - ETA: 0s2966977.125 wasserstein_loss: 0.0 plot generated_image epoch 126 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 90.98054194450378 32/64 [==============>...............] - ETA: 0s298728.328125 32/64 [==============>...............] - ETA: 0s-298728.3125 wasserstein_loss: 0.015625 plot generated_image epoch 127 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.2581169605255 32/64 [==============>...............] - ETA: 0s859160.875 32/64 [==============>...............] - ETA: 0s-859161.0625 wasserstein_loss: -0.1875 plot generated_image epoch 128 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.4725706577301 32/64 [==============>...............] - ETA: 0s6754437.25 32/64 [==============>...............] - ETA: 0s-6754436.25 wasserstein_loss: 1.0 plot generated_image epoch 129 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 92.22029232978821 32/64 [==============>...............] - ETA: 0s1564634.8125 32/64 [==============>...............] - ETA: 0s-1564634.8125 wasserstein_loss: 0.0 plot generated_image epoch 130 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 100.03885293006897 32/64 [==============>...............] - ETA: 0s97899.37890625 32/64 [==============>...............] - ETA: 0s-97899.3828125 wasserstein_loss: -0.00390625 plot generated_image epoch 131 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.2764537334442 32/64 [==============>...............] - ETA: 0s41604.53515625 32/64 [==============>...............] - ETA: 0s-41604.54296875 wasserstein_loss: -0.0078125 plot generated_image epoch 132 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.21879148483276 32/64 [==============>...............] - ETA: 0s40605.484375 32/64 [==============>...............] - ETA: 0s-40605.478515625 wasserstein_loss: 0.005859375 plot generated_image epoch 133 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.51913452148438 32/64 [==============>...............] - ETA: 0s214518.0859375 32/64 [==============>...............] - ETA: 0s-214518.0703125 wasserstein_loss: 0.015625 plot generated_image epoch 134 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.10009956359863 32/64 [==============>...............] - ETA: 0s123344.9453125 32/64 [==============>...............] - ETA: 0s-123344.9140625 wasserstein_loss: 0.03125 plot generated_image epoch 135 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.6028447151184 32/64 [==============>...............] - ETA: 0s1035.5948486328125 32/64 [==============>...............] - ETA: 0s-1035.59423828125 wasserstein_loss: 0.0006103515625 plot generated_image epoch 136 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.51336359977722 32/64 [==============>...............] - ETA: 0s133188.09765625 32/64 [==============>...............] - ETA: 0s-133188.09375 wasserstein_loss: 0.00390625 plot generated_image epoch 137 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.1413857936859 32/64 [==============>...............] - ETA: 0s-9734.141357421875 32/64 [==============>...............] - ETA: 0s9734.142333984375 wasserstein_loss: 0.0009765625 plot generated_image epoch 138 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.35851645469666 32/64 [==============>...............] - ETA: 0s3388.68310546875 32/64 [==============>...............] - ETA: 0s-3388.6829833984375 wasserstein_loss: 0.0001220703125 plot generated_image epoch 139 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.29530119895935 32/64 [==============>...............] - ETA: 0s4461845.0 32/64 [==============>...............] - ETA: 0s-4461845.25 wasserstein_loss: -0.25 plot generated_image epoch 140 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.34258890151978 32/64 [==============>...............] - ETA: 0s24317.57421875 32/64 [==============>...............] - ETA: 0s-24317.576171875 wasserstein_loss: -0.001953125 plot generated_image epoch 141 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.4493944644928 32/64 [==============>...............] - ETA: 0s72503.4609375 32/64 [==============>...............] - ETA: 0s-72503.45703125 wasserstein_loss: 0.00390625 plot generated_image epoch 142 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.6987280845642 32/64 [==============>...............] - ETA: 0s-286738.6015625 32/64 [==============>...............] - ETA: 0s286738.59375 wasserstein_loss: -0.0078125 plot generated_image epoch 143 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.52633714675903 32/64 [==============>...............] - ETA: 0s300382.296875 32/64 [==============>...............] - ETA: 0s-300382.28125 wasserstein_loss: 0.015625 plot generated_image epoch 144 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.56690669059753 32/64 [==============>...............] - ETA: 0s7134.33984375 32/64 [==============>...............] - ETA: 0s-7134.31640625 wasserstein_loss: 0.0234375 plot generated_image epoch 145 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.30307483673096 32/64 [==============>...............] - ETA: 0s298654.46875 32/64 [==============>...............] - ETA: 0s-298654.453125 wasserstein_loss: 0.015625 plot generated_image epoch 146 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.6303904056549 32/64 [==============>...............] - ETA: 0s9581149.0 32/64 [==============>...............] - ETA: 0s-9581151.0 wasserstein_loss: -2.0 plot generated_image epoch 147 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.46967005729675 32/64 [==============>...............] - ETA: 0s19526.373046875 32/64 [==============>...............] - ETA: 0s-19526.3798828125 wasserstein_loss: -0.0068359375 plot generated_image epoch 148 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.51828145980835 32/64 [==============>...............] - ETA: 0s-193105.1484375 32/64 [==============>...............] - ETA: 0s193105.1328125 wasserstein_loss: -0.015625 plot generated_image epoch 149 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.44229292869568 32/64 [==============>...............] - ETA: 0s130019.921875 32/64 [==============>...............] - ETA: 0s-130019.90625 wasserstein_loss: 0.015625 plot generated_image epoch 150 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.5628592967987 32/64 [==============>...............] - ETA: 0s5028.9306640625 32/64 [==============>...............] - ETA: 0s-5028.930908203125 wasserstein_loss: -0.000244140625 plot generated_image epoch 151 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.37159776687622 32/64 [==============>...............] - ETA: 0s35954.2333984375 32/64 [==============>...............] - ETA: 0s-35954.2255859375 wasserstein_loss: 0.0078125 plot generated_image epoch 152 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.41151189804077 32/64 [==============>...............] - ETA: 0s2071.8991088867188 32/64 [==============>...............] - ETA: 0s-2071.8994140625 wasserstein_loss: -0.00030517578125 plot generated_image epoch 153 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.21896076202393 32/64 [==============>...............] - ETA: 0s-24249.8564453125 32/64 [==============>...............] - ETA: 0s24249.8486328125 wasserstein_loss: -0.0078125 plot generated_image epoch 154 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.33394408226013 32/64 [==============>...............] - ETA: 0s21920.33203125 32/64 [==============>...............] - ETA: 0s-21920.3349609375 wasserstein_loss: -0.0029296875 plot generated_image epoch 155 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.21161031723022 32/64 [==============>...............] - ETA: 0s-53836.109375 32/64 [==============>...............] - ETA: 0s53836.10546875 wasserstein_loss: -0.00390625 plot generated_image epoch 156 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.45905947685242 32/64 [==============>...............] - ETA: 0s229407.9609375 32/64 [==============>...............] - ETA: 0s-229407.984375 wasserstein_loss: -0.0234375 plot generated_image epoch 157 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.52859044075012 32/64 [==============>...............] - ETA: 0s21418.171875 32/64 [==============>...............] - ETA: 0s-21418.169921875 wasserstein_loss: 0.001953125 plot generated_image epoch 158 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.21117162704468 32/64 [==============>...............] - ETA: 0s-1485652.625 32/64 [==============>...............] - ETA: 0s1485652.875 wasserstein_loss: 0.25 plot generated_image epoch 159 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.43936467170715 32/64 [==============>...............] - ETA: 0s-56377.078125 32/64 [==============>...............] - ETA: 0s56377.07421875 wasserstein_loss: -0.00390625 plot generated_image epoch 160 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.2586591243744 32/64 [==============>...............] - ETA: 0s-433444.453125 32/64 [==============>...............] - ETA: 0s433444.421875 wasserstein_loss: -0.03125 plot generated_image epoch 161 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.0935788154602 32/64 [==============>...............] - ETA: 0s19004.5078125 32/64 [==============>...............] - ETA: 0s-19004.5078125 wasserstein_loss: 0.0 plot generated_image epoch 162 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.19678020477295 32/64 [==============>...............] - ETA: 0s18283.7861328125 32/64 [==============>...............] - ETA: 0s-18283.798828125 wasserstein_loss: -0.0126953125 plot generated_image epoch 163 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.08730816841125 32/64 [==============>...............] - ETA: 0s-46664.322265625 32/64 [==============>...............] - ETA: 0s46664.330078125 wasserstein_loss: 0.0078125 plot generated_image epoch 164 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.06575775146484 32/64 [==============>...............] - ETA: 0s-5894.667724609375 32/64 [==============>...............] - ETA: 0s5894.6673583984375 wasserstein_loss: -0.0003662109375 plot generated_image epoch 165 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.2676305770874 32/64 [==============>...............] - ETA: 0s5193.876525878906 32/64 [==============>...............] - ETA: 0s-5193.8775634765625 wasserstein_loss: -0.00103759765625 plot generated_image epoch 166 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.06949949264526 32/64 [==============>...............] - ETA: 0s283060.828125 32/64 [==============>...............] - ETA: 0s-283060.890625 wasserstein_loss: -0.0625 plot generated_image epoch 167 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.1079249382019 32/64 [==============>...............] - ETA: 0s-5143120.0 32/64 [==============>...............] - ETA: 0s5143119.75 wasserstein_loss: -0.25 plot generated_image epoch 168 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.0216999053955 32/64 [==============>...............] - ETA: 0s1087.3720703125 32/64 [==============>...............] - ETA: 0s-1087.3719482421875 wasserstein_loss: 0.0001220703125 plot generated_image epoch 169 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.16277837753296 32/64 [==============>...............] - ETA: 0s247903.296875 32/64 [==============>...............] - ETA: 0s-247903.2890625 wasserstein_loss: 0.0078125 plot generated_image epoch 170 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.1348729133606 32/64 [==============>...............] - ETA: 0s2592202.5 32/64 [==============>...............] - ETA: 0s-2592202.25 wasserstein_loss: 0.25 plot generated_image epoch 171 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.13363814353943 32/64 [==============>...............] - ETA: 0s-67282.98828125 32/64 [==============>...............] - ETA: 0s67283.00390625 wasserstein_loss: 0.015625 plot generated_image epoch 172 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.18478965759277 32/64 [==============>...............] - ETA: 0s-98865.91015625 32/64 [==============>...............] - ETA: 0s98865.8984375 wasserstein_loss: -0.01171875 plot generated_image epoch 173 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.2745177745819 32/64 [==============>...............] - ETA: 0s2428343.375 32/64 [==============>...............] - ETA: 0s-2428343.375 wasserstein_loss: 0.0 plot generated_image epoch 174 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.07663488388062 32/64 [==============>...............] - ETA: 0s4099.4478759765625 32/64 [==============>...............] - ETA: 0s-4099.447265625 wasserstein_loss: 0.0006103515625 plot generated_image epoch 175 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 139.95160675048828 32/64 [==============>...............] - ETA: 0s-5380.99462890625 32/64 [==============>...............] - ETA: 0s5380.99462890625 wasserstein_loss: 0.0 plot generated_image epoch 176 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.24401092529297 32/64 [==============>...............] - ETA: 0s123943.6796875 32/64 [==============>...............] - ETA: 0s-123943.6328125 wasserstein_loss: 0.046875 plot generated_image epoch 177 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.38559007644653 32/64 [==============>...............] - ETA: 0s8191186.0 32/64 [==============>...............] - ETA: 0s-8191185.75 wasserstein_loss: 0.25 plot generated_image epoch 178 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.25012755393982 32/64 [==============>...............] - ETA: 0s179649.09375 32/64 [==============>...............] - ETA: 0s-179649.0703125 wasserstein_loss: 0.0234375 plot generated_image epoch 179 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.04164242744446 32/64 [==============>...............] - ETA: 0s-88463.76953125 32/64 [==============>...............] - ETA: 0s88463.78515625 wasserstein_loss: 0.015625 plot generated_image epoch 180 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.20641684532166 32/64 [==============>...............] - ETA: 0s548428.0625 32/64 [==============>...............] - ETA: 0s-548428.109375 wasserstein_loss: -0.046875 plot generated_image epoch 181 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.17823314666748 32/64 [==============>...............] - ETA: 0s18817.703125 32/64 [==============>...............] - ETA: 0s-18817.7041015625 wasserstein_loss: -0.0009765625 plot generated_image epoch 182 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.2331666946411 32/64 [==============>...............] - ETA: 0s1638612.625 32/64 [==============>...............] - ETA: 0s-1638612.5625 wasserstein_loss: 0.0625 plot generated_image epoch 183 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.17245864868164 32/64 [==============>...............] - ETA: 0s-195514.2265625 32/64 [==============>...............] - ETA: 0s195514.2265625 wasserstein_loss: 0.0 plot generated_image epoch 184 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.08425736427307 32/64 [==============>...............] - ETA: 0s-20301.299560546875 32/64 [==============>...............] - ETA: 0s20301.3037109375 wasserstein_loss: 0.004150390625 plot generated_image epoch 185 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 139.97170400619507 32/64 [==============>...............] - ETA: 0s6000.267333984375 32/64 [==============>...............] - ETA: 0s-6000.26611328125 wasserstein_loss: 0.001220703125 plot generated_image epoch 186 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.44896841049194 32/64 [==============>...............] - ETA: 0s595463.28125 32/64 [==============>...............] - ETA: 0s-595463.3125 wasserstein_loss: -0.03125 plot generated_image epoch 187 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.42949533462524 32/64 [==============>...............] - ETA: 0s-4049728.625 32/64 [==============>...............] - ETA: 0s4049728.75 wasserstein_loss: 0.125 plot generated_image epoch 188 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.34088277816772 32/64 [==============>...............] - ETA: 0s19891.8056640625 32/64 [==============>...............] - ETA: 0s-19891.8076171875 wasserstein_loss: -0.001953125 plot generated_image epoch 189 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.1138153076172 32/64 [==============>...............] - ETA: 0s38543.1953125 32/64 [==============>...............] - ETA: 0s-38543.185546875 wasserstein_loss: 0.009765625 plot generated_image epoch 190 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 139.96330738067627 32/64 [==============>...............] - ETA: 0s1170394.875 32/64 [==============>...............] - ETA: 0s-1170394.5625 wasserstein_loss: 0.3125 plot generated_image epoch 191 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 139.92219066619873 32/64 [==============>...............] - ETA: 0s-17287.1953125 32/64 [==============>...............] - ETA: 0s17287.224609375 wasserstein_loss: 0.029296875 plot generated_image epoch 192 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.36749792099 32/64 [==============>...............] - ETA: 0s9200.2509765625 32/64 [==============>...............] - ETA: 0s-9200.25244140625 wasserstein_loss: -0.00146484375 plot generated_image epoch 193 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.28316068649292 32/64 [==============>...............] - ETA: 0s104511.78125 32/64 [==============>...............] - ETA: 0s-104511.7734375 wasserstein_loss: 0.0078125 plot generated_image epoch 194 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.16211676597595 32/64 [==============>...............] - ETA: 0s354283.5625 32/64 [==============>...............] - ETA: 0s-354283.609375 wasserstein_loss: -0.046875 plot generated_image epoch 195 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.21356654167175 32/64 [==============>...............] - ETA: 0s-242885.5234375 32/64 [==============>...............] - ETA: 0s242885.59375 wasserstein_loss: 0.0703125 plot generated_image epoch 196 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.15337920188904 32/64 [==============>...............] - ETA: 0s171459.3203125 32/64 [==============>...............] - ETA: 0s-171459.3515625 wasserstein_loss: -0.03125 plot generated_image epoch 197 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.5099527835846 32/64 [==============>...............] - ETA: 0s135725.23828125 32/64 [==============>...............] - ETA: 0s-135725.16796875 wasserstein_loss: 0.0703125 plot generated_image epoch 198 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.3613624572754 32/64 [==============>...............] - ETA: 0s-365018.59375 32/64 [==============>...............] - ETA: 0s365018.59375 wasserstein_loss: 0.0 plot generated_image epoch 199 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.37651562690735 32/64 [==============>...............] - ETA: 0s122017.625 32/64 [==============>...............] - ETA: 0s-122017.62890625 wasserstein_loss: -0.00390625 plot generated_image epoch 200 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.4214415550232 32/64 [==============>...............] - ETA: 0s73031.515625 32/64 [==============>...............] - ETA: 0s-73031.52734375 wasserstein_loss: -0.01171875 plot generated_image epoch 201 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.15376257896423 32/64 [==============>...............] - ETA: 0s297095.28125 32/64 [==============>...............] - ETA: 0s-297095.296875 wasserstein_loss: -0.015625 plot generated_image epoch 202 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.52474522590637 32/64 [==============>...............] - ETA: 0s-27966.412109375 32/64 [==============>...............] - ETA: 0s27966.435546875 wasserstein_loss: 0.0234375 plot generated_image epoch 203 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.61294269561768 32/64 [==============>...............] - ETA: 0s-54736.73046875 32/64 [==============>...............] - ETA: 0s54736.7265625 wasserstein_loss: -0.00390625 plot generated_image epoch 204 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.1966848373413 32/64 [==============>...............] - ETA: 0s-53158.65625 32/64 [==============>...............] - ETA: 0s53158.6484375 wasserstein_loss: -0.0078125 plot generated_image epoch 205 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.17578220367432 32/64 [==============>...............] - ETA: 0s-252425.125 32/64 [==============>...............] - ETA: 0s252425.1328125 wasserstein_loss: 0.0078125 plot generated_image epoch 206 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.53828120231628 32/64 [==============>...............] - ETA: 0s-31057.7431640625 32/64 [==============>...............] - ETA: 0s31057.7421875 wasserstein_loss: -0.0009765625 plot generated_image epoch 207 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.4165277481079 32/64 [==============>...............] - ETA: 0s1960390.375 32/64 [==============>...............] - ETA: 0s-1960390.25 wasserstein_loss: 0.125 plot generated_image epoch 208 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.39478373527527 32/64 [==============>...............] - ETA: 0s-253509.9921875 32/64 [==============>...............] - ETA: 0s253509.9609375 wasserstein_loss: -0.03125 plot generated_image epoch 209 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.38646149635315 32/64 [==============>...............] - ETA: 0s-41177.58203125 32/64 [==============>...............] - ETA: 0s41177.578125 wasserstein_loss: -0.00390625 plot generated_image epoch 210 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.30245995521545 32/64 [==============>...............] - ETA: 0s2404.2552490234375 32/64 [==============>...............] - ETA: 0s-2404.255615234375 wasserstein_loss: -0.0003662109375 plot generated_image epoch 211 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.4444739818573 32/64 [==============>...............] - ETA: 0s-4374.0313720703125 32/64 [==============>...............] - ETA: 0s4374.03125 wasserstein_loss: -0.0001220703125 plot generated_image epoch 212 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.77875900268555 32/64 [==============>...............] - ETA: 0s3145.0904541015625 32/64 [==============>...............] - ETA: 0s-3145.0904541015625 wasserstein_loss: 0.0 plot generated_image epoch 213 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.66811680793762 32/64 [==============>...............] - ETA: 0s265215.828125 32/64 [==============>...............] - ETA: 0s-265215.78125 wasserstein_loss: 0.046875 plot generated_image epoch 214 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.6588089466095 32/64 [==============>...............] - ETA: 0s33058.552734375 32/64 [==============>...............] - ETA: 0s-33058.5517578125 wasserstein_loss: 0.0009765625 plot generated_image epoch 215 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.47322416305542 32/64 [==============>...............] - ETA: 0s-356000.65625 32/64 [==============>...............] - ETA: 0s356000.65625 wasserstein_loss: 0.0 plot generated_image epoch 216 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.49773955345154 32/64 [==============>...............] - ETA: 0s216244.53125 32/64 [==============>...............] - ETA: 0s-216244.5234375 wasserstein_loss: 0.0078125 plot generated_image epoch 217 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.44935989379883 32/64 [==============>...............] - ETA: 0s25558.05078125 32/64 [==============>...............] - ETA: 0s-25558.048828125 wasserstein_loss: 0.001953125 plot generated_image epoch 218 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.6693937778473 32/64 [==============>...............] - ETA: 0s315.8489532470703 32/64 [==============>...............] - ETA: 0s-315.8489532470703 wasserstein_loss: 0.0 plot generated_image epoch 219 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.55491614341736 32/64 [==============>...............] - ETA: 0s-24407518.0 32/64 [==============>...............] - ETA: 0s24407518.0 wasserstein_loss: 0.0 plot generated_image epoch 220 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.59102845191956 32/64 [==============>...............] - ETA: 0s11752022.0 32/64 [==============>...............] - ETA: 0s-11752021.0 wasserstein_loss: 1.0 plot generated_image epoch 221 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.5240979194641 32/64 [==============>...............] - ETA: 0s32354.794921875 32/64 [==============>...............] - ETA: 0s-32354.7978515625 wasserstein_loss: -0.0029296875 plot generated_image epoch 222 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.32040071487427 32/64 [==============>...............] - ETA: 0s580056.125 32/64 [==============>...............] - ETA: 0s-580056.0 wasserstein_loss: 0.125 plot generated_image epoch 223 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.5332272052765 32/64 [==============>...............] - ETA: 0s50946.1826171875 32/64 [==============>...............] - ETA: 0s-50946.1875 wasserstein_loss: -0.0048828125 plot generated_image epoch 224 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.63098168373108 32/64 [==============>...............] - ETA: 0s35327.1162109375 32/64 [==============>...............] - ETA: 0s-35327.1103515625 wasserstein_loss: 0.005859375 plot generated_image epoch 225 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.3417465686798 32/64 [==============>...............] - ETA: 0s-7219240.0 32/64 [==============>...............] - ETA: 0s7219239.75 wasserstein_loss: -0.25 plot generated_image epoch 226 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.5146472454071 32/64 [==============>...............] - ETA: 0s-217199.6484375 32/64 [==============>...............] - ETA: 0s217199.6640625 wasserstein_loss: 0.015625 plot generated_image epoch 227 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.3384644985199 32/64 [==============>...............] - ETA: 0s-1227.5751953125 32/64 [==============>...............] - ETA: 0s1227.5765380859375 wasserstein_loss: 0.0013427734375 plot generated_image epoch 228 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.16542792320251 32/64 [==============>...............] - ETA: 0s-752817.9375 32/64 [==============>...............] - ETA: 0s752818.0625 wasserstein_loss: 0.125 plot generated_image epoch 229 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.17821788787842 32/64 [==============>...............] - ETA: 0s10370.091796875 32/64 [==============>...............] - ETA: 0s-10370.0888671875 wasserstein_loss: 0.0029296875 plot generated_image epoch 230 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.13474035263062 32/64 [==============>...............] - ETA: 0s1285029.75 32/64 [==============>...............] - ETA: 0s-1285030.25 wasserstein_loss: -0.5 plot generated_image epoch 231 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.17756295204163 32/64 [==============>...............] - ETA: 0s-16587.08984375 32/64 [==============>...............] - ETA: 0s16587.08984375 wasserstein_loss: 0.0 plot generated_image epoch 232 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.03373432159424 32/64 [==============>...............] - ETA: 0s-794630.125 32/64 [==============>...............] - ETA: 0s794630.25 wasserstein_loss: 0.125 plot generated_image epoch 233 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.1701624393463 32/64 [==============>...............] - ETA: 0s-48060.763671875 32/64 [==============>...............] - ETA: 0s48060.7578125 wasserstein_loss: -0.005859375 plot generated_image epoch 234 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.22006130218506 32/64 [==============>...............] - ETA: 0s15923.3251953125 32/64 [==============>...............] - ETA: 0s-15923.3251953125 wasserstein_loss: 0.0 plot generated_image epoch 235 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 139.9410035610199 32/64 [==============>...............] - ETA: 0s5535259.0 32/64 [==============>...............] - ETA: 0s-5535258.75 wasserstein_loss: 0.25 plot generated_image epoch 236 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 139.87699103355408 32/64 [==============>...............] - ETA: 0s-84022.69140625 32/64 [==============>...............] - ETA: 0s84022.69921875 wasserstein_loss: 0.0078125 plot generated_image epoch 237 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.15626049041748 32/64 [==============>...............] - ETA: 0s35292.34765625 32/64 [==============>...............] - ETA: 0s-35292.345703125 wasserstein_loss: 0.001953125 plot generated_image epoch 238 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 139.96535658836365 32/64 [==============>...............] - ETA: 0s2934506.5 32/64 [==============>...............] - ETA: 0s-2934504.625 wasserstein_loss: 1.875 plot generated_image epoch 239 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.37100553512573 32/64 [==============>...............] - ETA: 0s6749.932861328125 32/64 [==============>...............] - ETA: 0s-6749.93310546875 wasserstein_loss: -0.000244140625 plot generated_image epoch 240 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 139.89924550056458 32/64 [==============>...............] - ETA: 0s-368429.140625 32/64 [==============>...............] - ETA: 0s368429.203125 wasserstein_loss: 0.0625 plot generated_image epoch 241 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.16006755828857 32/64 [==============>...............] - ETA: 0s259481.84375 32/64 [==============>...............] - ETA: 0s-259481.8984375 wasserstein_loss: -0.0546875 plot generated_image epoch 242 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.03136348724365 32/64 [==============>...............] - ETA: 0s11429.71044921875 32/64 [==============>...............] - ETA: 0s-11429.70947265625 wasserstein_loss: 0.0009765625 plot generated_image epoch 243 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.13418292999268 32/64 [==============>...............] - ETA: 0s96441.06640625 32/64 [==============>...............] - ETA: 0s-96441.0625 wasserstein_loss: 0.00390625 plot generated_image epoch 244 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.2090983390808 32/64 [==============>...............] - ETA: 0s4780.6561279296875 32/64 [==============>...............] - ETA: 0s-4780.65478515625 wasserstein_loss: 0.0013427734375 plot generated_image epoch 245 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.1966676712036 32/64 [==============>...............] - ETA: 0s1926691.0 32/64 [==============>...............] - ETA: 0s-1926691.125 wasserstein_loss: -0.125 plot generated_image epoch 246 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.2466847896576 32/64 [==============>...............] - ETA: 0s-52492.28125 32/64 [==============>...............] - ETA: 0s52492.283203125 wasserstein_loss: 0.001953125 plot generated_image epoch 247 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.0598521232605 32/64 [==============>...............] - ETA: 0s7095.906005859375 32/64 [==============>...............] - ETA: 0s-7095.905029296875 wasserstein_loss: 0.0009765625 plot generated_image epoch 248 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.22690415382385 32/64 [==============>...............] - ETA: 0s-4233.4915771484375 32/64 [==============>...............] - ETA: 0s4233.4912109375 wasserstein_loss: -0.0003662109375 plot generated_image epoch 249 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.1159598827362 32/64 [==============>...............] - ETA: 0s1957649.6875 32/64 [==============>...............] - ETA: 0s-1957649.5625 wasserstein_loss: 0.125 plot generated_image epoch 250 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.4335994720459 32/64 [==============>...............] - ETA: 0s-365557.421875 32/64 [==============>...............] - ETA: 0s365557.40625 wasserstein_loss: -0.015625 plot generated_image epoch 251 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.13378047943115 32/64 [==============>...............] - ETA: 0s70536.01171875 32/64 [==============>...............] - ETA: 0s-70536.00390625 wasserstein_loss: 0.0078125 plot generated_image epoch 252 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.06038880348206 32/64 [==============>...............] - ETA: 0s765598.875 32/64 [==============>...............] - ETA: 0s-765598.96875 wasserstein_loss: -0.09375 plot generated_image epoch 253 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.0494692325592 32/64 [==============>...............] - ETA: 0s50056.62890625 32/64 [==============>...............] - ETA: 0s-50056.626953125 wasserstein_loss: 0.001953125 plot generated_image epoch 254 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.11598300933838 32/64 [==============>...............] - ETA: 0s76757.9140625 32/64 [==============>...............] - ETA: 0s-76757.921875 wasserstein_loss: -0.0078125 plot generated_image epoch 255 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.19652843475342 32/64 [==============>...............] - ETA: 0s2025092.0 32/64 [==============>...............] - ETA: 0s-2025092.125 wasserstein_loss: -0.125 plot generated_image epoch 256 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.05908513069153 32/64 [==============>...............] - ETA: 0s124960.203125 32/64 [==============>...............] - ETA: 0s-124960.20703125 wasserstein_loss: -0.00390625 plot generated_image epoch 257 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.26385855674744 32/64 [==============>...............] - ETA: 0s93832.88671875 32/64 [==============>...............] - ETA: 0s-93832.890625 wasserstein_loss: -0.00390625 plot generated_image epoch 258 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 139.85965728759766 32/64 [==============>...............] - ETA: 0s-5954084.25 32/64 [==============>...............] - ETA: 0s5954084.0 wasserstein_loss: -0.25 plot generated_image epoch 259 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 139.94051957130432 32/64 [==============>...............] - ETA: 0s-106032.515625 32/64 [==============>...............] - ETA: 0s106032.5 wasserstein_loss: -0.015625 plot generated_image epoch 260 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.62405848503113 32/64 [==============>...............] - ETA: 0s3226287.625 32/64 [==============>...............] - ETA: 0s-3226287.0 wasserstein_loss: 0.625 plot generated_image epoch 261 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.20928740501404 32/64 [==============>...............] - ETA: 0s-512019.96875 32/64 [==============>...............] - ETA: 0s512019.9375 wasserstein_loss: -0.03125 plot generated_image epoch 262 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 139.9331169128418 32/64 [==============>...............] - ETA: 0s54342.0478515625 32/64 [==============>...............] - ETA: 0s-54342.0458984375 wasserstein_loss: 0.001953125 plot generated_image epoch 263 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.32653427124023 32/64 [==============>...............] - ETA: 0s-22247.8359375 32/64 [==============>...............] - ETA: 0s22247.8408203125 wasserstein_loss: 0.0048828125 plot generated_image epoch 264 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.31312322616577 32/64 [==============>...............] - ETA: 0s201075.8359375 32/64 [==============>...............] - ETA: 0s-201075.828125 wasserstein_loss: 0.0078125 plot generated_image epoch 265 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.3847496509552 32/64 [==============>...............] - ETA: 0s109466.96875 32/64 [==============>...............] - ETA: 0s-109466.96484375 wasserstein_loss: 0.00390625 plot generated_image epoch 266 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.1712543964386 32/64 [==============>...............] - ETA: 0s98684.8984375 32/64 [==============>...............] - ETA: 0s-98684.91015625 wasserstein_loss: -0.01171875 plot generated_image epoch 267 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.4696593284607 32/64 [==============>...............] - ETA: 0s37528.494140625 32/64 [==============>...............] - ETA: 0s-37528.49609375 wasserstein_loss: -0.001953125 plot generated_image epoch 268 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.50038814544678 32/64 [==============>...............] - ETA: 0s-205319.1796875 32/64 [==============>...............] - ETA: 0s205319.1640625 wasserstein_loss: -0.015625 plot generated_image epoch 269 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.24025225639343 32/64 [==============>...............] - ETA: 0s363242.234375 32/64 [==============>...............] - ETA: 0s-363242.1875 wasserstein_loss: 0.046875 plot generated_image epoch 270 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.3301866054535 32/64 [==============>...............] - ETA: 0s-3758684.75 32/64 [==============>...............] - ETA: 0s3758684.0 wasserstein_loss: -0.75 plot generated_image epoch 271 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.35215020179749 32/64 [==============>...............] - ETA: 0s-5656870.75 32/64 [==============>...............] - ETA: 0s5656872.0 wasserstein_loss: 1.25 plot generated_image epoch 272 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.17522382736206 32/64 [==============>...............] - ETA: 0s-194992.875 32/64 [==============>...............] - ETA: 0s194992.8828125 wasserstein_loss: 0.0078125 plot generated_image epoch 273 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.40031456947327 32/64 [==============>...............] - ETA: 0s172865.4375 32/64 [==============>...............] - ETA: 0s-172865.40625 wasserstein_loss: 0.03125 plot generated_image epoch 274 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.44141483306885 32/64 [==============>...............] - ETA: 0s88919.7109375 32/64 [==============>...............] - ETA: 0s-88919.71484375 wasserstein_loss: -0.00390625 plot generated_image epoch 275 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.28384351730347 32/64 [==============>...............] - ETA: 0s4407393.25 32/64 [==============>...............] - ETA: 0s-4407392.875 wasserstein_loss: 0.375 plot generated_image epoch 276 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.4914481639862 32/64 [==============>...............] - ETA: 0s457488.375 32/64 [==============>...............] - ETA: 0s-457488.40625 wasserstein_loss: -0.03125 plot generated_image epoch 277 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.4501600265503 32/64 [==============>...............] - ETA: 0s-35653.96875 32/64 [==============>...............] - ETA: 0s35653.958984375 wasserstein_loss: -0.009765625 plot generated_image epoch 278 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.39008045196533 32/64 [==============>...............] - ETA: 0s4147.4617919921875 32/64 [==============>...............] - ETA: 0s-4147.4683837890625 wasserstein_loss: -0.006591796875 plot generated_image epoch 279 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.17290210723877 32/64 [==============>...............] - ETA: 0s1056723.0 32/64 [==============>...............] - ETA: 0s-1056723.1875 wasserstein_loss: -0.1875 plot generated_image epoch 280 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.37723875045776 32/64 [==============>...............] - ETA: 0s5601942.0 32/64 [==============>...............] - ETA: 0s-5601941.75 wasserstein_loss: 0.25 plot generated_image epoch 281 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.57939076423645 32/64 [==============>...............] - ETA: 0s7120688.5 32/64 [==============>...............] - ETA: 0s-7120687.75 wasserstein_loss: 0.75 plot generated_image epoch 282 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 139.83891201019287 32/64 [==============>...............] - ETA: 0s77170.97265625 32/64 [==============>...............] - ETA: 0s-77170.99609375 wasserstein_loss: -0.0234375 plot generated_image epoch 283 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.17716217041016 32/64 [==============>...............] - ETA: 0s15635.5048828125 32/64 [==============>...............] - ETA: 0s-15635.50439453125 wasserstein_loss: 0.00048828125 plot generated_image epoch 284 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 139.93994283676147 32/64 [==============>...............] - ETA: 0s-134296.359375 32/64 [==============>...............] - ETA: 0s134296.3515625 wasserstein_loss: -0.0078125 plot generated_image epoch 285 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.14635181427002 32/64 [==============>...............] - ETA: 0s-145115.921875 32/64 [==============>...............] - ETA: 0s145115.90625 wasserstein_loss: -0.015625 plot generated_image epoch 286 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.25439071655273 32/64 [==============>...............] - ETA: 0s-9286542.5 32/64 [==============>...............] - ETA: 0s9286545.0 wasserstein_loss: 2.5 plot generated_image epoch 287 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.1350383758545 32/64 [==============>...............] - ETA: 0s-90459.57421875 32/64 [==============>...............] - ETA: 0s90459.5703125 wasserstein_loss: -0.00390625 plot generated_image epoch 288 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.05842423439026 32/64 [==============>...............] - ETA: 0s-232904.4375 32/64 [==============>...............] - ETA: 0s232904.4765625 wasserstein_loss: 0.0390625 plot generated_image epoch 289 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 139.9763948917389 32/64 [==============>...............] - ETA: 0s-237077.5859375 32/64 [==============>...............] - ETA: 0s237077.6171875 wasserstein_loss: 0.03125 plot generated_image epoch 290 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 139.76170110702515 32/64 [==============>...............] - ETA: 0s17711.373046875 32/64 [==============>...............] - ETA: 0s-17711.3740234375 wasserstein_loss: -0.0009765625 plot generated_image epoch 291 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.20232892036438 32/64 [==============>...............] - ETA: 0s-895604.8125 32/64 [==============>...............] - ETA: 0s895604.75 wasserstein_loss: -0.0625 plot generated_image epoch 292 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.14176082611084 32/64 [==============>...............] - ETA: 0s-1164845.875 32/64 [==============>...............] - ETA: 0s1164845.875 wasserstein_loss: 0.0 plot generated_image epoch 293 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 139.83081221580505 32/64 [==============>...............] - ETA: 0s410229.0 32/64 [==============>...............] - ETA: 0s-410229.015625 wasserstein_loss: -0.015625 plot generated_image epoch 294 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.15480732917786 32/64 [==============>...............] - ETA: 0s4403.84521484375 32/64 [==============>...............] - ETA: 0s-4403.8406982421875 wasserstein_loss: 0.0045166015625 plot generated_image epoch 295 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 139.82702708244324 32/64 [==============>...............] - ETA: 0s-89753.482421875 32/64 [==============>...............] - ETA: 0s89753.458984375 wasserstein_loss: -0.0234375 plot generated_image epoch 296 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 139.90143704414368 32/64 [==============>...............] - ETA: 0s4037340.5 32/64 [==============>...............] - ETA: 0s-4037341.25 wasserstein_loss: -0.75 plot generated_image epoch 297 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 139.95788717269897 32/64 [==============>...............] - ETA: 0s15520.8916015625 32/64 [==============>...............] - ETA: 0s-15520.89208984375 wasserstein_loss: -0.00048828125 plot generated_image epoch 298 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 139.72371673583984 32/64 [==============>...............] - ETA: 0s26861.962890625 32/64 [==============>...............] - ETA: 0s-26861.96484375 wasserstein_loss: -0.001953125 plot generated_image epoch 299 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.14342141151428 32/64 [==============>...............] - ETA: 0s35371.5 32/64 [==============>...............] - ETA: 0s-35371.50390625 wasserstein_loss: -0.00390625 plot generated_image epoch 300 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.0716691017151 32/64 [==============>...............] - ETA: 0s-389268.0859375 32/64 [==============>...............] - ETA: 0s389268.1796875 wasserstein_loss: 0.09375 plot generated_image epoch 301 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 139.8188557624817 32/64 [==============>...............] - ETA: 0s1082473.15625 32/64 [==============>...............] - ETA: 0s-1082473.1875 wasserstein_loss: -0.03125 plot generated_image epoch 302 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 140.12926054000854 32/64 [==============>...............] - ETA: 0s118977.69921875 32/64 [==============>...............] - ETA: 0s-118977.6796875 wasserstein_loss: 0.01953125 plot generated_image epoch 303 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 139.9989321231842 32/64 [==============>...............] - ETA: 0s122950.98046875 32/64 [==============>...............] - ETA: 0s-122950.9765625 wasserstein_loss: 0.00390625 plot generated_image epoch 304 of 500 number of batches: 937 936/937 [============================>.] - ETA: 0s epoch time: 139.90365266799927 32/64 [==============>...............] - ETA: 0s240191.03125 32/64 [==============>...............] - ETA: 0s-240191.015625 wasserstein_loss: 0.015625 plot generated_image epoch 305 of 500 number of batches: 937 78/937 [=>............................] - ETA: 127s
--------------------------------------------------------------------------- KeyboardInterrupt Traceback (most recent call last) <ipython-input-19-9c2c40cad8e3> in <module>() 28 discriminator.trainable = False 29 generator.trainable = True ---> 30 generator_loss.append(model_for_training_generator.train_on_batch(np.random.randn(BATCHSIZE, 128), real_y)) 31 32 print('\nepoch time: {}'.format(time()-start_time)) /home/mathlab115/anaconda3/lib/python3.6/site-packages/keras/engine/training.py in train_on_batch(self, x, y, sample_weight, class_weight) 1760 ins = x + y + sample_weights 1761 self._make_train_function() -> 1762 outputs = self.train_function(ins) 1763 if len(outputs) == 1: 1764 return outputs[0] /home/mathlab115/anaconda3/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py in __call__(self, inputs) 2271 updated = session.run(self.outputs + [self.updates_op], 2272 feed_dict=feed_dict, -> 2273 **self.session_kwargs) 2274 return updated[:len(self.outputs)] 2275 /home/mathlab115/anaconda3/lib/python3.6/site-packages/tensorflow/python/client/session.py in run(self, fetches, feed_dict, options, run_metadata) 776 try: 777 result = self._run(None, fetches, feed_dict, options_ptr, --> 778 run_metadata_ptr) 779 if run_metadata: 780 proto_data = tf_session.TF_GetBuffer(run_metadata_ptr) /home/mathlab115/anaconda3/lib/python3.6/site-packages/tensorflow/python/client/session.py in _run(self, handle, fetches, feed_dict, options, run_metadata) 980 if final_fetches or final_targets: 981 results = self._do_run(handle, final_targets, final_fetches, --> 982 feed_dict_string, options, run_metadata) 983 else: 984 results = [] /home/mathlab115/anaconda3/lib/python3.6/site-packages/tensorflow/python/client/session.py in _do_run(self, handle, target_list, fetch_list, feed_dict, options, run_metadata) 1030 if handle is None: 1031 return self._do_call(_run_fn, self._session, feed_dict, fetch_list, -> 1032 target_list, options, run_metadata) 1033 else: 1034 return self._do_call(_prun_fn, self._session, handle, feed_dict, /home/mathlab115/anaconda3/lib/python3.6/site-packages/tensorflow/python/client/session.py in _do_call(self, fn, *args) 1037 def _do_call(self, fn, *args): 1038 try: -> 1039 return fn(*args) 1040 except errors.OpError as e: 1041 message = compat.as_text(e.message) /home/mathlab115/anaconda3/lib/python3.6/site-packages/tensorflow/python/client/session.py in _run_fn(session, feed_dict, fetch_list, target_list, options, run_metadata) 1019 return tf_session.TF_Run(session, options, 1020 feed_dict, fetch_list, target_list, -> 1021 status, run_metadata) 1022 1023 def _prun_fn(session, handle, feed_dict, fetch_list): KeyboardInterrupt:
plt.plot(W_loss)
[<matplotlib.lines.Line2D at 0x7f668a461ef0>]
plt.imshow(old)
<matplotlib.image.AxesImage at 0x7f668a19a550>