3章 変分オートエンコーダ

Diederik P. Kingma, Max Welling が変分オートエンコーダ (variational autoencoder: VAE) の論文(https://arxiv.org/abs/1312.6114 2013)を発表した。

3.1 展覧会 (p.69)

数字(0, 1, ..., 9)のモノクロ画像と2次元座標の間のマップ(写像)を扱う。

3.2 オートエンコーダ (p.72)

  • エンコーダネットワークは、高次元の入力データをより低次元の表現ベクトルに圧縮する。
  • デコーダネットワークは、与えられた表現ベクトルを元の領域に復元する。

3.2.1 最初のオートエンコーダ (p.74)

本のソースコードにある 03_01_autoencoder_train.ipynb にしたがってオートエンコーダを作る。 ただし、この ipynb はソースコード中の utils, modelsフォルダの下の python ファイルを使っている。この ipynb 中では、それらも理解するために、このipynb中に書き下して実行する。

3.2.2 エンコーダ

入力画像を潜在空間のある1点に写像する。 画像の入力層を4つのConv2D層に渡して、それぞれ高レベルの特徴を抽出する。出力サイズを減らすために stride を 2 とする。 最後の畳み込み層で平坦化 Flatten して、サイズ 2 の完全結合層 Dense 層に入れる。これにより潜在空間は 2 次元となる。

3.2.3 デコーダ

転置畳み込み層を使ってデコーダを構成する。転置畳み込み層を何層か重ねることでサイズを拡張できる。 デコーダはエンコーダと対照である必要はなく、デコーダの最後の層からの出力がエンコーダの入力と同じサイズであればよい。

3.2.4 エンコーダとデコーダを連結する

エンコーダとデコーダを同時に訓練するために、エンコーダを通った画像がデコーダを通って戻ってくるモデルを構成する。 損失関数を、元の画像と復元画像の各ピクセルの平均2乗誤差 (Root Mean Squared Error, RMSE)として定義する。 損失関数は binary_crossentropy でも大丈夫だが、おとなしい学習結果となりがちだそうだ。

ライブラリ

In [1]:
# DGL_code/utils/loaders.py
from tensorflow.keras.datasets import mnist

def load_mnist():
    (x_train, y_train), (x_test, y_test) = mnist.load_data()
    x_train = x_train.astype('float32') / 255.0
    x_train = x_train.reshape(x_train.shape + (1,))
    x_test = x_test.astype('float32') / 255.0
    x_test = x_test.reshape(x_test.shape + (1,))
    return (x_train, y_train), (x_test, y_test)
In [2]:
# DGL_code/models/AE.py
# [自分へのメモ] Autoencoder クラスの中の plot_mode() 関数で、フォルダを作成するコードを追加した。

from tensorflow.keras.layers import Input, Conv2D, LeakyReLU, BatchNormalization, Dropout, Flatten, Dense, Reshape, Conv2DTranspose, Activation
from tensorflow.keras import backend as K
from tensorflow.keras.models import Model
from tensorflow.keras.optimizers import Adam
from tensorflow.keras.utils import plot_model
from tensorflow.keras.callbacks import ModelCheckpoint

import os
import pickle


class Autoencoder():
    def __init__(self, 
                input_dim,
                encoder_conv_filters,
                encoder_conv_kernel_size,
                encoder_conv_strides,
                decoder_conv_t_filters,
                decoder_conv_t_kernel_size,
                decoder_conv_t_strides,
                z_dim,
                use_batch_norm = False,
                use_dropout = False
                ):
            self.name = 'autoencoder'
            self.input_dim = input_dim
            self.encoder_conv_filters = encoder_conv_filters
            self.encoder_conv_kernel_size = encoder_conv_kernel_size
            self.encoder_conv_strides = encoder_conv_strides
            self.decoder_conv_t_filters = decoder_conv_t_filters
            self.decoder_conv_t_kernel_size = decoder_conv_t_kernel_size
            self.decoder_conv_t_strides = decoder_conv_t_strides
            self.z_dim = z_dim
            
            self.use_batch_norm = use_batch_norm
            self.use_dropout = use_dropout
            
            self.n_layers_encoder = len(encoder_conv_filters)
            self.n_layers_decoder = len(decoder_conv_t_filters)
            
            self._build()
 

    def _build(self):
        ### THE ENCODER
        encoder_input = Input(shape=self.input_dim, name='encoder_input')
        x = encoder_input
        
        for i in range(self.n_layers_encoder):
            conv_layer =Conv2D(
                filters = self.encoder_conv_filters[i],
                kernel_size = self.encoder_conv_kernel_size[i],
                strides = self.encoder_conv_strides[i],
                padding  = 'same',
                name = 'encoder_conv_' + str(i)
            )
            x = conv_layer(x)
            x = LeakyReLU()(x)
            if self.use_batch_norm:
                x = BatchNormalization()(x)
            if self.use_dropout:
                x = Dropout(rate = 0.25)(x)
        
        shape_before_flattening = K.int_shape(x)[1:]
        
        x = Flatten()(x)
        encoder_output = Dense(self.z_dim, name='encoder_output')(x)
        
        self.encoder = Model(encoder_input, encoder_output)
        
        ### THE DECODER
        decoder_input = Input(shape=(self.z_dim,), name='decoder_input')
        x = Dense(np.prod(shape_before_flattening))(decoder_input)
        x = Reshape(shape_before_flattening)(x)
        
        for i in range(self.n_layers_decoder):
            conv_t_layer =   Conv2DTranspose(
                filters = self.decoder_conv_t_filters[i],
                kernel_size = self.decoder_conv_t_kernel_size[i],
                strides = self.decoder_conv_t_strides[i],
                padding = 'same',
                name = 'decoder_conv_t_' + str(i)
            )
            x = conv_t_layer(x)
            
            if i < self.n_layers_decoder - 1:
                x = LeakyReLU()(x)
                if self.use_batch_norm:
                    x = BatchNormalization()(x)
                if self.use_dropout:
                    x = Dropout(rate=0.25)(x)
            else:
                x = Activation('sigmoid')(x)
       
        decoder_output = x
        self.decoder = Model(decoder_input, decoder_output)
        
        ### THE FULL AUTOENCODER
        model_input = encoder_input
        model_output = self.decoder(encoder_output)
        
        self.model = Model(model_input, model_output)

        
    def compile(self, learning_rate):
        self.learning_rate = learning_rate
        optimizer = Adam(lr=learning_rate)
        def r_loss(y_true, y_pred):
            return K.mean(K.square(y_true - y_pred), axis = [1,2,3])
        self.model.compile(optimizer=optimizer, loss = r_loss)
        
        
    def save(self, folder):
        if not os.path.exists(folder):
            os.makedirs(folder)
            os.makedirs(os.path.join(folder, 'viz'))
            os.makedirs(os.path.join(folder, 'weights'))
            os.makedirs(os.path.join(folder, 'images'))
            
        with open(os.path.join(folder, 'params.pkl'), 'wb') as f:
            pickle.dump([
                self.input_dim,
                self.encoder_conv_filters,
                self.encoder_conv_kernel_size,
                self.encoder_conv_strides,
                self.decoder_conv_t_filters,
                self.decoder_conv_t_kernel_size,
                self.decoder_conv_t_strides,
                self.z_dim,
                self.use_batch_norm,
                self.use_dropout
            ], f)
            
        self.plot_model(folder)
        
        
    def plot_model(self, run_folder):
        ### start of section added by nitta
        path = os.path.join(run_folder, 'viz')
        if not os.path.exists(path):
            os.makedirs(path)
        ### end of section added by nitta
        plot_model(self.model, to_file=os.path.join(run_folder, 'viz/model.png'), show_shapes=True, show_layer_names=True)
        plot_model(self.encoder, to_file=os.path.join(run_folder, 'viz/encoder.png'), show_shapes=True, show_layer_names=True)
        plot_model(self.decoder, to_file=os.path.join(run_folder, 'viz/decoder.png'), show_shapes=True, show_layer_names=True)

        
    def load_weights(self, filepath):
        self.model.load_weights(filepath)
        
        
    def train(self, x_train, batch_size, epochs, run_folder, print_every_n_batches=100, initial_epoch=0, lr_decay=1):
        custom_callback = CustomCallback(run_folder, print_every_n_batches, initial_epoch, self)
        lr_sched = step_decay_schedule(initial_lr=self.learning_rate, decay_factor=lr_decay, step_size=1)
        checkpoint2 = ModelCheckpoint(os.path.join(run_folder, 'weights/weights.h5'), save_weights_only=True, verbose=1)
        callbacks_list = [checkpoint2, custom_callback, lr_sched]
        self.model.fit(
            x_train,
            x_train,
            batch_size = batch_size,
            shuffle = True,
            epochs = epochs,
            initial_epoch = initial_epoch,
            callbacks = callbacks_list)
In [3]:
# GDL_code/utils/callbacks.py

import os
import numpy as np
import matplotlib.pyplot as plt
from tensorflow.keras.callbacks import Callback, LearningRateScheduler

class CustomCallback(Callback):
    def __init__(self, run_folder, print_every_n_batches, initial_epoch, vae):
        self.run_folder = run_folder
        self.print_every_n_batches = print_every_n_batches
        self.epoch = initial_epoch
        self.vae = vae
        
        
    def on_train_batch_end(self, batch, logs={}):
        if batch % self.print_every_n_batches == 0:
            z_new = np.random.normal(size=(1,self.vae.z_dim))
            reconst = self.vae.decoder.predict(np.array(z_new))[0].squeeze()
            
            filepath = os.path.join(self.run_folder, 'images', 'img_'+str(self.epoch).zfill(3)+'_'+str(batch)+'.jpg')
            if len(reconst.shape) == 2:
                plt.imsave(filepath, reconst, cmap='gray_r')
            else:
                plt.imsave(filepath, reconst)
        
        
    def on_epoch_begin(self, epoch, logs={}):
        self.epoch += 1
        
        
def step_decay_schedule(initial_lr, decay_factor=0.5, step_size=1):
    '''
    Wrapper function to create a LearningRateScheduler with step decay schedule.
    '''
    def schedule(epoch):
        new_lr = initial_lr * (decay_factor ** np.floor(epoch/step_size))
        return new_lr
    return LearningRateScheduler(schedule)

パラメータの設定

In [4]:
# run params
# [自分へのメモ] os.mkdir() 関数はpathの途中のフォルダが存在しないとエラーとなるので os.makedirs() 関数に変更した。

SECTION = 'vae'
RUN_ID = '0001'
DATA_NAME = 'digits'
RUN_FOLDER = 'run/{}/'.format(SECTION)
RUN_FOLDER += '_'.join([RUN_ID, DATA_NAME])

if not os.path.exists(RUN_FOLDER):
    os.makedirs(RUN_FOLDER)                                            # os.mkdir() よりも os.makedirs() の方が深い階層まで再帰的に作成できて便利
    os.makedirs(os.path.join(RUN_FOLDER, 'viz'))
    os.makedirs(os.path.join(RUN_FOLDER, 'images'))
    os.makedirs(os.path.join(RUN_FOLDER, 'weights'))
    
MODE = 'build' #'load'

データのロード

In [5]:
(x_train, y_train), (x_test, y_test) = load_mnist()
In [6]:
print(x_train.shape)
(60000, 28, 28, 1)

ニューラルネットワークの作成

In [7]:
import os

AE = Autoencoder(
    input_dim = (28, 28, 1),
    encoder_conv_filters = [32, 64, 64, 64],
    encoder_conv_kernel_size = [3, 3, 3, 3],
    encoder_conv_strides = [1, 2, 2, 1],
    decoder_conv_t_filters = [64, 64, 32, 1],
    decoder_conv_t_kernel_size = [3, 3, 3, 3],
    decoder_conv_t_strides = [1, 2, 2, 1],
    z_dim = 2
)

if MODE == 'build':
    AE.save(RUN_FOLDER)
else:
    AE.load_weights(os.path.join(RUN_FOLDER, 'weights/weights.h5'))

run/vae/0001_digits/viz/encoder.png




run/vae/0001_digits/viz/decoder.png




run/vae/0001_digits/viz/model.png




In [8]:
AE.encoder.summary()
Model: "model"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
encoder_input (InputLayer)   [(None, 28, 28, 1)]       0         
_________________________________________________________________
encoder_conv_0 (Conv2D)      (None, 28, 28, 32)        320       
_________________________________________________________________
leaky_re_lu (LeakyReLU)      (None, 28, 28, 32)        0         
_________________________________________________________________
encoder_conv_1 (Conv2D)      (None, 14, 14, 64)        18496     
_________________________________________________________________
leaky_re_lu_1 (LeakyReLU)    (None, 14, 14, 64)        0         
_________________________________________________________________
encoder_conv_2 (Conv2D)      (None, 7, 7, 64)          36928     
_________________________________________________________________
leaky_re_lu_2 (LeakyReLU)    (None, 7, 7, 64)          0         
_________________________________________________________________
encoder_conv_3 (Conv2D)      (None, 7, 7, 64)          36928     
_________________________________________________________________
leaky_re_lu_3 (LeakyReLU)    (None, 7, 7, 64)          0         
_________________________________________________________________
flatten (Flatten)            (None, 3136)              0         
_________________________________________________________________
encoder_output (Dense)       (None, 2)                 6274      
=================================================================
Total params: 98,946
Trainable params: 98,946
Non-trainable params: 0
_________________________________________________________________
In [9]:
AE.decoder.summary()
Model: "model_1"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
decoder_input (InputLayer)   [(None, 2)]               0         
_________________________________________________________________
dense (Dense)                (None, 3136)              9408      
_________________________________________________________________
reshape (Reshape)            (None, 7, 7, 64)          0         
_________________________________________________________________
decoder_conv_t_0 (Conv2DTran (None, 7, 7, 64)          36928     
_________________________________________________________________
leaky_re_lu_4 (LeakyReLU)    (None, 7, 7, 64)          0         
_________________________________________________________________
decoder_conv_t_1 (Conv2DTran (None, 14, 14, 64)        36928     
_________________________________________________________________
leaky_re_lu_5 (LeakyReLU)    (None, 14, 14, 64)        0         
_________________________________________________________________
decoder_conv_t_2 (Conv2DTran (None, 28, 28, 32)        18464     
_________________________________________________________________
leaky_re_lu_6 (LeakyReLU)    (None, 28, 28, 32)        0         
_________________________________________________________________
decoder_conv_t_3 (Conv2DTran (None, 28, 28, 1)         289       
_________________________________________________________________
activation (Activation)      (None, 28, 28, 1)         0         
=================================================================
Total params: 102,017
Trainable params: 102,017
Non-trainable params: 0
_________________________________________________________________
In [10]:
AE.model.summary()
Model: "model_2"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
encoder_input (InputLayer)   [(None, 28, 28, 1)]       0         
_________________________________________________________________
encoder_conv_0 (Conv2D)      (None, 28, 28, 32)        320       
_________________________________________________________________
leaky_re_lu (LeakyReLU)      (None, 28, 28, 32)        0         
_________________________________________________________________
encoder_conv_1 (Conv2D)      (None, 14, 14, 64)        18496     
_________________________________________________________________
leaky_re_lu_1 (LeakyReLU)    (None, 14, 14, 64)        0         
_________________________________________________________________
encoder_conv_2 (Conv2D)      (None, 7, 7, 64)          36928     
_________________________________________________________________
leaky_re_lu_2 (LeakyReLU)    (None, 7, 7, 64)          0         
_________________________________________________________________
encoder_conv_3 (Conv2D)      (None, 7, 7, 64)          36928     
_________________________________________________________________
leaky_re_lu_3 (LeakyReLU)    (None, 7, 7, 64)          0         
_________________________________________________________________
flatten (Flatten)            (None, 3136)              0         
_________________________________________________________________
encoder_output (Dense)       (None, 2)                 6274      
_________________________________________________________________
model_1 (Model)              (None, 28, 28, 1)         102017    
=================================================================
Total params: 200,963
Trainable params: 200,963
Non-trainable params: 0
_________________________________________________________________

autoencoder を訓練する

In [11]:
LEARNING_RATE = 0.0005
BATCH_SIZE = 32
INITIAL_EPOCH = 0
In [12]:
AE.compile(LEARNING_RATE)
In [13]:
AE.train(
    x_train[:1000],
    batch_size = BATCH_SIZE,
    epochs = 200,
    run_folder = RUN_FOLDER,
    initial_epoch = INITIAL_EPOCH
)
Epoch 1/200
 1/32 [..............................] - ETA: 0s - loss: 0.2308WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.351681). Check your callbacks.
32/32 [==============================] - ETA: 0s - loss: 0.1976
Epoch 00001: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 1s 26ms/step - loss: 0.1976 - lr: 5.0000e-04
Epoch 2/200
 1/32 [..............................] - ETA: 0s - loss: 0.0996WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.162947). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0913
Epoch 00002: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 14ms/step - loss: 0.0911 - lr: 5.0000e-04
Epoch 3/200
 1/32 [..............................] - ETA: 0s - loss: 0.0737WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.140250). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0688
Epoch 00003: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0687 - lr: 5.0000e-04
Epoch 4/200
 1/32 [..............................] - ETA: 0s - loss: 0.0670WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.235288). Check your callbacks.
WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.117644). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0608
Epoch 00004: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 13ms/step - loss: 0.0607 - lr: 5.0000e-04
Epoch 5/200
 1/32 [..............................] - ETA: 0s - loss: 0.0560WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.139814). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0569
Epoch 00005: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0570 - lr: 5.0000e-04
Epoch 6/200
 1/32 [..............................] - ETA: 0s - loss: 0.0593WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.254095). Check your callbacks.
WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.127047). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0558
Epoch 00006: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 14ms/step - loss: 0.0558 - lr: 5.0000e-04
Epoch 7/200
 1/32 [..............................] - ETA: 0s - loss: 0.0575WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.131309). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0548
Epoch 00007: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 14ms/step - loss: 0.0548 - lr: 5.0000e-04
Epoch 8/200
 1/32 [..............................] - ETA: 0s - loss: 0.0570WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.127173). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0539
Epoch 00008: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 14ms/step - loss: 0.0539 - lr: 5.0000e-04
Epoch 9/200
 1/32 [..............................] - ETA: 0s - loss: 0.0509WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.185971). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0531
Epoch 00009: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 14ms/step - loss: 0.0532 - lr: 5.0000e-04
Epoch 10/200
 1/32 [..............................] - ETA: 0s - loss: 0.0494WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.158487). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0526
Epoch 00010: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0527 - lr: 5.0000e-04
Epoch 11/200
 1/32 [..............................] - ETA: 0s - loss: 0.0506WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.154163). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0521
Epoch 00011: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 13ms/step - loss: 0.0522 - lr: 5.0000e-04
Epoch 12/200
 1/32 [..............................] - ETA: 0s - loss: 0.0555WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.185749). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0518
Epoch 00012: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 13ms/step - loss: 0.0517 - lr: 5.0000e-04
Epoch 13/200
 1/32 [..............................] - ETA: 0s - loss: 0.0538WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.181462). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0513
Epoch 00013: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0513 - lr: 5.0000e-04
Epoch 14/200
 1/32 [..............................] - ETA: 0s - loss: 0.0540WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.133945). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0510
Epoch 00014: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0509 - lr: 5.0000e-04
Epoch 15/200
 1/32 [..............................] - ETA: 0s - loss: 0.0550WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.153093). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0506
Epoch 00015: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0506 - lr: 5.0000e-04
Epoch 16/200
 1/32 [..............................] - ETA: 0s - loss: 0.0496WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.178599). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0502
Epoch 00016: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0502 - lr: 5.0000e-04
Epoch 17/200
 1/32 [..............................] - ETA: 0s - loss: 0.0478WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.178946). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0499
Epoch 00017: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0498 - lr: 5.0000e-04
Epoch 18/200
 1/32 [..............................] - ETA: 0s - loss: 0.0467WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.203085). Check your callbacks.
WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.101543). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0495
Epoch 00018: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 13ms/step - loss: 0.0496 - lr: 5.0000e-04
Epoch 19/200
 1/32 [..............................] - ETA: 0s - loss: 0.0497WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.220675). Check your callbacks.
WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.110337). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0492
Epoch 00019: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 13ms/step - loss: 0.0493 - lr: 5.0000e-04
Epoch 20/200
 1/32 [..............................] - ETA: 0s - loss: 0.0515WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.165447). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0489
Epoch 00020: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 14ms/step - loss: 0.0489 - lr: 5.0000e-04
Epoch 21/200
 1/32 [..............................] - ETA: 0s - loss: 0.0470WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.145810). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0487
Epoch 00021: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 14ms/step - loss: 0.0487 - lr: 5.0000e-04
Epoch 22/200
 1/32 [..............................] - ETA: 0s - loss: 0.0459WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.167757). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0485
Epoch 00022: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 14ms/step - loss: 0.0485 - lr: 5.0000e-04
Epoch 23/200
 1/32 [..............................] - ETA: 0s - loss: 0.0447WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.127624). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0484
Epoch 00023: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 13ms/step - loss: 0.0483 - lr: 5.0000e-04
Epoch 24/200
 1/32 [..............................] - ETA: 0s - loss: 0.0487WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.185315). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0483
Epoch 00024: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 13ms/step - loss: 0.0484 - lr: 5.0000e-04
Epoch 25/200
 1/32 [..............................] - ETA: 0s - loss: 0.0477WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.119600). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0478
Epoch 00025: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0478 - lr: 5.0000e-04
Epoch 26/200
 1/32 [..............................] - ETA: 0s - loss: 0.0452WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.181677). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0476
Epoch 00026: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0477 - lr: 5.0000e-04
Epoch 27/200
 1/32 [..............................] - ETA: 0s - loss: 0.0523WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.187767). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0473
Epoch 00027: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 15ms/step - loss: 0.0473 - lr: 5.0000e-04
Epoch 28/200
 1/32 [..............................] - ETA: 0s - loss: 0.0517WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.153900). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0471
Epoch 00028: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0471 - lr: 5.0000e-04
Epoch 29/200
 1/32 [..............................] - ETA: 0s - loss: 0.0454WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.193685). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0469
Epoch 00029: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 13ms/step - loss: 0.0469 - lr: 5.0000e-04
Epoch 30/200
 1/32 [..............................] - ETA: 0s - loss: 0.0523WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.159962). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0468
Epoch 00030: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0468 - lr: 5.0000e-04
Epoch 31/200
 1/32 [..............................] - ETA: 0s - loss: 0.0487WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.137866). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0462
Epoch 00031: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 15ms/step - loss: 0.0462 - lr: 5.0000e-04
Epoch 32/200
 1/32 [..............................] - ETA: 0s - loss: 0.0496WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.164079). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0462
Epoch 00032: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0462 - lr: 5.0000e-04
Epoch 33/200
 1/32 [..............................] - ETA: 0s - loss: 0.0448WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.152622). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0463
Epoch 00033: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0463 - lr: 5.0000e-04
Epoch 34/200
 1/32 [..............................] - ETA: 0s - loss: 0.0407WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.172727). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0460
Epoch 00034: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0460 - lr: 5.0000e-04
Epoch 35/200
 1/32 [..............................] - ETA: 0s - loss: 0.0467WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.153515). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0454
Epoch 00035: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0454 - lr: 5.0000e-04
Epoch 36/200
 1/32 [..............................] - ETA: 0s - loss: 0.0446WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.128518). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0453
Epoch 00036: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0453 - lr: 5.0000e-04
Epoch 37/200
 1/32 [..............................] - ETA: 0s - loss: 0.0496WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.195105). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0454
Epoch 00037: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0454 - lr: 5.0000e-04
Epoch 38/200
 1/32 [..............................] - ETA: 0s - loss: 0.0429WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.184883). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0454
Epoch 00038: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0455 - lr: 5.0000e-04
Epoch 39/200
 1/32 [..............................] - ETA: 0s - loss: 0.0411WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.201833). Check your callbacks.
WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.101416). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0450
Epoch 00039: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 13ms/step - loss: 0.0449 - lr: 5.0000e-04
Epoch 40/200
 1/32 [..............................] - ETA: 0s - loss: 0.0466WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.119749). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0448
Epoch 00040: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 13ms/step - loss: 0.0449 - lr: 5.0000e-04
Epoch 41/200
 1/32 [..............................] - ETA: 0s - loss: 0.0451WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.204513). Check your callbacks.
WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.102256). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0444
Epoch 00041: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0445 - lr: 5.0000e-04
Epoch 42/200
 1/32 [..............................] - ETA: 0s - loss: 0.0476WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.119689). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0445
Epoch 00042: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 13ms/step - loss: 0.0445 - lr: 5.0000e-04
Epoch 43/200
 1/32 [..............................] - ETA: 0s - loss: 0.0444WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.134088). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0444
Epoch 00043: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0444 - lr: 5.0000e-04
Epoch 44/200
 1/32 [..............................] - ETA: 0s - loss: 0.0428WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.134843). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0440
Epoch 00044: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 14ms/step - loss: 0.0440 - lr: 5.0000e-04
Epoch 45/200
31/32 [============================>.] - ETA: 0s - loss: 0.0436
Epoch 00045: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0436 - lr: 5.0000e-04
Epoch 46/200
 1/32 [..............................] - ETA: 0s - loss: 0.0437WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.168516). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0436
Epoch 00046: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0436 - lr: 5.0000e-04
Epoch 47/200
 1/32 [..............................] - ETA: 0s - loss: 0.0429WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.129259). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0436
Epoch 00047: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 13ms/step - loss: 0.0436 - lr: 5.0000e-04
Epoch 48/200
 1/32 [..............................] - ETA: 0s - loss: 0.0477WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.135571). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0433
Epoch 00048: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0433 - lr: 5.0000e-04
Epoch 49/200
 1/32 [..............................] - ETA: 0s - loss: 0.0386WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.116691). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0431
Epoch 00049: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0432 - lr: 5.0000e-04
Epoch 50/200
 1/32 [..............................] - ETA: 0s - loss: 0.0443WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.110375). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0430
Epoch 00050: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0431 - lr: 5.0000e-04
Epoch 51/200
 1/32 [..............................] - ETA: 0s - loss: 0.0437WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.118361). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0433
Epoch 00051: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 13ms/step - loss: 0.0432 - lr: 5.0000e-04
Epoch 52/200
 1/32 [..............................] - ETA: 0s - loss: 0.0443WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.186457). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0428
Epoch 00052: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 13ms/step - loss: 0.0428 - lr: 5.0000e-04
Epoch 53/200
 1/32 [..............................] - ETA: 0s - loss: 0.0435WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.114945). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0427
Epoch 00053: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 13ms/step - loss: 0.0426 - lr: 5.0000e-04
Epoch 54/200
 1/32 [..............................] - ETA: 0s - loss: 0.0412WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.125634). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0423
Epoch 00054: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0423 - lr: 5.0000e-04
Epoch 55/200
31/32 [============================>.] - ETA: 0s - loss: 0.0423
Epoch 00055: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0423 - lr: 5.0000e-04
Epoch 56/200
 1/32 [..............................] - ETA: 0s - loss: 0.0405WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.104284). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0422
Epoch 00056: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 14ms/step - loss: 0.0422 - lr: 5.0000e-04
Epoch 57/200
 1/32 [..............................] - ETA: 0s - loss: 0.0448WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.105100). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0420
Epoch 00057: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0420 - lr: 5.0000e-04
Epoch 58/200
 1/32 [..............................] - ETA: 0s - loss: 0.0410WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.171283). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0419
Epoch 00058: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 13ms/step - loss: 0.0419 - lr: 5.0000e-04
Epoch 59/200
 1/32 [..............................] - ETA: 0s - loss: 0.0412WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.127077). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0418
Epoch 00059: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 14ms/step - loss: 0.0417 - lr: 5.0000e-04
Epoch 60/200
 1/32 [..............................] - ETA: 0s - loss: 0.0466WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.137723). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0414
Epoch 00060: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0415 - lr: 5.0000e-04
Epoch 61/200
31/32 [============================>.] - ETA: 0s - loss: 0.0416
Epoch 00061: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0415 - lr: 5.0000e-04
Epoch 62/200
 1/32 [..............................] - ETA: 0s - loss: 0.0426WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.142526). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0416
Epoch 00062: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0416 - lr: 5.0000e-04
Epoch 63/200
 1/32 [..............................] - ETA: 0s - loss: 0.0421WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.180391). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0415
Epoch 00063: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0416 - lr: 5.0000e-04
Epoch 64/200
31/32 [============================>.] - ETA: 0s - loss: 0.0412
Epoch 00064: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 13ms/step - loss: 0.0413 - lr: 5.0000e-04
Epoch 65/200
 1/32 [..............................] - ETA: 0s - loss: 0.0427WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.164148). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0413
Epoch 00065: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0412 - lr: 5.0000e-04
Epoch 66/200
 1/32 [..............................] - ETA: 0s - loss: 0.0403WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.159097). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0410
Epoch 00066: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0410 - lr: 5.0000e-04
Epoch 67/200
 1/32 [..............................] - ETA: 0s - loss: 0.0442WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.143583). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0407
Epoch 00067: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 14ms/step - loss: 0.0408 - lr: 5.0000e-04
Epoch 68/200
 1/32 [..............................] - ETA: 0s - loss: 0.0375WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.112629). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0410
Epoch 00068: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0410 - lr: 5.0000e-04
Epoch 69/200
31/32 [============================>.] - ETA: 0s - loss: 0.0415
Epoch 00069: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 13ms/step - loss: 0.0415 - lr: 5.0000e-04
Epoch 70/200
 1/32 [..............................] - ETA: 0s - loss: 0.0386WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.148578). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0407
Epoch 00070: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 14ms/step - loss: 0.0407 - lr: 5.0000e-04
Epoch 71/200
 1/32 [..............................] - ETA: 0s - loss: 0.0378WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.127689). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0404
Epoch 00071: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0405 - lr: 5.0000e-04
Epoch 72/200
 1/32 [..............................] - ETA: 0s - loss: 0.0377WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.117565). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0403
Epoch 00072: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0403 - lr: 5.0000e-04
Epoch 73/200
 1/32 [..............................] - ETA: 0s - loss: 0.0413WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.105204). Check your callbacks.
27/32 [========================>.....] - ETA: 0s - loss: 0.0408
Epoch 00073: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0408 - lr: 5.0000e-04
Epoch 74/200
 1/32 [..............................] - ETA: 0s - loss: 0.0388WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.136623). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0406
Epoch 00074: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 13ms/step - loss: 0.0406 - lr: 5.0000e-04
Epoch 75/200
 1/32 [..............................] - ETA: 0s - loss: 0.0427WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.157797). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0402
Epoch 00075: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0402 - lr: 5.0000e-04
Epoch 76/200
 1/32 [..............................] - ETA: 0s - loss: 0.0373WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.210308). Check your callbacks.
WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.105154). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0397
Epoch 00076: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 14ms/step - loss: 0.0398 - lr: 5.0000e-04
Epoch 77/200
 1/32 [..............................] - ETA: 0s - loss: 0.0397WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.245679). Check your callbacks.
WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.122840). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0401
Epoch 00077: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0400 - lr: 5.0000e-04
Epoch 78/200
 1/32 [..............................] - ETA: 0s - loss: 0.0439WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.132807). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0398
Epoch 00078: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0398 - lr: 5.0000e-04
Epoch 79/200
 1/32 [..............................] - ETA: 0s - loss: 0.0364WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.134304). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0396
Epoch 00079: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0396 - lr: 5.0000e-04
Epoch 80/200
 1/32 [..............................] - ETA: 0s - loss: 0.0395WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.116076). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0399
Epoch 00080: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 13ms/step - loss: 0.0399 - lr: 5.0000e-04
Epoch 81/200
 1/32 [..............................] - ETA: 0s - loss: 0.0416WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.144999). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0397
Epoch 00081: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0396 - lr: 5.0000e-04
Epoch 82/200
 1/32 [..............................] - ETA: 0s - loss: 0.0425WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.159446). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0398
Epoch 00082: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 13ms/step - loss: 0.0399 - lr: 5.0000e-04
Epoch 83/200
 1/32 [..............................] - ETA: 0s - loss: 0.0377WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.177429). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0399
Epoch 00083: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 13ms/step - loss: 0.0399 - lr: 5.0000e-04
Epoch 84/200
 1/32 [..............................] - ETA: 0s - loss: 0.0385WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.119000). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0391
Epoch 00084: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 1s 34ms/step - loss: 0.0391 - lr: 5.0000e-04
Epoch 85/200
 1/32 [..............................] - ETA: 0s - loss: 0.0381WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.261014). Check your callbacks.
WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.130507). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0391
Epoch 00085: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 1s 26ms/step - loss: 0.0391 - lr: 5.0000e-04
Epoch 86/200
 1/32 [..............................] - ETA: 0s - loss: 0.0377WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.120770). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0394
Epoch 00086: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 13ms/step - loss: 0.0395 - lr: 5.0000e-04
Epoch 87/200
 1/32 [..............................] - ETA: 0s - loss: 0.0396WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.114269). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0394
Epoch 00087: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 1s 39ms/step - loss: 0.0394 - lr: 5.0000e-04
Epoch 88/200
 1/32 [..............................] - ETA: 0s - loss: 0.0392WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.351007). Check your callbacks.
WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.175504). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0394
Epoch 00088: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 1s 34ms/step - loss: 0.0394 - lr: 5.0000e-04
Epoch 89/200
 1/32 [..............................] - ETA: 0s - loss: 0.0414WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.122991). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0390
Epoch 00089: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 1s 37ms/step - loss: 0.0390 - lr: 5.0000e-04
Epoch 90/200
 1/32 [..............................] - ETA: 0s - loss: 0.0368WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.152745). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0390
Epoch 00090: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 13ms/step - loss: 0.0390 - lr: 5.0000e-04
Epoch 91/200
 1/32 [..............................] - ETA: 0s - loss: 0.0324WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.104987). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0388
Epoch 00091: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0388 - lr: 5.0000e-04
Epoch 92/200
 1/32 [..............................] - ETA: 0s - loss: 0.0372WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.151107). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0387
Epoch 00092: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 13ms/step - loss: 0.0388 - lr: 5.0000e-04
Epoch 93/200
31/32 [============================>.] - ETA: 0s - loss: 0.0388
Epoch 00093: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 14ms/step - loss: 0.0388 - lr: 5.0000e-04
Epoch 94/200
 1/32 [..............................] - ETA: 0s - loss: 0.0420WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.119211). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0384
Epoch 00094: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0385 - lr: 5.0000e-04
Epoch 95/200
 1/32 [..............................] - ETA: 0s - loss: 0.0347WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.169799). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0388
Epoch 00095: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 13ms/step - loss: 0.0388 - lr: 5.0000e-04
Epoch 96/200
 1/32 [..............................] - ETA: 0s - loss: 0.0329WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.144081). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0389
Epoch 00096: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0389 - lr: 5.0000e-04
Epoch 97/200
31/32 [============================>.] - ETA: 0s - loss: 0.0388
Epoch 00097: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0387 - lr: 5.0000e-04
Epoch 98/200
 1/32 [..............................] - ETA: 0s - loss: 0.0347WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.193964). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0387
Epoch 00098: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 13ms/step - loss: 0.0387 - lr: 5.0000e-04
Epoch 99/200
 1/32 [..............................] - ETA: 0s - loss: 0.0431WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.118795). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0389
Epoch 00099: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 13ms/step - loss: 0.0387 - lr: 5.0000e-04
Epoch 100/200
 1/32 [..............................] - ETA: 0s - loss: 0.0358WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.133508). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0383
Epoch 00100: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0384 - lr: 5.0000e-04
Epoch 101/200
 1/32 [..............................] - ETA: 0s - loss: 0.0401WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.130525). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0384
Epoch 00101: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0384 - lr: 5.0000e-04
Epoch 102/200
 1/32 [..............................] - ETA: 0s - loss: 0.0388WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.133069). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0385
Epoch 00102: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0385 - lr: 5.0000e-04
Epoch 103/200
 1/32 [..............................] - ETA: 0s - loss: 0.0371WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.116869). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0382
Epoch 00103: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0382 - lr: 5.0000e-04
Epoch 104/200
 1/32 [..............................] - ETA: 0s - loss: 0.0367WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.157788). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0383
Epoch 00104: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0383 - lr: 5.0000e-04
Epoch 105/200
 1/32 [..............................] - ETA: 0s - loss: 0.0415WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.146682). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0383
Epoch 00105: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0383 - lr: 5.0000e-04
Epoch 106/200
 1/32 [..............................] - ETA: 0s - loss: 0.0360WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.110870). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0378
Epoch 00106: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0378 - lr: 5.0000e-04
Epoch 107/200
 1/32 [..............................] - ETA: 0s - loss: 0.0429WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.129730). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0377
Epoch 00107: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0378 - lr: 5.0000e-04
Epoch 108/200
 1/32 [..............................] - ETA: 0s - loss: 0.0363WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.189367). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0376
Epoch 00108: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 13ms/step - loss: 0.0376 - lr: 5.0000e-04
Epoch 109/200
 1/32 [..............................] - ETA: 0s - loss: 0.0371WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.113837). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0376
Epoch 00109: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0376 - lr: 5.0000e-04
Epoch 110/200
31/32 [============================>.] - ETA: 0s - loss: 0.0375
Epoch 00110: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0376 - lr: 5.0000e-04
Epoch 111/200
 1/32 [..............................] - ETA: 0s - loss: 0.0382WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.115215). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0374
Epoch 00111: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0375 - lr: 5.0000e-04
Epoch 112/200
 1/32 [..............................] - ETA: 0s - loss: 0.0399WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.167160). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0374
Epoch 00112: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0375 - lr: 5.0000e-04
Epoch 113/200
 1/32 [..............................] - ETA: 0s - loss: 0.0341WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.116912). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0378
Epoch 00113: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0378 - lr: 5.0000e-04
Epoch 114/200
 1/32 [..............................] - ETA: 0s - loss: 0.0376WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.106004). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0376
Epoch 00114: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0376 - lr: 5.0000e-04
Epoch 115/200
31/32 [============================>.] - ETA: 0s - loss: 0.0374
Epoch 00115: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 13ms/step - loss: 0.0375 - lr: 5.0000e-04
Epoch 116/200
 1/32 [..............................] - ETA: 0s - loss: 0.0371WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.145559). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0376
Epoch 00116: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0376 - lr: 5.0000e-04
Epoch 117/200
 1/32 [..............................] - ETA: 0s - loss: 0.0407WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.150721). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0376
Epoch 00117: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 13ms/step - loss: 0.0376 - lr: 5.0000e-04
Epoch 118/200
 1/32 [..............................] - ETA: 0s - loss: 0.0381WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.118821). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0377
Epoch 00118: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 13ms/step - loss: 0.0377 - lr: 5.0000e-04
Epoch 119/200
 1/32 [..............................] - ETA: 0s - loss: 0.0336WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.143196). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0375
Epoch 00119: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0376 - lr: 5.0000e-04
Epoch 120/200
 1/32 [..............................] - ETA: 0s - loss: 0.0402WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.128713). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0373
Epoch 00120: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0373 - lr: 5.0000e-04
Epoch 121/200
31/32 [============================>.] - ETA: 0s - loss: 0.0378
Epoch 00121: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0378 - lr: 5.0000e-04
Epoch 122/200
31/32 [============================>.] - ETA: 0s - loss: 0.0372
Epoch 00122: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0372 - lr: 5.0000e-04
Epoch 123/200
 1/32 [..............................] - ETA: 0s - loss: 0.0376WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.121814). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0374
Epoch 00123: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0373 - lr: 5.0000e-04
Epoch 124/200
 1/32 [..............................] - ETA: 0s - loss: 0.0436WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.104713). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0372
Epoch 00124: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0371 - lr: 5.0000e-04
Epoch 125/200
 1/32 [..............................] - ETA: 0s - loss: 0.0345WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.136396). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0373
Epoch 00125: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0373 - lr: 5.0000e-04
Epoch 126/200
 1/32 [..............................] - ETA: 0s - loss: 0.0367WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.194277). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0370
Epoch 00126: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0371 - lr: 5.0000e-04
Epoch 127/200
 1/32 [..............................] - ETA: 0s - loss: 0.0338WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.125493). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0370
Epoch 00127: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 14ms/step - loss: 0.0371 - lr: 5.0000e-04
Epoch 128/200
31/32 [============================>.] - ETA: 0s - loss: 0.0368
Epoch 00128: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 13ms/step - loss: 0.0368 - lr: 5.0000e-04
Epoch 129/200
 1/32 [..............................] - ETA: 0s - loss: 0.0347WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.127764). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0370
Epoch 00129: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 13ms/step - loss: 0.0370 - lr: 5.0000e-04
Epoch 130/200
 1/32 [..............................] - ETA: 0s - loss: 0.0359WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.161100). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0369
Epoch 00130: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 13ms/step - loss: 0.0370 - lr: 5.0000e-04
Epoch 131/200
 1/32 [..............................] - ETA: 0s - loss: 0.0374WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.109851). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0370
Epoch 00131: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0369 - lr: 5.0000e-04
Epoch 132/200
 1/32 [..............................] - ETA: 0s - loss: 0.0360WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.114379). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0371
Epoch 00132: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0371 - lr: 5.0000e-04
Epoch 133/200
31/32 [============================>.] - ETA: 0s - loss: 0.0367
Epoch 00133: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0368 - lr: 5.0000e-04
Epoch 134/200
 1/32 [..............................] - ETA: 0s - loss: 0.0291WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.108830). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0368
Epoch 00134: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0367 - lr: 5.0000e-04
Epoch 135/200
31/32 [============================>.] - ETA: 0s - loss: 0.0371
Epoch 00135: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0371 - lr: 5.0000e-04
Epoch 136/200
31/32 [============================>.] - ETA: 0s - loss: 0.0369
Epoch 00136: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0369 - lr: 5.0000e-04
Epoch 137/200
 1/32 [..............................] - ETA: 0s - loss: 0.0377WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.112227). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0366
Epoch 00137: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0365 - lr: 5.0000e-04
Epoch 138/200
 1/32 [..............................] - ETA: 0s - loss: 0.0380WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.112669). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0368
Epoch 00138: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 13ms/step - loss: 0.0368 - lr: 5.0000e-04
Epoch 139/200
 1/32 [..............................] - ETA: 0s - loss: 0.0362WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.134874). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0368
Epoch 00139: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0368 - lr: 5.0000e-04
Epoch 140/200
 1/32 [..............................] - ETA: 0s - loss: 0.0397WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.153912). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0368
Epoch 00140: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0368 - lr: 5.0000e-04
Epoch 141/200
 1/32 [..............................] - ETA: 0s - loss: 0.0390WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.130529). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0365
Epoch 00141: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0365 - lr: 5.0000e-04
Epoch 142/200
31/32 [============================>.] - ETA: 0s - loss: 0.0366
Epoch 00142: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 13ms/step - loss: 0.0367 - lr: 5.0000e-04
Epoch 143/200
 1/32 [..............................] - ETA: 0s - loss: 0.0365WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.149135). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0370
Epoch 00143: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0370 - lr: 5.0000e-04
Epoch 144/200
 1/32 [..............................] - ETA: 0s - loss: 0.0340WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.168043). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0370
Epoch 00144: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0370 - lr: 5.0000e-04
Epoch 145/200
31/32 [============================>.] - ETA: 0s - loss: 0.0363
Epoch 00145: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0363 - lr: 5.0000e-04
Epoch 146/200
 1/32 [..............................] - ETA: 0s - loss: 0.0354WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.113825). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0362
Epoch 00146: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 13ms/step - loss: 0.0362 - lr: 5.0000e-04
Epoch 147/200
 1/32 [..............................] - ETA: 0s - loss: 0.0306WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.132873). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0365
Epoch 00147: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 13ms/step - loss: 0.0365 - lr: 5.0000e-04
Epoch 148/200
 1/32 [..............................] - ETA: 0s - loss: 0.0359WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.127897). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0364
Epoch 00148: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0363 - lr: 5.0000e-04
Epoch 149/200
 1/32 [..............................] - ETA: 0s - loss: 0.0320WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.103766). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0362
Epoch 00149: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0363 - lr: 5.0000e-04
Epoch 150/200
 1/32 [..............................] - ETA: 0s - loss: 0.0386WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.127532). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0362
Epoch 00150: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0362 - lr: 5.0000e-04
Epoch 151/200
 1/32 [..............................] - ETA: 0s - loss: 0.0346WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.112187). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0363
Epoch 00151: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0362 - lr: 5.0000e-04
Epoch 152/200
 1/32 [..............................] - ETA: 0s - loss: 0.0366WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.146342). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0359
Epoch 00152: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0360 - lr: 5.0000e-04
Epoch 153/200
 1/32 [..............................] - ETA: 0s - loss: 0.0324WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.172528). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0364
Epoch 00153: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0364 - lr: 5.0000e-04
Epoch 154/200
 1/32 [..............................] - ETA: 0s - loss: 0.0403WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.104089). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0363
Epoch 00154: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0363 - lr: 5.0000e-04
Epoch 155/200
 1/32 [..............................] - ETA: 0s - loss: 0.0380WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.116439). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0362
Epoch 00155: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 14ms/step - loss: 0.0363 - lr: 5.0000e-04
Epoch 156/200
 1/32 [..............................] - ETA: 0s - loss: 0.0380WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.118985). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0363
Epoch 00156: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0363 - lr: 5.0000e-04
Epoch 157/200
31/32 [============================>.] - ETA: 0s - loss: 0.0362
Epoch 00157: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0362 - lr: 5.0000e-04
Epoch 158/200
 1/32 [..............................] - ETA: 0s - loss: 0.0340WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.139539). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0364
Epoch 00158: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0364 - lr: 5.0000e-04
Epoch 159/200
31/32 [============================>.] - ETA: 0s - loss: 0.0360
Epoch 00159: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0360 - lr: 5.0000e-04
Epoch 160/200
 1/32 [..............................] - ETA: 0s - loss: 0.0325WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.102324). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0362
Epoch 00160: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 13ms/step - loss: 0.0362 - lr: 5.0000e-04
Epoch 161/200
 1/32 [..............................] - ETA: 0s - loss: 0.0389WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.109350). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0362
Epoch 00161: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0362 - lr: 5.0000e-04
Epoch 162/200
 1/32 [..............................] - ETA: 0s - loss: 0.0333WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.130358). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0359
Epoch 00162: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0359 - lr: 5.0000e-04
Epoch 163/200
 1/32 [..............................] - ETA: 0s - loss: 0.0370WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.107801). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0359
Epoch 00163: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 13ms/step - loss: 0.0359 - lr: 5.0000e-04
Epoch 164/200
 1/32 [..............................] - ETA: 0s - loss: 0.0344WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.167726). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0358
Epoch 00164: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0359 - lr: 5.0000e-04
Epoch 165/200
31/32 [============================>.] - ETA: 0s - loss: 0.0357
Epoch 00165: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0357 - lr: 5.0000e-04
Epoch 166/200
 1/32 [..............................] - ETA: 0s - loss: 0.0341WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.168941). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0357
Epoch 00166: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0357 - lr: 5.0000e-04
Epoch 167/200
 1/32 [..............................] - ETA: 0s - loss: 0.0320WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.135426). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0356
Epoch 00167: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0355 - lr: 5.0000e-04
Epoch 168/200
 1/32 [..............................] - ETA: 0s - loss: 0.0397WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.106583). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0359
Epoch 00168: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0359 - lr: 5.0000e-04
Epoch 169/200
 1/32 [..............................] - ETA: 0s - loss: 0.0380WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.123190). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0358
Epoch 00169: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0358 - lr: 5.0000e-04
Epoch 170/200
 1/32 [..............................] - ETA: 0s - loss: 0.0412WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.172005). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0354
Epoch 00170: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 13ms/step - loss: 0.0355 - lr: 5.0000e-04
Epoch 171/200
31/32 [============================>.] - ETA: 0s - loss: 0.0355
Epoch 00171: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0354 - lr: 5.0000e-04
Epoch 172/200
 1/32 [..............................] - ETA: 0s - loss: 0.0399WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.134673). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0355
Epoch 00172: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0355 - lr: 5.0000e-04
Epoch 173/200
31/32 [============================>.] - ETA: 0s - loss: 0.0355
Epoch 00173: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0355 - lr: 5.0000e-04
Epoch 174/200
 1/32 [..............................] - ETA: 0s - loss: 0.0340WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.143764). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0357
Epoch 00174: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0358 - lr: 5.0000e-04
Epoch 175/200
 1/32 [..............................] - ETA: 0s - loss: 0.0353WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.133860). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0358
Epoch 00175: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0358 - lr: 5.0000e-04
Epoch 176/200
 1/32 [..............................] - ETA: 0s - loss: 0.0347WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.159564). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0356
Epoch 00176: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0356 - lr: 5.0000e-04
Epoch 177/200
 1/32 [..............................] - ETA: 0s - loss: 0.0294WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.153865). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0353
Epoch 00177: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 13ms/step - loss: 0.0354 - lr: 5.0000e-04
Epoch 178/200
 1/32 [..............................] - ETA: 0s - loss: 0.0349WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.105075). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0354
Epoch 00178: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 13ms/step - loss: 0.0354 - lr: 5.0000e-04
Epoch 179/200
 1/32 [..............................] - ETA: 0s - loss: 0.0314WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.109728). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0353
Epoch 00179: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0353 - lr: 5.0000e-04
Epoch 180/200
 1/32 [..............................] - ETA: 0s - loss: 0.0382WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.164529). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0354
Epoch 00180: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0353 - lr: 5.0000e-04
Epoch 181/200
 1/32 [..............................] - ETA: 0s - loss: 0.0309WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.111639). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0354
Epoch 00181: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 13ms/step - loss: 0.0354 - lr: 5.0000e-04
Epoch 182/200
31/32 [============================>.] - ETA: 0s - loss: 0.0355
Epoch 00182: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0355 - lr: 5.0000e-04
Epoch 183/200
 1/32 [..............................] - ETA: 0s - loss: 0.0371WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.158155). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0355
Epoch 00183: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0354 - lr: 5.0000e-04
Epoch 184/200
 1/32 [..............................] - ETA: 0s - loss: 0.0283WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.140011). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0356
Epoch 00184: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 13ms/step - loss: 0.0357 - lr: 5.0000e-04
Epoch 185/200
 1/32 [..............................] - ETA: 0s - loss: 0.0359WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.132058). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0353
Epoch 00185: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0353 - lr: 5.0000e-04
Epoch 186/200
 1/32 [..............................] - ETA: 0s - loss: 0.0382WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.115101). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0352
Epoch 00186: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0352 - lr: 5.0000e-04
Epoch 187/200
 1/32 [..............................] - ETA: 0s - loss: 0.0343WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.121085). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0353
Epoch 00187: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 13ms/step - loss: 0.0353 - lr: 5.0000e-04
Epoch 188/200
 1/32 [..............................] - ETA: 0s - loss: 0.0347WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.168395). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0355
Epoch 00188: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0354 - lr: 5.0000e-04
Epoch 189/200
 1/32 [..............................] - ETA: 0s - loss: 0.0265WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.109189). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0357
Epoch 00189: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0357 - lr: 5.0000e-04
Epoch 190/200
31/32 [============================>.] - ETA: 0s - loss: 0.0353
Epoch 00190: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0353 - lr: 5.0000e-04
Epoch 191/200
 1/32 [..............................] - ETA: 0s - loss: 0.0342WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.144513). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0355
Epoch 00191: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0355 - lr: 5.0000e-04
Epoch 192/200
31/32 [============================>.] - ETA: 0s - loss: 0.0351
Epoch 00192: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 13ms/step - loss: 0.0352 - lr: 5.0000e-04
Epoch 193/200
31/32 [============================>.] - ETA: 0s - loss: 0.0349
Epoch 00193: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 14ms/step - loss: 0.0349 - lr: 5.0000e-04
Epoch 194/200
 1/32 [..............................] - ETA: 0s - loss: 0.0324WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.170247). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0351
Epoch 00194: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0351 - lr: 5.0000e-04
Epoch 195/200
 1/32 [..............................] - ETA: 0s - loss: 0.0397WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.113760). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0349
Epoch 00195: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0350 - lr: 5.0000e-04
Epoch 196/200
 1/32 [..............................] - ETA: 0s - loss: 0.0329WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.126841). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0354
Epoch 00196: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0353 - lr: 5.0000e-04
Epoch 197/200
 1/32 [..............................] - ETA: 0s - loss: 0.0289WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.112251). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0348
Epoch 00197: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0348 - lr: 5.0000e-04
Epoch 198/200
 1/32 [..............................] - ETA: 0s - loss: 0.0342WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.149568). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0350
Epoch 00198: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0349 - lr: 5.0000e-04
Epoch 199/200
 1/32 [..............................] - ETA: 0s - loss: 0.0361WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.116491). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0349
Epoch 00199: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0349 - lr: 5.0000e-04
Epoch 200/200
 1/32 [..............................] - ETA: 0s - loss: 0.0388WARNING:tensorflow:Method (on_train_batch_end) is slow compared to the batch update (0.107144). Check your callbacks.
31/32 [============================>.] - ETA: 0s - loss: 0.0348
Epoch 00200: saving model to run/vae/0001_digits\weights/weights.h5
32/32 [==============================] - 0s 12ms/step - loss: 0.0348 - lr: 5.0000e-04

autoencoderをtrain中に出力された画像を表示する

In [14]:
import os
import glob


path = os.path.join(RUN_FOLDER, 'images')
fs = glob.glob(os.path.join(path, '*.jpg'))

print(len(fs))
200
In [15]:
%matplotlib inline
import matplotlib.pyplot as plt
import matplotlib.image as mpimg

n_images = len(fs)
n_rows=10
n_lines = (n_images + n_rows - 1) // n_rows

fig, ax = plt.subplots(n_lines, n_rows, figsize=(2.8 * n_rows, 2.8 * n_lines))
for i, path in  enumerate(fs):
    y = i // n_rows
    x = i % n_rows
    img = mpimg.imread(path)
    ax[y][x].imshow(img)
    ax[y][x].axis('off')
    
plt.show()