Я пытаюсь обучить VAE на изображениях лиц и получаю ошибку после метода model.fit (). Я не смог найти решение, которое решило бы мою проблему.
я получаю ошибку:
ValueError: Cannot create an execution function which is comprised of elements from multiple graphs.
кодировщик:
def build_encoder(self):
global K
K.clear_session()
conv_filters = [32, 64, 64, 64]
conv_kernel_size = [3, 3, 3, 3]
conv_strides = [2, 2, 2, 2]
n_layers = len(conv_filters)
x = self.encoder_input
for i in range(n_layers):
x = Conv2D(filters=conv_filters[i],
kernel_size=conv_kernel_size[i],
strides=conv_strides[i],
padding='same',
name='encoder_conv_' + str(i)
)(x)
if self.use_batch_norm:
x = BatchNormalization()(x)
x = LeakyReLU()(x)
if self.use_dropout:
x = Dropout(rate=0.25)(x)
self.shape_before_flattening = K.int_shape(x)[1:]
x = Flatten()(x)
self.mean_layer = Dense(self.encoder_output_dim, name='mu')(x)
self.sd_layer = Dense(self.encoder_output_dim, name='log_var')(x)
def sampling(args):
mean_mu, log_var = args
epsilon = K.random_normal(shape=K.shape(mean_mu), mean=0., stddev=1.)
return mean_mu + K.exp(log_var / 2) * epsilon
encoder_output = Lambda(sampling, name='encoder_output')([self.mean_layer, self.sd_layer])
return Model(self.encoder_input, encoder_output, name="VAE_Encoder")
декодер:
def build_decoder(self):
conv_filters = [64, 64, 32, 3]
conv_kernel_size = [3, 3, 3, 3]
conv_strides = [2, 2, 2, 2]
n_layers = len(conv_filters)
decoder_input = self.decoder_input
x = Dense(np.prod(self.shape_before_flattening))(decoder_input)
x = Reshape(self.shape_before_flattening)(x)
for i in range(n_layers):
x = Conv2DTranspose(filters=conv_filters[i],
kernel_size=conv_kernel_size[i],
strides=conv_strides[i],
padding='same',
name='decoder_conv_' + str(i)
)(x)
if i < n_layers - 1:
x = LeakyReLU()(x)
else:
x = Activation('sigmoid')(x)
self.decoder_output = x
return Model(decoder_input, self.decoder_output, name="VAE_Decoder")
комбинированная модель:
def build_autoencoder(self):
self.encoder = self.build_encoder()
self.decoder = self.build_decoder()
self.autoencoder = Model(self.encoder_input, self.decoder(self.encoder(self.encoder_input)),
name="Variational_Auto_Encoder")
self.autoencoder.compile(optimizer=self.adam_optimizer, loss=self.total_loss,
metrics=[self.r_loss, self.kl_loss],
experimental_run_tf_function=False)
self.autoencoder.summary()
if os.path.exists(self.model_name + ".h5"):
self.autoencoder.load_weights(self.model_name + ".h5") # Loading pre-trained weights
return self.autoencoder
тренировка:
def train(self):
filenames = np.array(glob.glob(os.path.join(self.data_dir, '*/*.jpg')))
NUM_IMAGES = len(filenames)
print("Total number of images : " + str(NUM_IMAGES))
data_flow = ImageDataGenerator(rescale=1. / 255).flow_from_directory(self.data_dir,
target_size=self.input_shape[:2],
batch_size=self.batch_size,
shuffle=True,
class_mode='input',
subset='training'
)
self.autoencoder.fit_generator(data_flow,
shuffle=True,
epochs=self.epochs,
initial_epoch=0,
steps_per_epoch=NUM_IMAGES // self.batch_size
# callbacks=[self.checkpoint_callback]
)
self.autoencoder.save_weights(self.save_dir + self.model_name + ".h5")
Я знаю, что это, вероятно, не лучший способ задать вопрос здесь, но у меня действительно нет Понять, как это решить, надеюсь, ты скажешь мне, что я делаю не так. ☺