Я изучаю учебник здесь. Моя модель часть:
input_img = keras.Input(shape=img_shape)
x = layers.Conv2D(32, (3, 3),
padding='same', activation='relu')(input_img)
...
x = layers.Conv2D(64, (3, 3),
padding='same', activation='relu')(x)
shape_before_flattening = K.int_shape(x)
x = layers.Flatten()(x)
x = layers.Dense(32, activation='relu')(x)
z_mean = layers.Dense(latent_dim)(x)
z_log_var = layers.Dense(latent_dim)(x)
def sampling(args):
...
z = layers.Lambda(sampling)([z_mean, z_log_var])
decoder_input = layers.Input(K.int_shape(z)[1:])
x = layers.Dense(np.prod(shape_before_flattening[1:]),
activation='relu')(decoder_input)
x = layers.Reshape(shape_before_flattening[1:])(x)
x = layers.Conv2DTranspose(32, 3,
padding='same', activation='relu',
strides=(2, 2))(x)
x = layers.Conv2D(1, 3,
padding='same', activation='sigmoid')(x)
# This is our decoder model from letent space to reconstructed images
decoder = Model(decoder_input, x)
# We then apply it to `z` to recover the decoded `z`.
z_decoded = decoder(z)
def vae_loss(self, x, z_decoded):
...
# Fit the end-to-end model
vae = Model(input_img, z_decoded) # vae = Model(input_img, x)
vae.compile(optimizer='rmsprop', loss=vae_loss)
vae.summary()
Мой вопрос: сквозной является vae = Model(input_img, z_decoded)
или vae = Model(input_img, x)
. Должны ли мы вычислять потери на input_img
и z_decoded
ИЛИ между input_img
и x
? Спасибо