ai-guru / ngdlm Goto Github PK

input_shape = (28, 28)
latent_dim = 128

encoder_input = layers.Input(shape=input_shape)
encoder_output = encoder_input
encoder_output = layers.Reshape(input_shape + (1,))(encoder_input)
encoder_output = layers.Conv2D(16, (3, 3), activation="relu", padding="same")(encoder_output)
encoder_output = layers.MaxPooling2D((2, 2), padding="same")(encoder_output)
encoder_output = layers.Conv2D(8, (3, 3), activation="relu", padding="same")(encoder_output)
encoder_output = layers.MaxPooling2D((2, 2), padding="same")(encoder_output)
encoder_output = layers.Conv2D(8, (3, 3), activation="relu", padding="same")(encoder_output)
encoder_output = layers.MaxPooling2D((2, 2), padding="same")(encoder_output)
encoder_output = layers.Flatten()(encoder_output)
encoder = models.Model(encoder_input, encoder_output)

# Create the decoder.
decoder_input = layers.Input(shape=(latent_dim,))
decoder_output = decoder_input
#decoder_output = layers.Dense(128, activation="relu")(decoder_output)
decoder_output = layers.Reshape((4, 4, 8))(decoder_output)
decoder_output = layers.Conv2D(8, (3, 3), activation="relu", padding="same")(decoder_output)
decoder_output = layers.UpSampling2D((2, 2))(decoder_output)
decoder_output = layers.Conv2D(8, (3, 3), activation="relu", padding="same")(decoder_output)
decoder_output = layers.UpSampling2D((2, 2))(decoder_output)
decoder_output = layers.Conv2D(16, (3, 3), activation="relu")(decoder_output)
decoder_output = layers.UpSampling2D((2, 2))(decoder_output)
decoder_output = layers.Conv2D(1, (3, 3), activation="sigmoid", padding="same")(decoder_output)
decoder_output = layers.Reshape((28, 28))(decoder_output)
decoder = models.Model(decoder_input, decoder_output)

# Create the VAE.
vae = ngdlmodels.VAE(encoder, decoder, latent_dim=latent_dim)
vae.compile(optimizer='adadelta', reconstruction_loss="binary_crossentropy")
vae.summary()

# Train.
print("Train...")
history = vae.fit(
        x_input_train, x_input_train,
        epochs=100,
        batch_size=32,
        shuffle=True,
        validation_data=(x_input_test, x_input_test)
    )
    
# Evaluate.
print("Evaluate...")
loss = vae.model.evaluate(x_input_test, x_input_test)
print("Loss:", loss)

TypeError                                 Traceback (most recent call last)
<ipython-input-22-1acf0e514e9b> in <module>()
     31 # Create the VAE.
     32 vae = ngdlmodels.VAE(encoder, decoder, latent_dim=latent_dim)
---> 33 vae.compile(optimizer='adadelta', reconstruction_loss="binary_crossentropy")
     34 vae.summary()
     35 

~/anaconda3/lib/python3.6/site-packages/ngdlm/models.py in compile(self, optimizer, loss, metrics, loss_weights, sample_weight_mode, weighted_metrics, target_tensors, **kwargs)
    433         # Compile model.
    434         loss = vae_loss
--> 435         self.autoencoder.compile(optimizer, loss, metrics, loss_weights, sample_weight_mode, weighted_metrics, **kwargs)
    436 
    437 

~/anaconda3/lib/python3.6/site-packages/keras/engine/training.py in compile(self, optimizer, loss, metrics, loss_weights, sample_weight_mode, weighted_metrics, target_tensors, **kwargs)
    330                 with K.name_scope(self.output_names[i] + '_loss'):
    331                     output_loss = weighted_loss(y_true, y_pred,
--> 332                                                 sample_weight, mask)
    333                 if len(self.outputs) > 1:
    334                     self.metrics_tensors.append(output_loss)

~/anaconda3/lib/python3.6/site-packages/keras/engine/training_utils.py in weighted(y_true, y_pred, weights, mask)
    401         """
    402         # score_array has ndim >= 2
--> 403         score_array = fn(y_true, y_pred)
    404         if mask is not None:
    405             # Cast the mask to floatX to avoid float64 upcasting in Theano

~/anaconda3/lib/python3.6/site-packages/ngdlm/models.py in vae_loss(loss_inputs, loss_outputs)
    419             else:
    420                 r_loss = self.loss
--> 421             r_loss *= inputs_dim
    422 
    423             # kl loss.

TypeError: unsupported operand type(s) for *=: 'NoneType' and 'int'