Skip to content
Advertisement

ValueError when using vae.fit in Keras

I am creating a vae model over the mnist dataset with hopes of plotting the loss function against the epochs. However I am experiencing some issues and was unable to find a solution online. During my imports I have the following imports (just to give some context to the code):

from keras import backend as K

from keras.layers import Input, Dense, Lambda, Layer, Add, Multiply
from keras.models import Model, Sequential
from keras.datasets import mnist

I have also created a function called bn for my own loss calculations and the class KLDivergenceLayer that adds a KL divergence layer to the final model loss.

Code:

decoder = Sequential([
    Dense(intermediate_dim, input_dim=latent_dim, activation='relu'),
    Dense(original_dim, activation='sigmoid')
])

x = Input(shape=(original_dim,))
h = Dense(intermediate_dim, activation='relu')(x)

z_mu = Dense(latent_dim)(h)
z_log_var = Dense(latent_dim)(h)

z_mu, z_log_var = KLDivergenceLayer()([z_mu, z_log_var])
z_sigma = Lambda(lambda t: K.exp(.5*t))(z_log_var)

eps = Input(tensor=K.random_normal(stddev=epsilon_std,
                                   shape=(K.shape(x)[0], latent_dim)))
z_eps = Multiply()([z_sigma, eps])
z = Add()([z_mu, z_eps])

x_pred = decoder(z)

vae = Model(inputs=[x, eps], outputs=x_pred)
vae.compile(optimizer='rmsprop', loss=bn)

# train the VAE on MNIST digits
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train = x_train.reshape(-1, original_dim) / 255.
x_test = x_test.reshape(-1, original_dim) / 255.

vae.fit(x_train, x_train,
        shuffle=True,
        epochs=epochs,
        batch_size=batch_size,
        validation_data=(x_test, x_test))

and the error I get back to me is as follows:

ValueError: Layer model expects 2 input(s), but it received 1 input tensors. Inputs received: [<tf.Tensor 'IteratorGetNext:0' shape=(100, 784) dtype=float32>]

Advertisement

Answer

The problem is in your eps layer. it’s not a model input

you can substitute it with a simple layer like this one:

eps = Lambda(lambda t: K.random_normal(stddev=1.0, shape=(K.shape(t)[0], latent_dim)))(z_log_var)

here u can find the running notebook:

https://colab.research.google.com/drive/1fLmfwCA_TOeOlXiiSabp4C4UKq73ofEN?usp=sharing

User contributions licensed under: CC BY-SA
9 People found this is helpful
Advertisement