CODEWITHSUNDEEP
deep-learningautoencoder
Boom
Boom

Reputation: 1315

ValueError: Dimensions must be equal, but are 512 and 1024

I'm trying to build a simple auto encoder model (the input come from cfar10).

    hiden_size1 = 1024
    hiden_size2 = 512
    hiden_size3 = 1024

    input_layer = Input(shape=(3072,))
    decoder_input_layer = Input(shape=(hiden_size2,))
    hidden_layer1 = Dense(hiden_size1, activation="relu", name="hidden1")
    hidden_layer2 = Dense(hiden_size2, activation="relu", name="hidden2")
    hidden_layer3 = Dense(hiden_size3, activation="relu", name="hidden3")
    autoencoder_output_layer = Dense(3072, activation="sigmoid", name="output")


    autoencoder = Sequential()
    autoencoder.add(input_layer)
    autoencoder.add(hidden_layer1)
    autoencoder.add(hidden_layer2)
    autoencoder.add(hidden_layer3)
    autoencoder.add(autoencoder_output_layer)
    autoencoder.compile(optimizer='adam', loss='binary_crossentropy')

    encoder = Sequential()
    encoder.add(input_layer)
    encoder.add(hidden_layer1)
    encoder.add(hidden_layer2)

    decoder = Sequential()
    decoder.add(decoder_input_layer)
    encoder.add(hidden_layer3)
    decoder.add(autoencoder_output_layer)

and I'm getting error on last code line (decoder.add(autoencoder_output_layer)):

ValueError: Dimensions must be equal, but are 512 and 1024 for '{{node output/MatMul}} = MatMul[T=DT_FLOAT, transpose_a=false, transpose_b=false](Placeholder, output/MatMul/ReadVariableOp)' with input shapes: [?,512], [1024,3072].

What is wrong and what am I missing ? How can I fix it ?

Upvotes: 1

Views: 179

Answers (1)

Pranjal dubey
Pranjal dubey

Reputation: 93

I think in the second last line , instead of

    encoder.add(hidden_layer3)

it will be

   decoder.add(hidden_layer3)

Upvotes: 1

Related Questions