CODEWITHSUNDEEP
tensorflowkerasdeep-learningneural-network
BSP
BSP

Reputation: 422

How to set custom weights in layers?

I am looking at how to set custom weights into the layers.

Below is the code I work with

batch_size = 64

input_dim = 12

units = 64
output_size = 1  # labels are from 0 to 9

# Build the RNN model
def build_model(allow_cudnn_kernel=True):


    lstm_layer = keras.layers.RNN(
            keras.layers.LSTMCell(units), input_shape=(None, input_dim)) 


    model = keras.models.Sequential(
        [
            lstm_layer,
            keras.layers.BatchNormalization(),
            keras.layers.Dense(output_size),
        ]
    )
    return model
model = build_model()

model.compile(
    loss=keras.losses.MeanSquaredError(),
    optimizer="Adam",
    metrics=["accuracy"],
)


model.fit(
    x_train, y_train, validation_data=(x_val, y_val), batch_size=batch_size, epochs=15
)

Modle Summary

enter image description here

Can anyone help me how to set_weights in above code? Thanks in advance.

Upvotes: 6

Views: 3684

Answers (1)

user11530462
user11530462

Reputation:

You can do it using set_weights method.

For example, if you want to set the weights of your LSTM Layer, it can be accessed using model.layers[0] and if your Custom Weights are, say in an array, named, my_weights_matrix, then you can set your Custom Weights to First Layer (LSTM) using the code shown below:

model.layers[0].set_weights([my_weights_matrix])

If you don't want your weights to be modified during Training, then you have to Freeze that Layer using the code, model.layers[0].trainable = False.

Please let me know if you face any other issue and I will be Happy to Help you.

Hope this helps. Happy Learning!

Upvotes: 8

Related Questions