Learning rate function on compiled model fails?

I’m adapting some code to neaten it up and call it from a module. The original code runs through fine where an uncompiled model is explicitly defined near the learning rate test. Please have a look at the error and code and let me know where I’m going wrong.

When I call the code as a function passing a similar compiled model I receive:

ValueError: `y` argument is not supported when using dataset as input.

This is raised at:

    lr_history = compiled_model.fit(training_dataset, num_epochs, 

The original code:

def create_uncompiled_model():
    model = tf.keras.models.Sequential([
        tf.keras.layers.Conv1D(filters=64, kernel_size=3, ...),
        tf.keras.layers.LSTM(64, return_sequences=True),
        tf.keras.layers.Dense(10, activation="relu"),
    return model

def adjust_learning_rate(dataset):
    model = create_uncompiled_model()
    lr_schedule = tf.keras.callbacks.LearningRateScheduler(lambda epoch: 1e-4 * 10**(epoch / 20))
    optimizer = tf.keras.optimizers.SGD(momentum=0.9)

    history = model.fit(dataset, epochs=100, callbacks=[lr_schedule])

    return history
    # Run the training with dynamic LR
lr_history = adjust_learning_rate(train_set)

My function code:

def learning_rate_history(compiled_model, train_set):
    lr_schedule = tf.keras.callbacks.LearningRateScheduler(lambda epoch: \
        1e-4 * 10**(epoch / 20))
    lr_history = compiled_model.fit(train_set, num_epochs, 
    return lr_history

Hi @brendonwp, The error is due to num_epochs value is considered as value to the y argument, where the values to the y argument is not accepted while passing dataset as the input to the model.fit method. please pass num_epochs by assigning it to the epochs argument. For example

    lr_history = compiled_model.fit(training_dataset, epochs=num_epochs, 

Thank You.

1 Like

Thanks @Kiran_Sai_Ramineni - works 100% now :slight_smile: