W2A2E2 input layer for alapaca model


In order to create an input layer, I used the code

tf.keras.layers.InputLayer(    input_shape=None, batch_size=None, dtype=None, input_tensor=None, sparse=None,    name=None, ragged=None, type_spec=None, **kwargs)

from the page tf.keras.layers.InputLayer  |  TensorFlow Core v2.6.0. But the error code seems to contradict it. What can be done?

For the input layer, try the argument “shape = input_shape”. No other arguments are needed.

Where the instructions say to use data augmentation, I recommend you use the “data_augmentation( inputs)” function.


Then it shows this.

(mentor edit - previous text removed)


The previous problem seems to be solved, but I’m now told to have mismatching dims. I have no idea about the dimensions at all, since they are not given in the problem.

{reply edited - padding to 20 chars}

The error doesn’t say mismatching dims - it says you have the wrong number of layers in the alpaca model.

I don’t think I have the chance to decide the number of layers either. Code sent in a separate message. Please check. Thanks!

Hello, have you seen it? I used private message for the first time, and not sure it it’s delivered.