Getting error in model.evaluate function

[karunaeerapu]

Hi Authors,
I am getting errors in the function model. evaluate, and I guess a custom evaluate function is required. Can you please share the custom evaluate function if any?
File "train_my_model.py", line 80, in train_model
loss, acc, sen, spe, F1 = our_model.evaluate(x=[test_X, test_Y], y=test_label, batch_size=1)
File "C:\Users\hp.conda\envs\ChangeDetection\lib\site-packages\keras\engine\training.py", line 1105, in evaluate
batch_size=batch_size)
File "C:\Users\hp.conda\envs\ChangeDetection\lib\site-packages\keras\engine\training.py", line 792, in _standardize_user_data
exception_prefix='target')
File "C:\Users\hp.conda\envs\ChangeDetection\lib\site-packages\keras\engine\training_utils.py", line 100, in standardize_input_data
str(len(data)) + ' arrays: ' + str(data)[:200] + '...')
ValueError: Error when checking model target: the list of Numpy arrays that you are passing to your model is not the size the model expected. Expected to see 1 array(s), but instead got the following list of 2 arrays: [array([[0., 0., 0., ..., 0., 0., 0.],
[0., 0., 0., ..., 0., 0., 0.],
[0., 0., 0., ..., 0., 0., 0.],
...,
[0., 0., 0., ..., 0., 0., 0.],
[0., 0., 0., ..., 0., 0., 0....

[ChenHongruixuan]

Hi, we didn't use any custom evaluation function. In your illustrated code, "our_model.evaluate()" is the built-in function of Keras. And according to your errors that say "Expected to see 1 array(s), but instead got the following list of 2 arrays", we think it could be caused by the dimension inconsistency between your given label and the network prediction result.