week3//A1//UNQ_C2

[Deep977]

when I run the cell: there must be some code wrong.

[[‘InputLayer’, [(None, 30, 37)], 0], [‘InputLayer’, [(None, 64)], 0], [‘Bidirectional’, (None, 30, 64), 17920], [‘RepeatVector’, (None, 30, 64), 0, 30], [‘Concatenate’, (None, 30, 128), 0], [‘Dense’, (None, 30, 10), 1290, ‘tanh’], [‘Dense’, (None, 30, 1), 11, ‘relu’], [‘Activation’, (None, 30, 1), 0], [‘Dot’, (None, 1, 64), 0], [‘InputLayer’, [(None, 64)], 0], [‘LSTM’, [(None, 64), (None, 64), (None, 64)], 33024, [(None, 1, 64), (None, 64), (None, 64)], ‘tanh’], [‘RepeatVector’, (None, 30, 64), 0, 30], [‘Concatenate’, (None, 30, 128), 0], [‘Dot’, (None, 1, 64), 0], [‘RepeatVector’, (None, 30, 64), 0, 30], [‘Concatenate’, (None, 30, 128), 0], [‘Dot’, (None, 1, 64), 0], [‘RepeatVector’, (None, 30, 64), 0, 30], [‘Concatenate’, (None, 30, 128), 0], [‘Dot’, (None, 1, 64), 0], [‘RepeatVector’, (None, 30, 64), 0, 30], [‘Concatenate’, (None, 30, 128), 0], [‘Dot’, (None, 1, 64), 0], [‘RepeatVector’, (None, 30, 64), 0, 30], [‘Concatenate’, (None, 30, 128), 0], [‘Dot’, (None, 1, 64), 0], [‘RepeatVector’, (None, 30, 64), 0, 30], [‘Concatenate’, (None, 30, 128), 0], [‘Dot’, (None, 1, 64), 0], [‘RepeatVector’, (None, 30, 64), 0, 30], [‘Concatenate’, (None, 30, 128), 0], [‘Dot’, (None, 1, 64), 0], [‘RepeatVector’, (None, 30, 64), 0, 30], [‘Concatenate’, (None, 30, 128), 0], [‘Dot’, (None, 1, 64), 0], [‘RepeatVector’, (None, 30, 64), 0, 30], [‘Concatenate’, (None, 30, 128), 0], [‘Dot’, (None, 1, 64), 0], [‘Dense’, (None, 11), 715, ‘softmax’]]
Test failed at layer: 11
Expected value

[‘Dense’, (None, 11), 715, ‘softmax’]

does not match the input value:

[‘RepeatVector’, (None, 30, 64), 0, 30]

AssertionError Traceback (most recent call last)
in
34
35
—> 36 modelf_test(modelf)

in modelf_test(target)
31 assert len(model.outputs) == 10, f"Wrong output shape. Expected 10 != {len(model.outputs)}"
32
—> 33 comparator(summary(model), expected_summary)
34
35

~/work/W3A1/test_utils.py in comparator(learner, instructor)
25 “\n\n does not match the input value: \n\n”,
26 colored(f"{a}", “red”))
—> 27 raise AssertionError(“Error in test”)
28 layer += 1
29 print(colored(“All tests passed!”, “green”))

AssertionError: Error in test

[edwardyu]

Hi @Deep977 ,

It looks like you created RepeatVector, Concatenate, Dot layer sfor each time step. The model won’t learn anything, because the weights in these layers won’t be updated through time. That’s why all layers are pre-defined as below. Please check UNQ_C1: one_step_attention again, and be sure to user these shared layers rather than create new layers.