Week 1, Assignment 3 (Jazz), issue with this function: music_inference_model

Course Q&A Deep Learning Specialization Sequence Models
1

Hi,

Ive written the below code in my notebook

However, I’m getting an assertion error when I’m getting tested by


#UNIT TEST 
inference_summary = summary(inference_model)
comparator(inference_summary, music_inference_model_out)

I’ve tried looking deeper and printed the items inside “inference_summary” and “music_inference_model_out” (the later is the “correct answer on which we’re graded”). What I figured out is that my model is not creating the layers of this kind
[‘TensorFlowOpLayer’, [(None,)], 0]

Here is a snipped of my output when I was comparing the two:

print(len(summary(inference_model)))
for i in summary(inference_model):
    print(i)
54
['InputLayer', [(None, 1, 90)], 0]
['InputLayer', [(None, 64)], 0]
['InputLayer', [(None, 64)], 0]
['LSTM', [(None, 64), (None, 64), (None, 64)], 39680, [(None, 1, 90), (None, 64), (None, 64)], 'tanh']
['Dense', (None, 90), 5850, 'softmax']
['RepeatVector', (None, 1, 90), 0, 1]
['RepeatVector', (None, 1, 90), 0, 1]
['RepeatVector', (None, 1, 90), 0, 1]
['RepeatVector', (None, 1, 90), 0, 1]

Which I compared to this:

print(len(music_inference_model_out))

for i in music_inference_model_out:
    print(i)
152
['InputLayer', [(None, 1, 90)], 0]
['InputLayer', [(None, 64)], 0]
['InputLayer', [(None, 64)], 0]
['LSTM', [(None, 64), (None, 64), (None, 64)], 39680, [(None, 1, 90), (None, 64), (None, 64)], 'tanh']
['Dense', (None, 90), 5850, 'softmax']
['TensorFlowOpLayer', [(None,)], 0]
['TensorFlowOpLayer', [(None, 90)], 0]
['RepeatVector', (None, 1, 90), 0, 1]
['TensorFlowOpLayer', [(None,)], 0]

Can someone please explain what I’m doing wrong here?

Thanks and good luck to all of you on your assignements.
Karim

2

Hi Karim,

Replace the input ‘out’ with ‘x’ in RepeatVector(1)(out). They were asking you to place the output of one hot encoding.

Cheers

3

Hello Jaya,

Thank you so much for that. Small details like that slip by without a second pair of eyes.

Cheers,
Karim

4

@karim1995
I am glad you fixed the mistake.

Please edit your post to remove the code - to respect the course Honor Code.