Week 3 assignment 1 [w3.] Exercice 2

Course Q&A Deep Learning Specialization Sequence Models
1

Hi,

I’ve completed both the first and second exercices and passed through all tests. whoever when I look at

summary(model)

[[‘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’],
[‘Dense’, (None, 11), 715, ‘softmax’],
[‘Dense’, (None, 11), 715, ‘softmax’],
[‘Dense’, (None, 11), 715, ‘softmax’],
[‘Dense’, (None, 11), 715, ‘softmax’],
[‘Dense’, (None, 11), 715, ‘softmax’],
[‘Dense’, (None, 11), 715, ‘softmax’],
[‘Dense’, (None, 11), 715, ‘softmax’],
[‘Dense’, (None, 11), 715, ‘softmax’],
[‘Dense’, (None, 11), 715, ‘softmax’]]

Also, I get a Total params= 59,395 and Trainable params= 59,395.
And when I run this cell

model.load_weights('models/model.h5')

I get the following error message:

ValueError Traceback (most recent call last)
in
----> 1 model.load_weights(‘models/model.h5’)

/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/training.py in load_weights(self, filepath, by_name, skip_mismatch, options)
2209 f, self.layers, skip_mismatch=skip_mismatch)
2210 else:
→ 2211 hdf5_format.load_weights_from_hdf5_group(f, self.layers)
2212
2213 def _updated_config(self):

/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/saving/hdf5_format.py in load_weights_from_hdf5_group(f, layers)
684 ‘containing ’ + str(len(layer_names)) +
685 ’ layers into a model with ’ + str(len(filtered_layers)) +
→ 686 ’ layers.’)
687
688 # We batch weight value assignments in a single backend call

ValueError: You are trying to load a weight file containing 5 layers into a model with 14 layers.

If someone could look at this it would be great.
Thanks

2

You have most likely not passed the modelf test, which is the cell under where you define modelf. You also see the expected summary in the test here:

expected_summary = [['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'],
                         ['Dense', (None, 11), 715, 'softmax']]