how to load weights back into the tensorflow.

[Pratyush852]

No description provided.

[Pratyush852]

Use the pre-trained model

trained_model = CFModel(max_userid, max_movieid, K_FACTORS)

Load weights

trained_model.load_weights('weights.h5')

It is showing error

AttributeError Traceback (most recent call last)
in
4 trained_model = CFModel(max_userid, max_movieid, K_FACTORS)
5 # Load weights
----> 6 trained_model.load_weights('weights.h5')

2 frames
/usr/local/lib/python3.7/dist-packages/keras/engine/topology.py in (.0)
2746 flattened_layers = filtered_layers
2747
-> 2748 layer_names = [n.decode('utf8') for n in f.attrs['layer_names']]
2749 filtered_layer_names = []
2750 for name in layer_names:

AttributeError: 'str' object has no attribute 'decode'

[HripsimeS]

trained_model = CFModel(max_userid, max_movieid, K_FACTORS)
trained_model([np.array([[1]]), np.array([[1]])]) # Pass the inputs as a list
trained_model.load_weights('weights.h5')