Error - "Cannot convert a symbolic Tensor to a numpy array" while running train.py

[quasayush]

Greetings Sir
Thank a lot for providing such a nice implementation. However, I was facing some issues while implementing the code.
First of all in new numpy version allow_pickle is False by default so I solved one of the error by using allow_pickle=True in np.load statements in batch_generator.py

However, while trying to run train.py I am getting an error "NotImplementedError: Cannot convert a symbolic Tensor (model/rnn_1/while/rnn/rnn_model/window/add_1:0) to a numpy array."

This is same error I am getting while trying to use pretrained model

I am using Tensorflow 1.15.2 and numpy 1.19.5 and running on Google Colab

[pcsingh]

Hi @quasayush
Replace the np.square with tf.math.square and it will solve the issue. It worked for me.

[ShubhamKumar2802]

Hi @quasayush
Replace the np.square with tf.math.square and it will solve the issue. It worked for me.

Hey @pcsingh
I've made the changes you mentioned but the code still throws the same error for me.