Initialization issues and model.predict doesn't work about tensorflow_macos

[masasakai]

Thank you, @devnev39.
I tried your code on my M1 mac. It is works! I understand this issue that is graph executing or eagerly executing. I change to design eagerly executable models. Thank you again.

[masasakai]

I have a same issue. MacTF a1,a2,a3 are same. Please suggest the environment for MacTF, For example numpy etc.

[devnev39]

It is working fine for me.
Try this ->

1. If you have numpy 1.20 then try to install numpy 1.19.5
2. Check if tf.executing_eagerly() is set to True as it should be

[edavidk7]

@devnev39 I have the numpy version supplied with TensorFlow-macOS, which is 1.18.5. I will try your recommended code and the changing the eagerly execution parameter. Thank you.

[edavidk7]

@devnev39 It seems the activation function in the last layer is the issue here. I changed the code line by line to match yours and it only works once the activation function parameter is removed in the last layer.
Edit: linear activation for output layer works fine, issue seems to be only with sigmoid

[devnev39]

I guess there is some error in your side of code. I just did all the possibilities with sigmoid and relu and also setting from_logits=True (generally used in loss function when there is no activation at output layer) and they all executed the same code in the pictures without any error.