AttributeError: module 'tensorflow.python.ops' has no attribute 'convert_to_tensor_v2' about coral-ordinal HOT 5 CLOSED

Ok this is fixed - 64e2836

from coral-ordinal.

Hello,

Thanks for letting me know about this issue! It appears that changes in Tensorflow 2.3 break the package right now, so I've updated the colab notebook to run on TF 2.2 in the short term. I will leave this issue open until I fix the package for TF 2.3.

Appreciate it,
Chris

from coral-ordinal.

I actually fixed it by just changing the following line in loss.py to

y_pred = ops.convert_to_tensor_v2(y_pred)

to

y_pred = tf.convert_to_tensor(y_pred)

Hope this helps

from coral-ordinal.

Yep, I followed that such a change would fix it for TF 2.3, but does it also work in TF 2.2? That's the other check before making the change, otherwise it will be more of a pain to maintain TF 2.2 compatibility.

from coral-ordinal.

Sorry for the late reply

tf.convert_to_tensor()

does work in TF 2.2 cause its base is derived from TF 1.0, therefore i think you can make the change and close this issue

from coral-ordinal.