AttributeError: 'Tensor' object has no attribute 'numpy' in custom loss function (Tensorflow 2.1.0)

user_9223749 0
Viewed 1540

I want to train a model with a custom loss function, in order to do that, I need to convert the tensor to numpy array inside the method below:

def median_loss_estimation(y_true, y_predicted):
    a = y_predicted.numpy()

but I have this error:

AttributeError: 'Tensor' object has no attribute 'numpy'

Why? How can I convert the tensor to a numpy array?

loss loss-function tensorflow numpy python
2 Answers

The answer is: put run_eagerly=True in model.compile!

user_92237490

You're doing the right thing, only Tensorflow 2.1 is currently broken in that aspect. This would normally happen if you run the code without eager mode enabled. However, Tensorflow 2 by default runs in eager mode... or at least it should. The issue is tracked here.

There are at least two solutions to this:

  1. Install the latest nightly build.
  2. Set model.run_eagerly = True.
user_13979460
Related