Casting X_batch to float32

[DavidLandup0]

Casting X_batch to float32 to avoid an InvalidArgumentError, caused by X_batch being of type uint8 instead of float32 in the tf.concat() operation, which should result in X_fake_and_real.

InvalidArgumentError: cannot compute ConcatV2 as input #1(zero-based) was expected to be a float tensor but is a uint8 tensor [Op:ConcatV2] name: concat

[review-notebook-app[bot]]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB

[ageron]

Hi @DavidLandup0 , Thanks for the PR. However, I cannot reproduce the error you were getting. I just tried running the notebook on Colab (which currently uses TensorFlow 2.6.0) and the code worked fine, I didn't get any error (or even any warning) in this part of the notebook:

Can you reproduce the error? If so, could you please indicate which version of TF you are using? And perhaps provide a minimum code example that I can use to reproduce the problem?

Thanks again.