Incorrect image shape when reading from TFRecordDataset

[genforce]

Incorrect image shape when reading from TFRecordDataset

[yuval-alaluf]

It seems like changing the get_train_data function in training_loop_encoder to utilize the TFRecordDataset class in training/datasets solves this issue.

In any case, is there any chance you can look into this issue? If it helps I am using the docker from StyleGAN-ADA which can be found here: https://github.com/NVlabs/stylegan2-ada

Could the fact that they use tensorflow 1.14 be causing this issue?

[ShenYujun]

Since the training of encoder only focuses on the largest resolution, it does not rely on the progressive training strategy. Therefore, you should specify a particular file (e.g., xxxx-r09.tfrecords for 512x512 resolution), instead of the dataset folder, for both the training_data and the test_data arguments.

[yuval-alaluf]

Thanks a lot for the clarification!
I completely missed the fact that the different .tfrecords files correspond to different resolutions! Now everything works as expected.
Thanks again!