Moving average already computed for: generator_loss/content_loss/Mean:0 with runGan.py 4

[Alessia Paccagnella]

If I try runGan.py 4
I get this error:

File "/.local/lib64/python3.6/site-packages/tensorflow/python/training/moving_averages.py", line 388, in apply
    raise ValueError("Moving average already computed for: %s" % var.name)
ValueError: Moving average already computed for: generator_loss/content_loss/Mean:0

I saw this issue #80 but I am not using the Docker so I don't know how to solve this.
Anybody else that had this issue?

[Anders]

Try restarting the training with the following in runGan.py:

cmd1 += [ # based on a pre-trained FRVSR model. Here we want to train a new adversarial training "--pre_trained_model", "--checkpoint", old_model, ]

where old_model points to the last saved checkpoint.

[yunxinjun]

I'm having this problem too, have you solved it please?