Open AndrzejBandurski opened 5 years ago
Hi,is this problem solved? I also encountered the same situation.
replace
for step, (lr_patchs, hr_patchs) in train_ds:
with
for step, (lr_patchs, hr_patchs) in enumerate(train_ds):
I have corrected this already by myself, thank you very much for conforming !
new Issue though... line 128: RuntimeError: GradientTape.gradient can only be called once on non-persistent tapes
@AndrzejBandurski set persistent=True
https://github.com/tensorlayer/srgan/blob/16c2e3f3d478a59675260d7d30389db110d0e0e3/train.py#L113
Traceback (most recent call last): File "train.py", line 356, in
File "train.py", line 113, in train
ValueError: too many values to unpack (expected 2)