too many values to unpack (expected 2)

tensorlayer / SRGAN

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network

https://github.com/tensorlayer/tensorlayerx

3.28k stars 809 forks source link

Open AndrzejBandurski opened 5 years ago

AndrzejBandurski commented 5 years ago

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)

yonghuixu commented 5 years ago

Hi,is this problem solved? I also encountered the same situation.

Fredy commented 5 years ago

replace

for step, (lr_patchs, hr_patchs) in train_ds:

with

for step, (lr_patchs, hr_patchs) in enumerate(train_ds):

AndrzejBandurski commented 5 years ago

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

zsdonghao commented 5 years ago

@AndrzejBandurski set persistent=True