Error in enhancing this image: CUDA out of memory.

[idanka]

Hi!
Step 3
Restoring test1.jpg
################ Error in enhancing this image: CUDA out of memory. Tried to allocate 758.00 MiB (GPU 0; 3.81 GiB total capacity; 2.10 GiB already allocated; 46.31 MiB free; 2.33 GiB reserved in total by PyTorch)
################ continue...
Step 4
error
missing image, Step4_FinalResults map empty

Im use Ubuntu 20.04
GeForce GTX 1650 / 4GB
Ubuntu default install: cuda 10.1 and libcudnn8_8.0.4.30-1+cuda10.1_amd64

[csxmli2016]

Hi!
Step 3
Restoring test1.jpg
################ Error in enhancing this image: CUDA out of memory. Tried to allocate 758.00 MiB (GPU 0; 3.81 GiB total capacity; 2.10 GiB already allocated; 46.31 MiB free; 2.33 GiB reserved in total by PyTorch)
################ continue...
Step 4
error
missing image, Step4_FinalResults map empty

Im use Ubuntu 20.04
GeForce GTX 1650 / 4GB
Ubuntu default install: cuda 10.1 and libcudnn8_8.0.4.30-1+cuda10.1_amd64

Hi, this is caused by the limited cuda memory. You can use cpu instead of gpu.
Besides, you can also use the colab (pls refer to #17 (comment))

[alessiapacca]

I have a GEFORCE RTX 2070, how is it possible that I get the error CUDA out of memory? Which GPUs are supported?

[ivellios1988]

Exactly same problem here. My GPU is Nvidia GeForce 940MX, system is Windows 10 x64

[mowshon]

@csxmli2016 what kind of RTX do you have?
I have RTX 2070 Super 8GB and I got this error:

Error in enhancing this image: CUDA out of memory. Tried to allocate 758.00 MiB
(GPU 0; 7.79 GiB total capacity; 5.26 GiB already allocated;
483.88 MiB free; 5.73 GiB reserved in total by PyTorch)