deep-image-prior
deep-image-prior copied to clipboard
Out of memory
RuntimeError: cuda runtime error (2) : out of memory at /opt/conda/conda-bld/pytorch_1512387374934/work/torch/lib/THC/generic/THCStorage.cu:58
After googling a bit it seems like my GPU does not have enough memory to run the examples? Would it be possible to get like a ballpark estimate on what kind of machine is required to run the notebooks?
We used 12GB GPU. You can try to reduce the number of filters in the network or image resolution for example, there is a chance it still works nicely after such changes.
It might be worth looking into the pytorch variable allocation, which can have a big impact on required GPU memory[1]. But I'm not really seeing any major issues in this code.