3D photographic inpainting from a single source image

Re:3D photographic inpainting from a single source image by frfl on Friday April 10, 2020 @07:09PM (#22838303)

Anyone with ML development experience know what changes are needed to make this work on a CPU without a CUDA GPU? Seems heavily coupled to CUDA.

[ Parent | on HN ]

Re:3D photographic inpainting from a single source image by johndough on Saturday April 11, 2020 @07:15AM (#22841068)

Here is a quick hack to make it work on CPU: https://github.com/983/3d-photo-inpainting

Maxed out at 4 GB RAM for 256x144 images for me.

PyTorch CPU installation instructions: https://pytorch.org/get-started/previous-versions/

OpenCV should work without CUDA. If not, build from source and consider `WITH_CUDA` flag.

[ Parent | on HN ]

Re:3D photographic inpainting from a single source image by fxtentacle on Saturday April 11, 2020 @03:56AM (#22840302)

Port it from Torch to TensorFlow framework, export the graph to tflite, compile with xla&aot and you end up with a c++ library running on CP.

[ Parent | on HN ]

Re:3D photographic inpainting from a single source image by rayuela on Friday April 10, 2020 @09:04PM (#22838930)

You could translate this to a non-CUDA GPU, such as a mobile GPU, but even that would require a bit of effort to be able to condense it such that is wasn't a total lag fest. Executing this on CPU seems damn near impossible from a usability standpoint given the large matrix multiplication involved. You really need the parallel capabilities of a GPU.

[ Parent | on HN ]

Re:3D photographic inpainting from a single source image by nestorD on Saturday April 11, 2020 @04:10AM (#22840361)

It relies on torch and openCV: - I have never tried running openCV explicitely on CPU but I believe it is doable. - It is trivial to run torch on CPU instead of GPU (just comment the line that sends the code to the GPU).

[ Parent | on HN ]