kvfrans / clipdraw Goto Github PK

great work, can you please add a license file?

Hi @kvfrans,

I'm trying to make the generated results reproducible.
I added the following lines at the beginning of the Curve Optimizer section of your clipdraw.ipynb colab notebook.

random.seed(rand_seed)
torch.random.manual_seed(rand_seed)
np.random.seed(rand_seed)

However, it seems the code still generates very different images (the initial shapes look similar but then diverge) even given the same rand_seed
Do you have a clue? Thanks

CUDA Runtime Error: the provided PTX was compiled with an unsupported toolchain. The prompt appears at diffvg/scene.cpp:35，How to solve it?

when running this in google colab, it no longer works, giving an error when running the final program along the lines of
RuntimeError: radix_sort: failed on 1st step: cudaErrorInvalidDeviceFunction: invalid device function

I was able to solve this by changing Pre Installation to un-comment the !pip install torch==1.7.1... line, then editing the cmakelists.txt file (located at /content/diffvg/) to add
string(APPEND CMAKE_CUDA_FLAGS " -gencode arch=compute_70,code=sm_70")
after line 87, inside if(DIFFVG_CUDA) to force it to use the correct compute capability version for the gpu colab was using. the correct version can be found in the future here by finding the gpu listed by "inputs and notebook utilities"'s output, and replacing the 70 above (e.g. my colab instance had a tesla v100, which supports compute 7.0)

Optimal number of iterations for Pixel Optimization code available at the end of clipdraw.ipynb