torchsort
torchsort copied to clipboard
Fast, differentiable sorting and ranking in PyTorch
Specifically, when I use python 3.9, it will report this error: ```python ImportError: /home/gyyang/anaconda3/lib/python3.9/site-packages/torchsort/isotonic_cpu.cpython-39-x86_64-linux-gnu.so: undefined symbol: _ZN3c105ErrorC2ENS_14SourceLocationESs ``` But Python 3.8 is not such an error.
Is there any way to sort a tensor by a given column? For example, soring by first column: ```py input_tensor = torch.tensor([ [1, 5], [30, 30], [6, 9], [80, -2]...
I wanted to try to improve/modify the torchsort code a little so I tried making a copy of the SoftSort class and the soft_sort function. Running some benchmarks I got...
Thanks a lot for this implementation. I was wondering how can I use the repo to reproduce the results on CIFAR as reported in the paper. As I understand, the...
A weighted soft_rank would be a great addition to have! It could be weighted by element index, by a weighting function, or by a vector of weights. My initial attempt...
I encountered a CUDA memory error when using torchsort.soft_rank during parallel training on the GPU. The error message is as follows: File "/home/xxx/anaconda3/envs/DL2/lib/python3.10/site-packages/torchsort/ops.py", line 121, in backward ).gather(1, inv_permutation) RuntimeError:...