- 22 Nov, 2021 1 commit
-
-
Joao Gomes authored
* change to stable sort in nms implementations
-
- 26 Aug, 2021 2 commits
-
-
Vasilis Vryniotis authored
-
Vasilis Vryniotis authored
[FBcode->GH] Port quantize_val and dequantize_val into torchvision to avoid at::native and android xplat incompatibility (#4311) Summary: This diff ports `quantize_val` and `dequantize_val` from at::native to torchvision because native kernels are incompatible with android xplat builds (see D30234056). This should only be temporary until we find a way to move those functions out of at::native, or until the at::native / android incompatibility disappears. Reviewed By: fmassa Differential Revision: D30393619 fbshipit-source-id: 18b7b1b349ad9a24088a120e23da7535f7fa7ddc Co-authored-by:Nicolas Hug <nicolashug@fb.com>
-
- 24 May, 2021 1 commit
-
-
Nicolas Hug authored
-
- 13 Apr, 2021 1 commit
-
-
Francisco Massa authored
-
- 08 Apr, 2021 1 commit
-
-
Nicolas Hug authored
* WIP * clang * docs * extracted out common utils * Use better quantization function and pass tensors as parameters * proper dequantization * Some tests * Dequantization optimization, seems to gain a few ms * clang-format * again * more correct test. Had to remove optimization although it almost works * Also test aligned=True * remove useless part * more docs and comments * Put back optimization with more robust test * Added check for index upper bound * avoid possible overflow * Move common function into common.h * oops * scale=1,zero_point=0 makes more sense * Force batch size of 1 to prevent any indexingbug * format * format again * updated docstring * put back description comment for pre_calc_bilinear_interpolate * revert most changes to docstring as it's taken care of in another PR
-
- 30 Mar, 2021 1 commit
-
-
Nicolas Hug authored
* Add quantized version of nms * Added tests * Compute areas only once * remove calls to dequantize_val * fix return type for empty tensor * flake8 * remove use of scale as it gets cancelled out * simpler int convertion in tests * explicitly set ovr to double * add tests for more values of scale and zero_point * comment about underflow * remove unnecessary accessor * properly convert to float for division * Add comments about underflow * explicitely cast coordinates to float to allow vectorization * clang * clang again * hopefully OK now
-