OSSForks/pytorch
1
0
Fork 0
mirror of https://github.com/zebrajr/pytorch.git synced 2025-12-07 12:21:27 +01:00
Code Issues Actions 37 Packages Projects Releases Wiki Activity
48ea440b15
pytorch/test/onnx
History
BowenBao 8d31706b9e [ONNX] Support restricted quantized range for activation. 
PyTorch restricts activations to be in the range (0, 127).
In ONNX, the supported ranges are (0, 255) and (-128, 127),
respectfully, uint8 and int8. This PR extends support for range
(0, 127), by adding additional clipping when detected.

Pull Request resolved: https://github.com/pytorch/pytorch/pull/76055

Approved by: https://github.com/garymm
2022-04-25 01:17:21 +00:00
..
assets [ONNX] add test images to repo (#63717) 2021-08-23 07:43:21 -07:00
expect Remove F.pad python implementation 2022-04-23 00:13:20 +00:00
model_defs Add lint to ensure all test files have headers with ownership info (#66826) 2021-11-03 18:21:49 -07:00
autograd_helper.py [ONNX] Add module name as PythonOp attribute (#67193) (#73281) 2022-03-09 14:26:18 +00:00
debug_embed_params.py [ONNX] use consistent quoting for string literals (#57757) (#58695) 2021-05-27 12:06:42 -07:00
export_onnx_tests_filter.py deprecate device getter from torch.testing namespace (#63844) 2021-09-29 02:40:52 -07:00
export_onnx_tests_generator.py [ONNX] use consistent quoting for string literals (#57757) (#58695) 2021-05-27 12:06:42 -07:00
pytorch_helper.py [ONNX] use consistent quoting for string literals (#57757) (#58695) 2021-05-27 12:06:42 -07:00
test_caffe2_common.py Set test owners for onnx tests (#66860) 2021-10-27 12:50:45 -07:00
test_custom_ops.py Implement Tanh Gelu Approximation (#61439) 2022-02-14 03:40:32 +00:00
test_models_onnxruntime.py [ONNX] Resolve attribute error in CI (#72350) 2022-02-04 20:22:24 +00:00
test_models.py [ONNX] update default opset_version to 13 (#73898) 2022-04-07 00:02:31 +00:00
test_onnx_common.py Set test owners for onnx tests (#66860) 2021-10-27 12:50:45 -07:00
test_onnx_export.py Emit ATen ops when symbolics raise + minor fixes 2022-04-23 21:24:25 +00:00
test_onnx_opset.py [ONNX] Add Concat to Scalar type analysis JIT pass (#69227) (#69548) 2022-02-11 22:05:15 +00:00
test_operators.py Update symbolics policy to emit aten::ATen for Caffe2 build only 2022-04-19 15:57:54 +00:00
test_pytorch_common.py [ONNX] update default opset_version to 13 (#73898) 2022-04-07 00:02:31 +00:00
test_pytorch_helper.py Set test owners for onnx tests (#66860) 2021-10-27 12:50:45 -07:00
test_pytorch_jit_onnx.py [ONNX] Initial test suite for Torch IR to ONNX 2022-04-11 19:28:28 +00:00
test_pytorch_onnx_caffe2_quantized.py [ONNX] update default opset_version to 13 (#73898) 2022-04-07 00:02:31 +00:00
test_pytorch_onnx_caffe2.py [ONNX] update default opset_version to 13 (#73898) 2022-04-07 00:02:31 +00:00
test_pytorch_onnx_onnxruntime_cuda.py [ONNX] Fix error comparing tensors on different devices in DeduplicateInitializers 2022-04-07 00:20:06 +00:00
test_pytorch_onnx_onnxruntime.py [ONNX] Support restricted quantized range for activation. 2022-04-25 01:17:21 +00:00
test_pytorch_onnx_shape_inference.py [ONNX] Remove redundant warning for reshape 2022-03-14 20:58:26 +00:00
test_utility_funs.py [onnx] Add support for torch.cross and torch.cdist 2022-04-21 20:35:25 +00:00
test_verify.py Set test owners for onnx tests (#66860) 2021-10-27 12:50:45 -07:00
verify.py [ONNX] Remove the argument example_outpus of export() method entirely. (#67082) (#67809) 2021-11-12 17:06:26 -08:00