mirror/opencv
1
0
Fork 0
mirror of https://github.com/opencv/opencv.git synced 2024-11-24 19:20:28 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Merge pull request #26050 from asmorkalov:as/supress_qdq_tests

Browse Source 
Supress more ONNX conformance test cases for quant-dequant with CUDA.
This commit is contained in:
Alexander Smorkalov 2024-08-20 17:46:58 +03:00 committed by GitHub
commit eee383fde8
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 8 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
modules/dnn/test/test_onnx_conformance_layer_filter__cuda_denylist.inl.hpp
View File

@ -91,3 +91,7 @@
"test_scatternd_min",
"test_scatternd_multiply",
"test_nllloss_NCd1d2d3d4d5_none_no_weight_expanded", // crash: https://github.com/opencv/opencv/issues/25471
"test_dequantizelinear_blocked", // Issue https://github.com/opencv/opencv/issues/25999
"test_quantizelinear", // Issue https://github.com/opencv/opencv/issues/25999
"test_quantizelinear_axis", // Issue https://github.com/opencv/opencv/issues/25999
"test_quantizelinear_blocked", // Issue https://github.com/opencv/opencv/issues/25999

4
modules/dnn/test/test_onnx_conformance_layer_filter__cuda_fp16_denylist.inl.hpp
View File

@ -19,3 +19,7 @@
"test_softmax_large_number", // fp16 accuracy issue
"test_softmax_large_number_expanded", // fp16 accuracy issue
"test_tan", // fp16 accuracy issue
"test_dequantizelinear_blocked", // Issue https://github.com/opencv/opencv/issues/25999
"test_quantizelinear", // Issue https://github.com/opencv/opencv/issues/25999
"test_quantizelinear_axis", // Issue https://github.com/opencv/opencv/issues/25999
"test_quantizelinear_blocked", // Issue https://github.com/opencv/opencv/issues/25999