IntenseWebs/openvino
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

[GNA] fix 4d batch size eltwise issue (#3127)

Browse Source
This commit is contained in:
Anna Alberska
2020-11-13 17:28:02 +01:00
committed by GitHub
parent c860f5fa7d
commit d87fdbe89b
2 changed files with 4 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
inference-engine/tests/functional/plugin/gna/shared_tests_instances/single_layer_tests/fake_quantize.cpp
View File

@@ -41,8 +41,7 @@ const std::vector<std::pair<std::string, ConfigType>> gnaQuantModes = {
// {"sw_exact_i8", configInt8},
};
// TODO: uncomment once fixed proper 4d import for GNA-plugin issue: 38806
const std::vector<std::vector<size_t>> inputShapes = {{1, 1, 1, 1}, /*{3, 10, 5, 6}*/};
const std::vector<std::vector<size_t>> inputShapes = {{1, 1, 1, 1}, {3, 10, 5, 6}};
const std::vector<std::vector<size_t>> constShapes = {{1}};
const std::vector<size_t> levels = {16, 255, 256};