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

[IE Common][WA] Skipped const folding for Convolution layer (#1002)

Browse Source
This commit is contained in:
Gorokhov Dmitriy
2020-06-19 01:25:20 +03:00
committed by GitHub
parent 2f3d5f68cd
commit 3bbe88e659
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
inference-engine/src/legacy_api/src/graph_transformer.cpp
View File

@@ -232,7 +232,8 @@ std::vector<CNNLayerPtr> ConstTransformer::foldConstSubgraphsInternal(const std:
static std::vector<std::string> skipConstInfer = {
"FakeQuantize",
"Quantize",
"CumSum" // Const inference function for CumSum is not implemented!
"CumSum", // Const inference function for CumSum is not implemented
"Convolution" // Const inference function for Convolution is not implemented
};
const std::map<std::string, bool> ConstTransformer::getConstLayers(const std::vector<CNNLayerPtr>& sortedLayers) {