Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Update TensorRT parser to fix accuracy issue in some opset11 models #5442

Merged
merged 1 commit into from
Oct 10, 2020
Merged

Update TensorRT parser to fix accuracy issue in some opset11 models #5442

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion cmake/external/onnx-tensorrt
Open in desktop
Submodule onnx-tensorrt updated 1 files
+46 −9 builtin_op_importers.cpp
2 changes: 1 addition & 1 deletion onnxruntime/core/providers/tensorrt/tensorrt_execution_provider.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1337,6 +1337,7 @@ common::Status TensorrtExecutionProvider::Provider_Compile(const std::vector<onn
}
return ORT_MAKE_STATUS(ONNXRUNTIME, FAIL, "TensorRT EP execution context enqueue failed.");
}
cudaDeviceSynchronize();

// Cast INT64 input to INT32 because TensorRT doesn't fully support INT64
for (int i = 0, end = output_binding_names.size(); i < end; ++i) {
Expand All @@ -1355,7 +1356,6 @@ common::Status TensorrtExecutionProvider::Provider_Compile(const std::vector<onn
}
}

cudaDeviceSynchronize();
for (const auto& binding_index : binding_buffers_to_freeup) {
cudaFree(buffers[binding_index]);
}
Expand Down