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.

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

Assertion `scale_1' failed #22

Closed
hoangnt2601 opened this issue Jan 8, 2021 · 3 comments
Closed

Assertion `scale_1' failed #22

hoangnt2601 opened this issue Jan 8, 2021 · 3 comments

Comments

@hoangnt2601
Copy link

[E] [TRT] Parameter check failed at: ../builder/Network.cpp::addScale::434, condition: shift.count > 0 ? (shift.values != nullptr) : (shift.values == nullptr)
0
common.hpp:190: nvinfer1::IScaleLayer* addBatchNorm2d(nvinfer1::INetworkDefinition*, std::map<std::__cxx11::basic_string, nvinfer1::Weights>&, nvinfer1::ITensor&, std::__cxx11::string, float): Assertion `scale_1' failed.

@marcoslucianops
Copy link
Owner

Which model are you using?

@hoangnt2601
Copy link
Author

hoangnt2601 commented Jan 9, 2021

Which model are you using?

I use yolov5s model, I fixed it by passing yolov5 to tag 3.1 and tensorrtx project with commit '6d0f5cb'. But continue with the error "Assertion failed: Unsupported SM." I use RTX 3000 architecture, CUDA 10.2, cudnn 7.6, tensorrt 7.0
Which tenssort version does the version use?

@hoangnt2601
Copy link
Author

I fixed it by comment the variable USE_FP16 in yolov5.cpp and the "Unsupported SM" error because I am using gpu RTX3000 and it doesn't match with tensorrt 7.0.
NVIDIA/TensorRT#975

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants