Open Nicoladao opened 3 years ago
I have meet the same error
I got the same issue. my logs:
[03/10/2021-01:00:59] [E] [TRT] (Unnamed Layer* 14) [Convolution]: kernel weights has count 0 but 12800 was expected
[03/10/2021-01:00:59] [E] [TRT] (Unnamed Layer* 14) [Convolution]: count of 0 weights in kernel, but kernel dimensions (1,1) with 160 input channels, 80 output channels and 1 groups were specified. Expected Weights count is 160 * 1*1 * 80 / 1 = 12800
[03/10/2021-01:00:59] [E] [TRT] Parameter check failed at: ../builder/Network.cpp::addScale::482, condition: shift.count > 0 ? (shift.values != nullptr) : (shift.values == nullptr)
yolov5: /opt/nvidia/deepstream/tools/Yolov5-in-Deepstream-5.0/common.hpp:190: nvinfer1::IScaleLayer* addBatchNorm2d(nvinfer1::INetworkDefinition*, std::map<std::__cxx11::basic_string<char>, nvinfer1::Weights>&, nvinfer1::ITensor&, std::__cxx11::string, float): Assertion `scale_1' failed.
Aborted
same here
same issue .maybe yolov5 version should use V3.0 or V3.1
Loading weights: ../yolov5s.wts [02/04/2021-12:51:45] [E] [TRT] (Unnamed Layer 14) [Convolution]: second input must be provided if kernel weights are empty. [02/04/2021-12:51:45] [E] [TRT] (Unnamed Layer 14) [Convolution]: kernel weights has count 0 but 2048 was expected [02/04/2021-12:51:45] [E] [TRT] (Unnamed Layer 14) [Convolution]: count of 0 weights in kernel, but kernel dimensions (1,1) with 64 input channels, 32 output channels and 1 groups were specified. Expected Weights count is 64 11 32 / 1 = 2048 [02/04/2021-12:51:45] [E] [TRT] Parameter check failed at: ../builder/Network.cpp::addScale::434, condition: shift.count > 0 ? (shift.values != nullptr) : (shift.values == nullptr) yolov5: /home/yupei/视频/code/pytorch/deepstream_yolov5/Yolov5-in-Deepstream-5.0/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.
i can kown how to fix it!thx