yolov5_tensorrt icon indicating copy to clipboard operation
yolov5_tensorrt copied to clipboard

This is the implementation that supports yolov5s, yolov5m, yolov5l, yolov5x.

Results 6 yolov5_tensorrt issues
Sort by recently updated
recently updated
newest added

Bumps [numpy](https://github.com/numpy/numpy) from 1.17.3 to 1.22.0. Release notes Sourced from numpy's releases. v1.22.0 NumPy 1.22.0 Release Notes NumPy 1.22.0 is a big release featuring the work of 153 contributors spread...

dependencies

我使用最新的yolov5m.pt转换成wts格式后,可以成功编译,但是无法生成引擎 出现了如下错误: ``` Loading weights: ./yolov5m.wts yolov5-m2: ../yolov5-m2/common.hpp:128:std::map loadWeights(std::__cxx11::string): 假设 ‘input.is_open() && "Unable to load weight file."’ 失败。 程序异常结束。 ``` 我之前使用wangxinyu的yolov5s可以成功生成引擎,应该不是环境问题吧? 我对比了我们的运行环境,是一致的。 感谢您的帮助

[ 25%] Building NVCC (Device) object CMakeFiles/yololayer.dir/yololayer_generated_yololayer.cu.o /home/yolov5_tensorrt/yolov5s/yololayer.h(103): warning: function "nvinfer1::IPluginV2Ext::configurePlugin(const nvinfer1::Dims *, int, const nvinfer1::Dims *, int, const nvinfer1::DataType *, const nvinfer1::DataType *, const __nv_bool *, const __nv_bool *,...

![image](https://user-images.githubusercontent.com/47818312/89142697-b9e8f580-d57a-11ea-9664-850f10764406.png)

我使用yolov5 v1.0训练了yolov5s模型,然后进行序列化,得到以下信息: ``` Loading weights: ../yolov5s.wts [07/31/2020-11:37:13] [E] [TRT] (Unnamed Layer* 173) [Convolution]: kernel weights has count 2304 but 32640 was expected [07/31/2020-11:37:13] [E] [TRT] (Unnamed Layer* 173) [Convolution]: count...

![sendpix0](https://user-images.githubusercontent.com/49978186/89095365-bb41e300-d3ff-11ea-8c93-49a198d32698.jpg) 我用的tensorrt版本是7.0.0.11,opencv的版本是3.4.10