Giters
hpc203
/
yolov5-dnn-cpp-python
用opencv的dnn模块做yolov5目标检测,包含C++和Python两个版本的程序
Geek Repo:
Geek Repo
Github PK Tool:
Github PK Tool
Stargazers:
500
Watchers:
6
Issues:
28
Forks:
122
hpc203/yolov5-dnn-cpp-python Issues
请问这个 c++ demo入和运行
Updated
10 months ago
Comments count
1
error. can you help me plz
Updated
a year ago
Comments count
1
File "convert_onnx.py", line 57, in <module> del utl_param['24.anchor_grid'] KeyError: '24.anchor_grid'
Updated
a year ago
Comments count
3
error: (-215:Assertion failed) model_proto.has_graph() in function 'populateNet'
Updated
2 years ago
Comments count
3
C++版本检测不到物体
Updated
2 years ago
Comments count
8
python 如何用opencv部署?
Updated
2 years ago
Comments count
1
模型是yolov5哪个版本跑出的 ultralytics / yolov5
Updated
2 years ago
Comments count
2
cpp 加载模型失败 Required argument "starts" not found into dictionary in function 'get' 求助!!!!
Updated
2 years ago
Comments count
2
导出ONNX的问题
Updated
2 years ago
Comments count
2
Does it work for own pretrained weights?
Updated
3 years ago
Comments count
1
undefined symbol: _ZN2cv3dnn14dnn4_v202009083Net7forwardERKNS_12
Updated
3 years ago
Comments count
1
cv2.error:
Updated
3 years ago
Comments count
1
run c++ main_yolo.cpp error
Closed
3 years ago
Comments count
4
terminate called after throwing an instance of 'cv::Exception'
Updated
3 years ago
标注的confidences全都太高,接近于1
Updated
3 years ago
Comments count
3
推理的置信度过高
Updated
3 years ago
Comments count
1
如何使用GPU加速?
Updated
3 years ago
Comments count
2
为什么需要原始anchors?
Updated
3 years ago
Comments count
1
Encoding Outputs to Bounding boxes
Updated
3 years ago
how to get _param.pth?
Updated
3 years ago
Comments count
6
OpenCV开了cuda加速,但是没有提升,会是什么原因呢?
Updated
3 years ago
您导出的yolov5s.onnx的推理结果和原版python差别很大
Closed
3 years ago
Error and optimization
Updated
3 years ago
Comments count
1
TracerWarning: Converting a tensor to a Python integer might cause the trace to be incorrect.
Closed
3 years ago
Comments count
10
support yolov5-fpn.py?
Updated
3 years ago
run convert_onnx.py , I get the warning TracerWarning: Converting a tensor to a Python integer might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs! route = F.interpolate(xRt3, size=(int(xRt3.shape[2] * 2), int(xRt3.shape[3] * 2)), mode='nearest')
Updated
3 years ago
Comments count
1
How to run?
Updated
3 years ago
Comments count
4