yolov5_obb
yolov5_obb copied to clipboard
yolov5 + csl_label.(Oriented Object Detection)(Rotation Detection)(Rotated BBox)基于yolov5的旋转目标检测
(pytorch_cpu_12) C:\Users\7758\Desktop\SZQ\Tuxaingshibie\yolov5_obb-master\utils\nms_rotated>python setup.py develop running develop running egg_info writing nms_rotated.egg-info\PKG-INFO writing dependency_links to nms_rotated.egg-info\dependency_links.txt writing top-level names to nms_rotated.egg-info\top_level.txt reading manifest file 'nms_rotated.egg-info\SOURCES.txt' writing manifest file 'nms_rotated.egg-info\SOURCES.txt' running build_ext building...
我在anaconda中创建了一个环境,并按install.md中的流程执行了前面的所有步骤,但是在执行‘python setup.py develop #or "pip install -v -e ."’这一步时报了这样的错误 虽然‘install.md’之后的语句运行也显示“完成代码生成” 但是运行train.py文件时就会出现这个错误 我看issue中有人也有这种错误,运行‘python setup.py develop #or "pip install -v -e ."’这一步就好了,但是我运行这一步会报如上的错误,求解答
用的win10系统,这个编译的文件一直通不过,cuda和cudnn安装了好多遍,好多教程都试了,发现,下载cpu版本的ptyorch可以正常编译,下载gpu版本的就出问题11.2,11.3,11.4版本的cuda我都安过,啊三天了好累。
硬件配置
大佬你好,我看你的知乎训练时设置batch_size=75,那得多大的显存啊,我训练是设置的batch_size=4结果模型收敛的很慢。
你好博主,在我运行detect.py加运行参数后,遇见了如下错误   在没加这个参数前运行时ok的
Hi @hukaixuan19970627 , I want to run val.py with --task test for calculating precision, recall in test dataset. But I have this issue: ``` test: Scanning 'test/labelTxt' images and labels...102...
Logging results to runs\train\exp35 Starting training for 300 epochs... Epoch gpu_mem box obj cls theta labels img_size 0/299 8.5G 0.1637 0.03505 0 10.14 33 1024: 100%|██████████| 39/39 [00:33