yolov5_obb

yolov5_obb copied to clipboard

install yolov5_obb error

5

Hi, anyone can share how to install this repo correctly. I got a problem when running setup.py as follow : ``` running develop C:\Users\Owner\anaconda3\envs\obb\lib\site-packages\setuptools\command\easy_install.py:147: EasyInstallDeprecationWarning: easy_install command is deprecated. Use...

ramdhan1989

RuntimeError: The size of tensor a (3) must match the size of tensor b (4) at non-singleton dimension 0

1

Hey Hu, thanks for your great work . After I start run my own dataset training 【python train.py --weights 'yolov5s.pt' --cfg models/yolov5s.yaml --data data/customer.yaml --hyp data/hyps/obb/hyp.finetune_dota.yaml --epochs 350 --batch-size 8...

NefarianZ

yolov5_obb no result on custom data after training

5

Hello, i trained the Yolo obb on custom data on colab but i did not get any predictions. I used 20 images for train/ 6 for val/ 4 for test...

alialoulou

UnboundLocalError: local variable 'rbox' referenced before assignment

1

在使用自己数据集时报错： UnboundLocalError: local variable 'rbox' referenced before assignment 但是在使用SSDD数据集的时候好好的，难道是数据集的问题？数据集的问题为啥报这个错啊

V-smart2019

weiyaokun

请问opt.yaml文件在哪 ？ 是配置参数列表？

weiyaokun

在小目标检测上面的效果不好

12

同样的imgsz（1280 x 1280）在yolov5上训练效果很好，但是在这个上面效果一直很差（mAP最高只有0.3），没办法收敛，切分数据集后训练，效果变好了（mAP高于0.9）。尝试过调高image size 到2560，效果还是不好，想问一下这里切割和调高图片输入尺寸的效果应该是一样的吧，为什么原数据集调高训练尺寸不能达到很好的训练效果？

Tigores

No module named 'shapely'

weiyaokun

训练的时候报错：FileNotFoundError: [Errno 2] No such file or directory: 'dataset/train_rate1.0_split1024_gap200/labelTxt.cache'

1

借助[https://github.com/hukaixuan19970627/yolov5_obb/blob/master/docs/GetStart.md](url)，可以跑val.py，可以跑detect。但是在用自己数据进行训练的时候报如下的错误： cache_labels = dataset/train_rate1.0_split1024_gap200/labelTxt.cache,prefix=train: Traceback (most recent call last): File "/home/test/hdd2t/test/DL/yolov5_obb/utils/datasets.py", line 437, in __init__ cache, exists = np.load(cache_path, allow_pickle=True).item(), True # load dict File "/home/test/miniconda3/lib/python3.9/site-packages/numpy/lib/npyio.py", line 405, in load...

NOON47

Do you have any plans to develop yolov8_obb?

nhathoang0110