Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

你好,我尝试复现您的yolov5xP2CBAM-TPH-BiFPN-SPP.yaml模型文件的结果,但是最终精度和您复现的效果相差比较大。 #84

Open
wong1998 opened this issue May 31, 2022 · 1 comment

Comments

@wong1998
Copy link

wong1998 commented May 31, 2022

以下是我的训练命令行:
nohup python train.py --cfg yolov5xP2CBAM-TPH-BiFPN-SPP.yaml --weights 'weights/yolov5x.pt' --img 640 --data myVisDrone.yaml --hyp data/hyps/hyp.visdrone.yaml --epochs 81 --device 0,1 --batch-size 2 --name '5x_tph_ori_640_526' &

然后我训练了81轮
我的metrics/mAP_0.5:0.95只有0.024101
以下是我的train_batch.jpg
image

这是我的数据集文件

Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]

#path: ../datasets/VisDrone # dataset root dir
#path: /home/ff/WangZF/datasets/visdrone # dataset root dir
train: /home/ff/WangZF/datasets/visdrone/YOLOFormat/train/images # train images (relative to 'path') 6471 images
val: /home/ff/WangZF/datasets/visdrone/YOLOFormat/val/images # val images (relative to 'path') 548 images
test: /home/ff/WangZF/datasets/visdrone/YOLOFormat/val/images # test images (optional) 1610 images

Classes

nc: 10 # number of classes
names: [ 'pedestrian', 'people', 'bicycle', 'car', 'van', 'truck', 'tricycle', 'awning-tricycle', 'bus', 'motor' ]
我不知道是哪里出错了

@dataconc
Copy link

预训练权重在哪??我没看到,如果那官方yolov5的权重那只有主干能用,那效果肯定差

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants
@wong1998 @dataconc and others