在小目标检测上面的效果不好

hukaixuan19970627 / yolov5_obb

yolov5 + csl_label.(Oriented Object Detection)（Rotation Detection）（Rotated BBox）基于yolov5的旋转目标检测

GNU General Public License v3.0

1.82k stars 425 forks source link

在小目标检测上面的效果不好 #554

Open Tigores opened 1 year ago

Tigores commented 1 year ago

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 commented 1 year ago

lr0: 0.001 lrf: 0.2 momentum: 0.937 weight_decay: 0.0005 warmup_epochs: 3.0 warmup_momentum: 0.8 warmup_bias_lr: 0.1 box: 0.005 cls: 0.5 cls_pw: 1.0 theta: 0.5 theta_pw: 1.0 obj: 1.0 obj_pw: 1.0 iou_t: 0.2 anchor_t: 4.0 fl_gamma: 0.0 hsv_h: 0.015 hsv_s: 0.7 hsv_v: 0.4 degrees: 180.0 translate: 0.1 scale: 0.0 shear: 0.0 perspective: 0.0 flipud: 0.0 fliplr: 0.5 mosaic: 0.0 mixup: 0.0 copy_paste: 0.0 cls_theta: 180 csl_radius: 2.0

Tigores commented 1 year ago

weights: weights\yolov5s.pt cfg: '' data: data\my_data.yaml hyp: data\hyps\obb\hyp.finetune_dota.yaml epochs: 1600 batch_size: 1 imgsz: 2560 rect: false resume: false nosave: false noval: false noautoanchor: false evolve: null bucket: '' cache: true image_weights: false device: '0' multi_scale: false single_cls: false adam: true sync_bn: false workers: 8 project: runs\train name: exp exist_ok: false quad: false linear_lr: false label_smoothing: 0.0 patience: 1400 freeze: