目录
1.detr源码下载
GitHub - facebookresearch/detr: End-to-End Object Detection with Transformers
2. 编译配置
编译参数只需要传递数据集路径即可,数据集格式是coco数据集类型
数据集文件夹名字和文件名字在coco.py的build函数中写死了。
可以在build函数中自己修改数据集的文件名字,配置完成后可以成功编译了。
3. 编译报错问题
ImportError: cannot import name '_new_empty_tensor' from 'torchvision.ops
是pytorch版本问题,点击进去,把下面3行代码注释掉即可
4. 训练过程打印参数解读
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.129
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.420
Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.029
Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.322
Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.141
Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.014
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.064
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.246
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.249
Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.375
Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.268
Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.014
terminate called without an active exception
在COCO数据集评价指标中,所有的AP 默认为mAP,
area:表示目标检测的物体是大物体还是小物体,大小物体的划分依据,all表示所有物体
APsmall % AP for small objects: area < 32^2
APmedium % AP for medium objects: 32^2 < area < 96^2
APlarge % AP for large objects: area > 96^2
masDets=100:表示一张图中能检测到的最多的物体数量是100
上图中mAP50=42.0%,mAP50:0.95 = 12.9%