detr(detection transformer)模型训练自己的数据集_detr打印出各项指标

目录

1.detr源码下载

 2. 编译配置

3. 编译报错问题 

4. 训练过程打印参数解读 

---

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%