当使用DETR训练自己的数据集时，发现训练500个epoch以后，精度仍然非常低，mAP仍然非常低，只有5%

[mingheyuemankong]

问题确认 Search before asking

• [X] 我已经搜索过问题，但是没有找到解答。I have searched the question and found no related answer.

请提出你的问题 Please ask your question

当使用DETR训练自己的数据集时，发现训练500个epoch以后，精度仍然非常低，mAP只有5%，我已经检查过数据集，应该并不是数据集的问题，因为用YOLOV3、FCOS、CenterNet，mAP都可以达到80%，甚至是90%。虽然DETR收敛比较慢，但只有5%也太不正常了？？？ Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.052 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.125 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.038 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.052 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.100 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.117 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.219 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.280 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.224 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.338 [07/27 21:14:27] ppdet.engine INFO: Total sample number: 542, averge FPS: 15.35280900697572

[lyuwenyu]

数据量有多少 可以加载coco上的预训练再试试

[mingheyuemankong]

训练数据集大概4400张左右，请问是要将PaddleDetection-release-2.4/configs/detr/base/detr_r50.yml文件中的 pretrain_weights: https://paddledet.bj.bcebos.com/models/pretrained/ResNet50_vb_normal_pretrained.pdparams 更改为 https://paddledet.bj.bcebos.com/models/detr_r50_1x_coco.pdparams 这样试一试吗？