DAMO-YOLO: a fast and accurate object detection method with some new techs, including NAS backbones, efficient RepGFPN, ZeroHead, AlignedOTA, and distillation enhancement.
[X] I have read the README carefully. 我已经仔细阅读了README上的操作指引。
[X] I want to train my custom dataset, and I have read the tutorials for finetune on your data carefully and organize my dataset correctly; 我想训练自定义数据集,我已经仔细阅读了训练自定义数据的教程,以及按照正确的目录结构存放数据集。
[X] I have pulled the latest code of main branch to run again and the problem still existed. 我已经拉取了主分支上最新的代码,重新运行之后,问题仍不能解决。
Search before asking
[X] I have searched the DAMO-YOLO issues and found no similar questions.
Before Asking
[X] I have read the README carefully. 我已经仔细阅读了README上的操作指引。
[X] I want to train my custom dataset, and I have read the tutorials for finetune on your data carefully and organize my dataset correctly; 我想训练自定义数据集,我已经仔细阅读了训练自定义数据的教程,以及按照正确的目录结构存放数据集。
[X] I have pulled the latest code of main branch to run again and the problem still existed. 我已经拉取了主分支上最新的代码,重新运行之后,问题仍不能解决。
Search before asking
Question
您好,我使用自己的数据在damo-yolo s上finetune(damoyolo_tinynasL25_S_460.pth) 对比训练yolox s网络. 单GPU batch-size改为16, 训练300个epoch,这与yolox 的设定一致,其余训练超参数没有改变; nms_conf_thre和nms_iou_thre也改为了和yolox 一致,分别设置为0.01和0.65。 但是最终在val上的mAP0.50:0.95 为0.75,相对于yolox s的0.87低了很多,这与https://www.modelscope.cn/models/damo/cv_tinynas_object-detection_damoyolo/summary中的模型评测相对值相差较大. 是否damo yolo模型对单类训练有其他要求? 类似的问题在https://github.com/tinyvision/DAMO-YOLO/issues/77中也没找出合理解释.
Additional
No response