lijoe123
lijoe123
``` And the detail is: 2022-06-14 12:32:30,844 - mmdet - INFO - Environment info: ------------------------------------------------------------ sys.platform: linux Python: 3.7.13 (default, Mar 29 2022, 02:18:16) [GCC 7.5.0] CUDA available: True GPU...
> Did you make any modifications to the coco dataset? No!!!! I use faster rcnn to train my own dataset, i can get the good mAP.
> vis_cam.py Which file is it? @hhaAndroid @eilenelxc can you find vis_demo.py i can't the file 
mmdet/core/evaluation/coco_utils.py, coco_eval, classwise👉别人发给我的答案,您看看行不行。 发自坚果 R2 * body { background-color: #ffffff; line-height: 1.4;word-wrap: break-word; word-break: normal; } div {word-wrap: break-word; word-break: normal; } p {word-wrap: break-word; word-break: normal; text-indent: 0pt !important;...
是把里面的classwise改为True发自坚果 R2 * body { background-color: #ffffff; line-height: 1.4;word-wrap: break-word; word-break: normal; } div {word-wrap: break-word; word-break: normal; } p {word-wrap: break-word; word-break: normal; text-indent: 0pt !important; } span {word-wrap:...
你好,我也有问题了,我把classwise改为True 了,也不行,也是没有输出各个类别的AP值 @JakobWu
@JakobWu 我之前用了mmdetection,不是用这个,程序跑完还能输出AP值吗
你好,我是直接在训练过程中就不显示评估结果 
> @lijoe123 我记得好像是分布式训练中可以在训练中显示每一个epoch评估结果,非分布式训练中没有,但是我看之前的问题中好像分布式训练中显示评估结果也有点问题 分布式训练是怎么实现的呢,可以给我个demo吗