Chilicyy
Chilicyy
Hi @KaranBhuva22 , did you do training with fuse_ab mode open?
@KaranBhuva22 Well, as for the problems you encountered, there's a few possible ways for improvements, I hope it helps. 1. With fuse_ab mode open, check anchors through AutoAnchor referring to...
Hi @Mirshal , In this case, I suggest that you modify the class_id in label files for your custom dataset , in order to directly and correctly apply coco pretrained...
Hi @sulaiman1988 , you could try to add `--verbose` when run evaluation.
您好,感谢支持和关注,pose检测的功能正在规划中,谢谢!
HI @debugmenot , YOLOv6 is a framework with dense regression, and NMS is necessary to get the final results.
您好 @Rosal-1998 需要与`--do_pr_metric True` 一起使用才会生效。
您好 @swift1988 ,日志文件默认是保存在`runs/train/exp/`这个目录下,需要用tensorboard进行可视化,`tensorboard --logdir=your_path/to/log `。
您好,我们默认是开启混合精度训练,没有一键关闭的功能。
Hi @Mirshal , could you please provide more details , such as the evaluation command and data.yaml, ...