Haian Huang(深度眸)

Results 45 issues of Haian Huang(深度眸)

我的android studio 3.0预览版 sdk25 gradle4.0 为何没有底部导航view的切换动画,不管咋点始终是第一个 条目,其他条目文字无法显示,请问这是为啥?我百度了下,默认应该是开启了的呀

Many thanks to the author for the repo. I've created a PR to support mmdet. Welcome those who have time to improve. #https://github.com/open-mmlab/mmdetection/pull/7987

Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily get feedback. If you do not understand...

Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily get feedback. If you do not understand...

We support cam visualization in mmdet. Currently, I have tested RetinaNet, Faster RCNN, Mask RCNN and YOLOX. Currently `grad_free` and `grad_based` methods are supported as shown below: ```python GRAD_FREE_METHOD_MAP =...

Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily get feedback. If you do not understand...

When I was reading the code, I found that the `align_method`s description was too few, which is not convenient to understand the code. Can you provide use cases or configurations...

### Describe the feature ```python losses=[ dict( type='ChannelWiseDivergence', name='loss_cwd_logits', # ---------------- this--------------- tau=1, loss_weight=5, ) ] ``` From the OpenMMLab development model, there should be no additional loss name field,...

enhancement

我比较好奇的是:用 collate_fn 实现batch_transforms太耗时了,原因是啥?感觉不合理啊

Applied to my own data, the effect is indeed improved, and it works very well! The disadvantage is that the code quality is not very good.