haofeng

First, I really thank for your work, which does help me! I think you can promote it better by mentioning about **squared L2 norm** in front of `x.T.dot(x)` or `sqrt(x.T.dot(x))`...

第一次体会到做程序猿的厉害之处！！！

[feature] Visualizer compatible with MultiTaskDataSample

1

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...

[Feature] ClsVisualizer compatible with MultiTaskDataSample

2

### Describe the feature There is no support for MultiTaskDataSample visualization. ### Will you implement it? - [X] I would like to implement this feature and create a PR!

Use pinhole to train?

1

Is the process using a pinhole to train, and then the image can be rendered as a pinhole, fisheye ..., like this?