flywheel1412

[Feature] add some feature for learning extremely un-balanced datasets

1

### Describe the feature **Re-sampling** - in mini-batch, every class is balanced (class-balanced sampling); - gradually transition from sample-balanced sampling(current sampling stategy) to class-balanced sampling in training time; **Re-weighting** -...

部署方式：docker mrdoc 版本：0.6.7 问题：行内公式解析失败，如下 

Tkx for your great work, I found this repository not contain RepVGG-A0 and RepVGG-A1, could you add these models in this repository reference link [repvgg](https://github.com/DingXiaoH/RepVGG/blob/9f4de3c7a065f8d0e56ad73ee4c1f53df9e66014/repvgg.py#L196)

请按照一下格式提交issue，谢谢！ 1. 你当前使用的是哪个版本的 BookStack? 2. 你当前使用的是什么操作系统? raspberry pi 4 树莓派官方最新系统 3. 你是如何操作的？ 4. 你期望得到什么结果? 希望发布armv7版本支持 5. 当前遇到的是什么结果? go语言小白，不知道怎么编译

环境 Mac OS 11.4 Wiznote Lite 2.1.2 问题 1. 过长的数学公式会出现排版问题； 2. 数学公式未能居中对齐； 

Thanks for your error report and we appreciate it a lot. **Checklist** 1. I have searched related issues but cannot get the expected help. 2. I have read the [FAQ...

[FEATURE] Support shufflenet

4

tkx for your wonderful work, I found the `timm` is not support shufflenet v1 and v2 yet, there is any plan to support it? and [here](https://github.com/megvii-model/ShuffleNet-Series) is the official repository...

thx for your great work! I'm very interested in the auxiliary training module, cloud you provide some reference paper about this? thank you

模型加载问题

4

作者您好，我用您提供的Resnet18_FER+_pytorch.pth.tar模型进行测试，出现如下报错RuntimeError: Error(s) in loading state_dict for ResNet_AT: Missing key(s) in state_dict: "alpha.0.bias", "alpha.0.weight", "beta.0.bias", "beta.0.weight", "pred_fc1.bias", "pred_fc1.weight", "pred_fc2.bias", "pred_fc2.weight". Unexpected key(s) in state_dict: "fc.weight", "fc.bias". 是因为我使用的网络不对吗？