Ren Tianhe

- Paper: [TRAR: Routing the Attention Spans in Transformer for Visual Question Answering](https://openaccess.thecvf.com/content/ICCV2021/papers/Zhou_TRAR_Routing_the_Attention_Spans_in_Transformer_for_Visual_Question_ICCV_2021_paper.pdf) - Code: [TRAR-VQA](https://github.com/rentainhe/TRAR-VQA)

### Problem Still meet the space problems mentioned in: - https://github.com/readthedocs/sphinx_rtd_theme/issues/1029 - https://github.com/readthedocs/sphinx_rtd_theme/pull/1202 I have no idea how to fix it~ ### Environment Info - Python Version: 3.7.10 - Sphinx...

Implement SK Module in Glasses

3

### Paper - https://arxiv.org/abs/1903.06586 ### Reference - https://github.com/rwightman/pytorch-image-models/blob/1c9284c640503ad53b819990a4c56985609704e2/timm/models/layers/selective_kernel.py ### TODO - [x] implement SelectiveKernelAttn Module - [x] implement SelectiveKernel Module - [ ] Finish Doc String

Contribute Guide

4

Hello! I've noticed that you did such an amazing work here. How can I be one of the contributors of this repo? Maybe I can help you to add more...

Thanks for adding our ICCV 2021 paper~ - Paper: https://openaccess.thecvf.com/content/ICCV2021/papers/Zhou_TRAR_Routing_the_Attention_Spans_in_Transformer_for_Visual_Question_ICCV_2021_paper.pdf - Code: https://github.com/rentainhe/TRAR-VQA - Topic: Visual Question Answering

Support Repeated Augmentation

2

## TODO - [x] 添加Repeated Augmentation (一种Mini-batch的采样策略） 在Swin-T，DeiT等主流ViT中都用到的一个增强策略，对于大模型涨点比较明显，对于小模型没有太大影响 ## Reference - deit实现: https://github.com/facebookresearch/deit/blob/main/samplers.py - 知乎解读: https://zhuanlan.zhihu.com/p/430563265 - mmcls的实现: https://github.com/open-mmlab/mmclassification/blob/master/mmcls/datasets/samplers/repeat_aug.py

Add OneCls projects in LiBai

3

## TODO - [x] 对接vision下的模型到libai中的训练，暂时命名为`OneCls` - [x] 写README - [x] 添加模型的example, 可以用vision中的注册机制轻松添加自己的模型进行训练

## 文档细节整理 from PR: https://github.com/Oneflow-Inc/libai/pull/229 by @khloe-zhang - 开发者的自我称呼：在文档中看到很多“we”用来指代开发者，显得不太客观。解决方法： - 尽量用“LiBai”来代替“we”，如：In LiBai, we define a standard set of config namespaces 改为 LiBai defines a standard set of config namespaces -...

visualization 0.6.0 Plan

2

## Visualization 0.6.0 TODO List - [ ] Add Patchfiy Image and Compose Image Func - [ ] Add Visualize BBox Func ## Reference - https://www.cnblogs.com/zgqcn/p/10963356.html - https://github.com/open-mmlab/mmcv/blob/master/mmcv/visualization/image.py - https://scikit-learn.org/stable/modules/generated/sklearn.feature_extraction.image.extract_patches_2d.html...