pytorch/vision

Implement AutoAugment for Detection

Open

#6,224 创建于 2022年6月30日

在 GitHub 查看
 (19 评论) (0 反应) (1 负责人)Python (15,050 star) (6,858 fork)batch import
help wantedmodule: transforms

描述

🚀 The feature

Implement Learning Data Augmentation Strategies for Object Detection Refers to: #3817

Motivation, pitch

Good to have augmentation in Torchvision

Alternatives

No response

Additional context

No response

cc @vfdev-5 @datumbox

贡献者指南

技术栈
python
领域
machine learning
议题类型
feature
难度面向新贡献者的预计实现难度，1 表示很小改动，5 表示专家级工作。
4
预计时间有经验贡献者完成调查、实现、测试并准备 pull request 的粗略时间范围。
3-5 days
活动状态议题当前的可参与程度：新鲜、活跃、陈旧、阻塞或等待维护者输入。
blocked
清晰度议题是否清楚说明期望改动、验收标准和下一步。
clear
前置要求
PythonPyTorchObject detection conceptsAugmentation methods
新手友好度1-100 的估计分数，表示该议题对首次贡献者的友好程度。
15
研究方向
Implement AutoAugment for detection as described in the referenced paper. Begin by reviewing the existing AutoAugment implementation for classification (likely in torchvision/transforms/autoaugment.py) and the discussion in issue #3817. Adapt the augmentation policies to work with object detection transforms, such as those in torchvision/transforms/functional.py. Check the assignee's progress and any linked branches for coordination.