pytorch/vision

Unit tests for Vision

Open

#110 创建于 2017年3月17日

在 GitHub 查看
 (8 评论) (3 反应) (0 负责人)Python (15,050 star) (6,858 fork)batch import
help wanted

描述

This issue fleshes out the full details and scope of the unit tests needed for torchvision.

There are very limited unit tests under test/ which dont cover the transform outputs themselves, but are limited to dimension and shape checks.

First, let's start with quantitative tests on known results.

We need to have a set of 10 test images, and then do each transformation of vision.transforms on these 10 images, and compare them pixel-wise with known results. We then compare the known results with the computed result from the transforms, and if they are within some threshold, we pass the test.

Some of the transforms such as Horizontal / Vertical flip can also have exact numerical unit-tests.

The test images:

  • 2 monochrome images
  • 2 3-channel images
  • 2 4-channel PNG images with an Alpha component

Can find some on Wikipedia that are freely licensed.

The tests need to cover all transforms under: https://github.com/pytorch/vision#transforms

For similar testing, you can have a look at:

https://github.com/torch/image/blob/master/test/test.lua#L258-L646

贡献者指南

技术栈
python
领域
testing
议题类型
test
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。
3
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。
stale
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
PythonPyTorchtorchvisionunit testing
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。
60
研究方向
Familiarize with current torchvision transforms at https://github.com/pytorch/vision#transforms. Create 10 test images (2 monochrome, 2 3 channel, 2 4 channel) from freely licensed sources. Implement unit tests for each transform comparing output to known results within a threshold, using the Lua test at https://github.com/torch/image/blob/master/test/test.lua#L258 L646 as reference.