pytorch/examples

MNIST test_loader not being used as intended (wrong)!

Open

#756 创建于 2020年4月19日

在 GitHub 查看
 (3 评论) (0 反应) (0 负责人)Python (21,634 star) (9,429 fork)batch import
good first issue

描述

In the MNIST code, around line 57 (I think), the following code is wrong in my opinion for data, target in test_loader: It should be replaced by for idx,(data, target) in test_loader: The original code gives an error (int has no attribute .to(device)) as originally, data is actually assigned an integer (idx value) wrongly. I have verified this fix works. The code for training is correct but surprisingly there is a mistake in test code.

贡献者指南

技术栈
python
领域
machine learning
议题类型
bug
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。
2
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。
under 1 hour
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
PythonBasic PyTorch
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。
80
研究方向
The issue is in the MNIST example code in the pytorch/examples repository, specifically in the test loop around line 57 of the mnist/main.py file. The bug is that `test loader` is iterated incorrectly: `for data, target in test loader` should be `for idx,(data, target) in test loader`. The fix is straightforward and confirmed by the issue author. To contribute, locate the file, apply the change, and submit a pull request.