transforms.ToTensor() for numpy float array in the range of [0.0, 255.0] · pytorch/vision#546 | Good First Issue

(6 评论) (4 反应) (0 负责人)Python (6,858 fork)batch import

enhancementhelp wantedmodule: transforms

仓库指标

Star: (15,050 star)
PR 合并指标: (平均合并 12天 8小时) (30 天内合并 14 个 PR)

描述

I had come across a debugging scenario where the ToTensor() didn't convert the numpy float array in the range of [0.0, 255.0] to the range [0.0 to 1.0] due to following lines: https://github.com/pytorch/vision/blob/master/torchvision/transforms/functional.py#L50-L53

Basically, this API assumes that all the float arrays will already be in range [0.0 to 1.0]. Do you think we have to change this behavior?

贡献者指南

研究方向: 检查 torchvision/transforms/functional.py 中的 ToTensor 转换，修改逻辑以检测值在 [0,255] 范围内的浮点数组，并将其缩放到 [0,1]，而不是假定为 [0,1]。
技术栈: python
领域: machine learning
议题类型: 缺陷
难度: 2
预计时间: 1-3 小时
活动状态: 活跃
清晰度: 清晰
前置要求: PythonPyTorch basics
新手友好度: 70