pytorch/vision

transforms.ToTensor() for numpy float array in the range of [0.0, 255.0]

Open

#546 opened on Jul 13, 2018

View on GitHub
 (6 comments) (4 reactions) (0 assignees)Python (15,050 stars) (6,858 forks)batch import
enhancementhelp wantedmodule: transforms

Description

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?

Contributor guide

Tech stack
pythonpytorchnumpy
Domain
machine learningdata
Issue type
feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
half day
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
stale
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
clear
Prerequisites
PythonPyTorchnumpy
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
30
Research direction
The issue points to lines in torchvision/transforms/functional.py where ToTensor assumes float inputs are in [0,1]. Read the linked code and comments for context. Propose a solution to handle float arrays in [0,255] by scaling them to [0,1], considering backwards compatibility. Add tests for both float and integer inputs.
transforms.ToTensor() for numpy float array in the range of [0.0, 255.0] · pytorch/vision#546 | Good First Issue