train on my own datasets

Description

Contributor guide

Tech stack

python

Domain

machine learning

Issue type

documentation

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.

1-3 hours

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.

unclear

Prerequisites

basic PyTorch knowledgefamiliarity with image classification

Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.

20

Research direction

This issue is a question about training NasNet on custom datasets. The repository lacks clear documentation or examples for custom dataset training. To address this, one could create a tutorial notebook or update the README with step by step instructions, referencing existing data loading patterns in PyTorch. The maintainer (Cadene) has not provided guidance in the comments, so the contributor should first review similar repos like torchvision for dataset handling patterns.