Resnet34 as backbone for segmentation models

Description

Contributor guide

Tech stack

python

Domain

machine learning

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.

1-2 days

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.

mostly clear

Prerequisites

Python programmingPyTorch basicsUnderstanding of ResNet architecture

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

55

Research direction

First, study how ResNet50 backbone was integrated into segmentation models in this repo (likely in torchvision/models/segmentation/backbone.py). Look for the existing FCN and DeepLab implementations to understand the pattern for adding a new backbone. Then, implement ResNet34 following similar steps: define the backbone, add it to the model registry, and update the weight loading logic if applicable. Check the issue comments for any additional guidance or unresolved questions.