pytorch/vision

Resnet34 as backbone for segmentation models

Open

Aperta il 20 apr 2020

Vedi su GitHub
 (5 commenti) (0 reazioni) (0 assegnatari)Python (15.050 star) (6858 fork)batch import
enhancementhelp wantedmodule: modelstopic: semantic segmentation

Descrizione

🚀 Feature

I would like segmentation models with resnet34 backbone

Motivation

They have added resnet50 backbone.

Guida contributor

Tech stack
python
Dominio
machine learning
Tipo issue
feature
DifficoltàQuanto dovrebbe essere impegnativa per un nuovo contributor.
3
Tempo stimatoTempo stimato per completare e verificare uno scope piccolo.
1-2 days
Stato attivitàQuanto è probabile che la issue sia ancora attiva e reviewable.
stale
ChiarezzaQuanto chiaramente la issue descrive problema, scope e risultato atteso.
mostly clear
Prerequisiti
Python programmingPyTorch basicsUnderstanding of ResNet architecture
Adatta ai principiantiQuanto la issue è adatta a contributor alla prima esperienza.
55
Direzione di ricerca
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.