microsoft / image-classification Open weights updated 3 years ago

swinv2-tiny-patch4-window16-256

Name: swinv2-tiny-patch4-window16-256
Author: microsoft

Swin Transformer v2 model pre-trained on ImageNet-1k at resolution 256x256. It was introduced in the paper Swin Transformer V2: Scaling Up Capacity and Resolution by Liu et al. and first released in this repository.

Params

—

Context

—

Downloads 30d

390 K

Likes

Commercial use: allowed apache-2.0 Not gated View on Hugging Face ↗

Download history

daily snapshots · 106 days

▲ 14 K in the last 30 days (3.6%)

437 K369 K

Jul 28Sep 1Oct 6Nov 10

Specifications

Architecture: Swinv2ForImageClassification
Licence: apache-2.0
First seen on the Hub: 2022-06-14
Training datasets: imagenet-1k
Added to our catalog: 2026-07-28

Compare with any image-classification model

Popular comparisons

vit-base-patch16-224 15.0 M mobilenetv3_small_100.lamb_in1k 12.7 M Gender-Classifier-Mini 8.1 M tf_efficientnetv2_s.in21k_ft_in1k 3.6 M resnet18.a1_in1k 2.0 M resnet50.a1_in1k 1.6 M