nvidia / image-classification Open weights updated 4 years ago

mit-b2

Name: mit-b2
Author: nvidia

SegFormer encoder fine-tuned on Imagenet-1k. It was introduced in the paper SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers by Xie et al. and first released in this repository.

Params

—

Context

—

Downloads 30d

240 K

Likes

Licence: other Not gated View on Hugging Face ↗

Download history

daily snapshots · 89 days

▲ 0 in the last 30 days (0.0%)

1.6 M240 K

Jul 28Aug 26Sep 25Oct 24

Specifications

Architecture: SegformerForImageClassification
Licence: other
First seen on the Hub: 2022-03-02
Training datasets: imagenet_1k
Added to our catalog: 2026-07-28

Compare with any image-classification model

Popular comparisons

mobilenetv3_small_100.lamb_in1k 17.0 M vit-base-patch16-224 14.0 M Gender-Classifier-Mini 6.1 M resnet18.a1_in1k 2.0 M tf_efficientnetv2_s.in21k_ft_in1k 1.9 M nsfw_image_detection 1.6 M