Apache MXNet
The high-performance deep learning framework for flexible and efficient distributed training.
Development
Open Source
View Pricing
Image Classification
Object Detection
Sequence Modeling
Vision Transformer (ViT) Large
4.6
Free A powerful and accurate image classification model with easy integration into the Hugging Face ecosystem, but may require significant computational resources.
A large-sized Vision Transformer model pre-trained on ImageNet for image classification tasks.
0 views
0 saves
|
Refined 3/2/2026
About Vision Transformer (ViT) Large
The Vision Transformer (ViT) Large model is a transformer encoder model pre-trained on ImageNet-21k (14 million images, 21,843 classes) and fine-tuned on ImageNet 2012 (1 million images, 1,000 classes), both at a resolution of 224x224. It processes images as a sequence of fixed-size patches (16x16) which are then linearly embedded and fed into the transformer encoder, enhanced with a classification token ([CLS]) and positional embeddings. The model's architecture leverages the attention mechanism to capture global relationships within the image, making it suitable for various downstream image classification tasks. The model weights were converted from JAX to PyTorch by Ross Wightman.
Core Capabilities
The Vision Transformer (ViT) Large model is a transformer encoder model pre-trained on ImageNet-21k (14 million images, 21,843 classes) and fine-tuned on ImageNet 2012 (1 million images, 1,000 classes), both at a resolution of 224x224.
Main Tasks
Classify images
Explore all tools that specialize in classify images. This domain focus ensures Vision Transformer (ViT) Large delivers optimized results for this specific requirement.
