ViT-Small (Patch16, 224px, AugReg, IN21k → IN1k)
JSON →A small Vision Transformer with patch size 16, pretrained on ImageNet-21k with AugReg and fine-tuned on ImageNet-1k for classification.
Capabilities
vision
Dates
releasedOct 2021
A small Vision Transformer with patch size 16, pretrained on ImageNet-21k with AugReg and fine-tuned on ImageNet-1k for classification.