Models / timm / ViT Base Patch32 384

ViT Base Patch32 384

JSON →
vision

A base Vision Transformer with 32x32 patch size and 384x384 input resolution, pretrained on ImageNet-21k with augmentation regularization and fine-tuned on ImageNet-1k.

imagevision
Specs
Context & limits
context window
max output
Lifecycle
Dates

No lifecycle dates recorded.

Resources

No resource links recorded.