| license: apache-2.0 | |
| tags: | |
| - vit | |
| # Vision Transformer (base-sized model) | |
| Random weights are provided for the ViT model. During each step, the model selects a random subset of the masked image patches. |
| license: apache-2.0 | |
| tags: | |
| - vit | |
| # Vision Transformer (base-sized model) | |
| Random weights are provided for the ViT model. During each step, the model selects a random subset of the masked image patches. |