| { | |
| "architecture": "shvit_s4", | |
| "num_classes": 1000, | |
| "num_features": 448, | |
| "pretrained_cfg": { | |
| "tag": "in1k", | |
| "custom_load": false, | |
| "input_size": [ | |
| 3, | |
| 256, | |
| 256 | |
| ], | |
| "fixed_input_size": false, | |
| "interpolation": "bicubic", | |
| "crop_pct": 0.875, | |
| "crop_mode": "center", | |
| "mean": [ | |
| 0.485, | |
| 0.456, | |
| 0.406 | |
| ], | |
| "std": [ | |
| 0.229, | |
| 0.224, | |
| 0.225 | |
| ], | |
| "num_classes": 1000, | |
| "pool_size": [ | |
| 4, | |
| 4 | |
| ], | |
| "first_conv": "patch_embed.0.c", | |
| "classifier": "head.l", | |
| "origin_url": "https://github.com/ysj9909/SHViT", | |
| "paper_name": "SHViT: Single-Head Vision Transformer with Memory Efficient Macro Design", | |
| "paper_ids": "arXiv:2401.16456" | |
| } | |
| } |