Instructions to use timm/vit_base_patch16_rope_reg1_gap_256.sbb_in1k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- timm
How to use timm/vit_base_patch16_rope_reg1_gap_256.sbb_in1k with timm:
import timm model = timm.create_model("hf_hub:timm/vit_base_patch16_rope_reg1_gap_256.sbb_in1k", pretrained=True) - Transformers
How to use timm/vit_base_patch16_rope_reg1_gap_256.sbb_in1k with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="timm/vit_base_patch16_rope_reg1_gap_256.sbb_in1k") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("timm/vit_base_patch16_rope_reg1_gap_256.sbb_in1k", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update model config and README
Browse files
README.md
CHANGED
|
@@ -36,8 +36,8 @@ Recipe details:
|
|
| 36 |
- **Model Type:** Image classification / feature backbone
|
| 37 |
- **Model Stats:**
|
| 38 |
- Params (M): 86.4
|
| 39 |
-
- GMACs:
|
| 40 |
-
- Activations (M):
|
| 41 |
- Image size: 256 x 256
|
| 42 |
- **Papers:**
|
| 43 |
- EVA-02: A Visual Representation for Neon Genesis: https://arxiv.org/abs/2303.11331
|
|
@@ -148,6 +148,7 @@ output = model.forward_head(output, pre_logits=True)
|
|
| 148 |
| [vit_medium_patch16_reg4_gap_256.sbb_in1k](https://huggingface.co/timm/vit_medium_patch16_reg4_gap_256.sbb_in1k) | 83.47 | 96.622 | 38.88 | 256 |
|
| 149 |
| [vit_medium_patch16_reg1_gap_256.sbb_in1k](https://huggingface.co/timm/vit_medium_patch16_reg1_gap_256.sbb_in1k) | 83.462 | 96.548 | 38.88 | 256 |
|
| 150 |
| [vit_little_patch16_reg4_gap_256.sbb_in1k](https://huggingface.co/timm/vit_little_patch16_reg4_gap_256.sbb_in1k) | 82.514 | 96.262 | 22.52 | 256 |
|
|
|
|
| 151 |
| [vit_pwee_patch16_reg1_gap_256.sbb_in1k](https://huggingface.co/timm/vit_pwee_patch16_reg1_gap_256.sbb_in1k) | 80.072 | 95.136 | 15.25 | 256 |
|
| 152 |
|
| 153 |
## Citation
|
|
|
|
| 36 |
- **Model Type:** Image classification / feature backbone
|
| 37 |
- **Model Stats:**
|
| 38 |
- Params (M): 86.4
|
| 39 |
+
- GMACs: 23.2
|
| 40 |
+
- Activations (M): 33.4
|
| 41 |
- Image size: 256 x 256
|
| 42 |
- **Papers:**
|
| 43 |
- EVA-02: A Visual Representation for Neon Genesis: https://arxiv.org/abs/2303.11331
|
|
|
|
| 148 |
| [vit_medium_patch16_reg4_gap_256.sbb_in1k](https://huggingface.co/timm/vit_medium_patch16_reg4_gap_256.sbb_in1k) | 83.47 | 96.622 | 38.88 | 256 |
|
| 149 |
| [vit_medium_patch16_reg1_gap_256.sbb_in1k](https://huggingface.co/timm/vit_medium_patch16_reg1_gap_256.sbb_in1k) | 83.462 | 96.548 | 38.88 | 256 |
|
| 150 |
| [vit_little_patch16_reg4_gap_256.sbb_in1k](https://huggingface.co/timm/vit_little_patch16_reg4_gap_256.sbb_in1k) | 82.514 | 96.262 | 22.52 | 256 |
|
| 151 |
+
| [vit_wee_patch16_reg1_gap_256.sbb_in1k](https://huggingface.co/timm/vit_wee_patch16_reg1_gap_256.sbb_in1k) | 80.258 | 95.360 | 13.42 | 256 |
|
| 152 |
| [vit_pwee_patch16_reg1_gap_256.sbb_in1k](https://huggingface.co/timm/vit_pwee_patch16_reg1_gap_256.sbb_in1k) | 80.072 | 95.136 | 15.25 | 256 |
|
| 153 |
|
| 154 |
## Citation
|