Instructions to use timm/vit_so150m_patch16_reg4_gap_384.sbb_e250_in12k_ft_in1k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- timm
How to use timm/vit_so150m_patch16_reg4_gap_384.sbb_e250_in12k_ft_in1k with timm:
import timm model = timm.create_model("hf-hub:timm/vit_so150m_patch16_reg4_gap_384.sbb_e250_in12k_ft_in1k", pretrained=True) - Transformers
How to use timm/vit_so150m_patch16_reg4_gap_384.sbb_e250_in12k_ft_in1k with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="timm/vit_so150m_patch16_reg4_gap_384.sbb_e250_in12k_ft_in1k") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("timm/vit_so150m_patch16_reg4_gap_384.sbb_e250_in12k_ft_in1k", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update model config and README
Browse files
README.md
CHANGED
|
@@ -37,8 +37,8 @@ Recipe details:
|
|
| 37 |
- **Model Type:** Image classification / feature backbone
|
| 38 |
- **Model Stats:**
|
| 39 |
- Params (M): 134.4
|
| 40 |
-
- GMACs:
|
| 41 |
-
- Activations (M):
|
| 42 |
- Image size: 384 x 384
|
| 43 |
- **Papers:**
|
| 44 |
- Vision Transformers Need Registers: https://arxiv.org/abs/2309.16588
|
|
|
|
| 37 |
- **Model Type:** Image classification / feature backbone
|
| 38 |
- **Model Stats:**
|
| 39 |
- Params (M): 134.4
|
| 40 |
+
- GMACs: 88.0
|
| 41 |
+
- Activations (M): 165.5
|
| 42 |
- Image size: 384 x 384
|
| 43 |
- **Papers:**
|
| 44 |
- Vision Transformers Need Registers: https://arxiv.org/abs/2309.16588
|