Instructions to use apple/DFN5B-CLIP-ViT-H-14 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- OpenCLIP
How to use apple/DFN5B-CLIP-ViT-H-14 with OpenCLIP:
import open_clip model, preprocess_train, preprocess_val = open_clip.create_model_and_transforms('hf-hub:apple/DFN5B-CLIP-ViT-H-14') tokenizer = open_clip.get_tokenizer('hf-hub:apple/DFN5B-CLIP-ViT-H-14') - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -42,7 +42,7 @@ These weights are directly usable in OpenCLIP (image + text).
|
|
| 42 |
| ImageNet-R | 0.929367 |
|
| 43 |
| KITTI Vehicle Distance | 0.336146 |
|
| 44 |
| MNIST | 0.8579 |
|
| 45 |
-
| ObjectNet | 0.
|
| 46 |
| Oxford Flowers-102 | 0.899534 |
|
| 47 |
| Oxford-IIIT Pet | 0.965515 |
|
| 48 |
| Pascal VOC 2007 | 0.818309 |
|
|
@@ -61,8 +61,7 @@ These weights are directly usable in OpenCLIP (image + text).
|
|
| 61 |
| FMoW | 0.207482 |
|
| 62 |
| Dollar Street | 0.699766 |
|
| 63 |
| GeoDE | 0.928184 |
|
| 64 |
-
| **Average**
|
| 65 |
-
|
| 66 |
## Model Usage
|
| 67 |
### With OpenCLIP
|
| 68 |
```
|
|
|
|
| 42 |
| ImageNet-R | 0.929367 |
|
| 43 |
| KITTI Vehicle Distance | 0.336146 |
|
| 44 |
| MNIST | 0.8579 |
|
| 45 |
+
| ObjectNet | 0.765156 |
|
| 46 |
| Oxford Flowers-102 | 0.899534 |
|
| 47 |
| Oxford-IIIT Pet | 0.965515 |
|
| 48 |
| Pascal VOC 2007 | 0.818309 |
|
|
|
|
| 61 |
| FMoW | 0.207482 |
|
| 62 |
| Dollar Street | 0.699766 |
|
| 63 |
| GeoDE | 0.928184 |
|
| 64 |
+
| **Average** | **0.698347** |
|
|
|
|
| 65 |
## Model Usage
|
| 66 |
### With OpenCLIP
|
| 67 |
```
|