Instructions to use microsoft/focalnet-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/focalnet-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="microsoft/focalnet-base") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# Load model directly from transformers import AutoImageProcessor, AutoModelForImageClassification processor = AutoImageProcessor.from_pretrained("microsoft/focalnet-base") model = AutoModelForImageClassification.from_pretrained("microsoft/focalnet-base") - Notebooks
- Google Colab
- Kaggle
Add hidden_sizes config attribute
Browse files- config.json +6 -0
config.json
CHANGED
|
@@ -8,6 +8,12 @@
|
|
| 8 |
18,
|
| 9 |
2
|
| 10 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
"drop_path_rate": 0.1,
|
| 12 |
"embed_dim": 128,
|
| 13 |
"encoder_stride": 32,
|
|
|
|
| 8 |
18,
|
| 9 |
2
|
| 10 |
],
|
| 11 |
+
"hidden_sizes": [
|
| 12 |
+
192,
|
| 13 |
+
384,
|
| 14 |
+
768,
|
| 15 |
+
768
|
| 16 |
+
],
|
| 17 |
"drop_path_rate": 0.1,
|
| 18 |
"embed_dim": 128,
|
| 19 |
"encoder_stride": 32,
|