Instructions to use CIDAS/clipseg-rd64 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use CIDAS/clipseg-rd64 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-segmentation", model="CIDAS/clipseg-rd64")# Load model directly from transformers import AutoProcessor, CLIPSegForImageSegmentation processor = AutoProcessor.from_pretrained("CIDAS/clipseg-rd64") model = CLIPSegForImageSegmentation.from_pretrained("CIDAS/clipseg-rd64") - Notebooks
- Google Colab
- Kaggle
Update preprocessor_config.json
Browse files- preprocessor_config.json +7 -7
preprocessor_config.json
CHANGED
|
@@ -4,14 +4,14 @@
|
|
| 4 |
"do_resize": true,
|
| 5 |
"feature_extractor_type": "ViTImageProcessor",
|
| 6 |
"image_mean": [
|
| 7 |
-
0.
|
| 8 |
-
0.
|
| 9 |
-
0.
|
| 10 |
],
|
| 11 |
"image_std": [
|
| 12 |
-
0.
|
| 13 |
-
0.
|
| 14 |
-
0.
|
| 15 |
],
|
| 16 |
"processor_class": "CLIPSegProcessor",
|
| 17 |
"resample": 2,
|
|
@@ -20,4 +20,4 @@
|
|
| 20 |
"height": 352,
|
| 21 |
"width": 352
|
| 22 |
}
|
| 23 |
-
}
|
|
|
|
| 4 |
"do_resize": true,
|
| 5 |
"feature_extractor_type": "ViTImageProcessor",
|
| 6 |
"image_mean": [
|
| 7 |
+
0.485,
|
| 8 |
+
0.456,
|
| 9 |
+
0.406
|
| 10 |
],
|
| 11 |
"image_std": [
|
| 12 |
+
0.229,
|
| 13 |
+
0.224,
|
| 14 |
+
0.225
|
| 15 |
],
|
| 16 |
"processor_class": "CLIPSegProcessor",
|
| 17 |
"resample": 2,
|
|
|
|
| 20 |
"height": 352,
|
| 21 |
"width": 352
|
| 22 |
}
|
| 23 |
+
}
|