Image Segmentation
Transformers
Safetensors
remote-sensing
earth-observation
open-vocabulary
clip
sam3
semantic-segmentation
Instructions to use BiliSakura/SegEarth-OV with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BiliSakura/SegEarth-OV with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-segmentation", model="BiliSakura/SegEarth-OV")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("BiliSakura/SegEarth-OV", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update all files for SegEarth-OV
Browse files
OV-2/weights/backbone/AlignEarth-SAR-ViT-B-16/conversion_meta.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"source_checkpoint": "/data/projects/models/hf_models/likyoo/AlignEarth-SAR-ViT-B-16/AlignEarth-SAR-ViT-B-16.pt",
|
| 3 |
+
"source_top_level_keys": [
|
| 4 |
+
"epoch",
|
| 5 |
+
"name",
|
| 6 |
+
"state_dict",
|
| 7 |
+
"optimizer",
|
| 8 |
+
"scaler"
|
| 9 |
+
],
|
| 10 |
+
"converted_to": "transformers.CLIPModel",
|
| 11 |
+
"notes": "Mapped OpenCLIP-style state_dict to HF CLIPModel key format (vision+text)."
|
| 12 |
+
}
|