Instructions to use BAAI/SegVol with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BAAI/SegVol with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="BAAI/SegVol", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("BAAI/SegVol", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
repace nearest-exact by nearest
#4
by yuxindu - opened
- model_segvol_single.py +1 -1
model_segvol_single.py
CHANGED
|
@@ -147,7 +147,7 @@ class SegVolProcessor():
|
|
| 147 |
transforms.ToTensord(keys=["image", "label"]),
|
| 148 |
]
|
| 149 |
)
|
| 150 |
-
self.zoom_out_transform = transforms.Resized(keys=["image", "label"], spatial_size=spatial_size, mode='nearest
|
| 151 |
self.transform4train = transforms.Compose(
|
| 152 |
[
|
| 153 |
# transforms.AddChanneld(keys=["image"]),
|
|
|
|
| 147 |
transforms.ToTensord(keys=["image", "label"]),
|
| 148 |
]
|
| 149 |
)
|
| 150 |
+
self.zoom_out_transform = transforms.Resized(keys=["image", "label"], spatial_size=spatial_size, mode='nearest')
|
| 151 |
self.transform4train = transforms.Compose(
|
| 152 |
[
|
| 153 |
# transforms.AddChanneld(keys=["image"]),
|