Image Segmentation
PyTorch
sam2
custom-sam2
glove
baseball
sports-analytics
computer-vision
custom-model
Instructions to use caball21/glove_labelling with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sam2
How to use caball21/glove_labelling with sam2:
# Use SAM2 with images import torch from sam2.sam2_image_predictor import SAM2ImagePredictor predictor = SAM2ImagePredictor.from_pretrained(caball21/glove_labelling) with torch.inference_mode(), torch.autocast("cuda", dtype=torch.bfloat16): predictor.set_image(<your_image>) masks, _, _ = predictor.predict(<input_prompts>)# Use SAM2 with videos import torch from sam2.sam2_video_predictor import SAM2VideoPredictor predictor = SAM2VideoPredictor.from_pretrained(caball21/glove_labelling) with torch.inference_mode(), torch.autocast("cuda", dtype=torch.bfloat16): state = predictor.init_state(<your_video>) # add new prompts and instantly get the output on the same frame frame_idx, object_ids, masks = predictor.add_new_points(state, <your_prompts>): # propagate the prompts to get masklets throughout the video for frame_idx, object_ids, masks in predictor.propagate_in_video(state): ... - Notebooks
- Google Colab
- Kaggle
Update config.json
Browse files- config.json +12 -26
config.json
CHANGED
|
@@ -1,28 +1,14 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
"
|
| 7 |
-
|
| 8 |
-
"
|
| 9 |
-
|
| 10 |
-
|
| 11 |
-
|
| 12 |
-
|
| 13 |
-
|
| 14 |
-
"_target_": "training.dataset.vos_dataset.VOSDataset",
|
| 15 |
-
"training": true,
|
| 16 |
-
"video_dataset": {
|
| 17 |
-
"_target_": "training.dataset.vos_dataset.VideoDatasetFromJSON",
|
| 18 |
-
"root_dir": "/content/drive/MyDrive/glove_labelling/final_train_data",
|
| 19 |
-
"json_paths": [
|
| 20 |
-
"/content/drive/MyDrive/glove_labelling/final_train_data"
|
| 21 |
-
]
|
| 22 |
-
}
|
| 23 |
-
}
|
| 24 |
-
]
|
| 25 |
-
}
|
| 26 |
-
},
|
| 27 |
-
"model": "sam2.1_hiera_l"
|
| 28 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"model_type": "custom-sam2",
|
| 3 |
+
"architecture": "SAM2Hierarchical",
|
| 4 |
+
"image_size": [720, 1280],
|
| 5 |
+
"num_classes": 6,
|
| 6 |
+
"class_labels": [
|
| 7 |
+
"glove_outline",
|
| 8 |
+
"webbing",
|
| 9 |
+
"thumb",
|
| 10 |
+
"palm_pocket",
|
| 11 |
+
"hand",
|
| 12 |
+
"glove_exterior"
|
| 13 |
+
]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
}
|