Image Segmentation
sam2
Safetensors
segmentation
medical-imaging
polyp-detection
gastrointestinal
colonoscopy
Eval Results (legacy)
Instructions to use usama10/sam2-kvasir-polyp-segmentation with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sam2
How to use usama10/sam2-kvasir-polyp-segmentation with sam2:
# Use SAM2 with images import torch from sam2.sam2_image_predictor import SAM2ImagePredictor predictor = SAM2ImagePredictor.from_pretrained(usama10/sam2-kvasir-polyp-segmentation) 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(usama10/sam2-kvasir-polyp-segmentation) 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
Upload processor
Browse files- processor_config.json +60 -0
processor_config.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"image_processor": {
|
| 3 |
+
"data_format": "channels_first",
|
| 4 |
+
"default_to_square": true,
|
| 5 |
+
"do_convert_rgb": true,
|
| 6 |
+
"do_normalize": true,
|
| 7 |
+
"do_rescale": true,
|
| 8 |
+
"do_resize": true,
|
| 9 |
+
"image_mean": [
|
| 10 |
+
0.485,
|
| 11 |
+
0.456,
|
| 12 |
+
0.406
|
| 13 |
+
],
|
| 14 |
+
"image_processor_type": "Sam2ImageProcessorFast",
|
| 15 |
+
"image_std": [
|
| 16 |
+
0.229,
|
| 17 |
+
0.224,
|
| 18 |
+
0.225
|
| 19 |
+
],
|
| 20 |
+
"mask_size": {
|
| 21 |
+
"height": 256,
|
| 22 |
+
"width": 256
|
| 23 |
+
},
|
| 24 |
+
"resample": 2,
|
| 25 |
+
"rescale_factor": 0.00392156862745098,
|
| 26 |
+
"size": {
|
| 27 |
+
"height": 1024,
|
| 28 |
+
"width": 1024
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"point_pad_value": -10,
|
| 32 |
+
"processor_class": "Sam2VideoProcessor",
|
| 33 |
+
"target_size": 1024,
|
| 34 |
+
"video_processor": {
|
| 35 |
+
"data_format": "channels_first",
|
| 36 |
+
"default_to_square": true,
|
| 37 |
+
"do_convert_rgb": true,
|
| 38 |
+
"do_normalize": true,
|
| 39 |
+
"do_rescale": true,
|
| 40 |
+
"do_resize": true,
|
| 41 |
+
"image_mean": [
|
| 42 |
+
0.485,
|
| 43 |
+
0.456,
|
| 44 |
+
0.406
|
| 45 |
+
],
|
| 46 |
+
"image_std": [
|
| 47 |
+
0.229,
|
| 48 |
+
0.224,
|
| 49 |
+
0.225
|
| 50 |
+
],
|
| 51 |
+
"resample": 2,
|
| 52 |
+
"rescale_factor": 0.00392156862745098,
|
| 53 |
+
"return_metadata": false,
|
| 54 |
+
"size": {
|
| 55 |
+
"height": 1024,
|
| 56 |
+
"width": 1024
|
| 57 |
+
},
|
| 58 |
+
"video_processor_type": "Sam2VideoVideoProcessor"
|
| 59 |
+
}
|
| 60 |
+
}
|