Instructions to use Gertlek/DetectiveSAM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Gertlek/DetectiveSAM with sam2:

# Use SAM2 with images
import torch
from sam2.sam2_image_predictor import SAM2ImagePredictor

predictor = SAM2ImagePredictor.from_pretrained(Gertlek/DetectiveSAM)

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(Gertlek/DetectiveSAM)

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

@@ -98,14 +98,14 @@ python -m detectivesam_inference.predict \
 ### 4. Bundled CocoGlide subset sweep
-Use this to evaluate all bundled CocoGlide demo pairs.
 ```bash
 python -m detectivesam_inference.evaluate \
   --checkpoint detective_sam \
   --dataset-root demo/cocoglide \
   --output-dir outputs/poster_eval_cocoglide \
-  --num-visualizations 5
 ```
 ## Outputs

 ### 4. Bundled CocoGlide subset sweep
+Use this to evaluate the bundled banana and train CocoGlide demo pairs.
 ```bash
 python -m detectivesam_inference.evaluate \
   --checkpoint detective_sam \
   --dataset-root demo/cocoglide \
   --output-dir outputs/poster_eval_cocoglide \
+  --num-visualizations 2
 ```
 ## Outputs

Gertlek
/

DetectiveSAM

Keep banana and train CocoGlide demos

Git LFS Details

Git LFS Details

Git LFS Details

Git LFS Details

Git LFS Details

Git LFS Details