Image Classification
PyTorch
sam2
torchscript
libtorch
image-segmentation
knowledge-distillation
convnextv2
shortcut-learning
Instructions to use DiegoXAI-Shape/abbadon-engine with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sam2
How to use DiegoXAI-Shape/abbadon-engine with sam2:
# Use SAM2 with images import torch from sam2.sam2_image_predictor import SAM2ImagePredictor predictor = SAM2ImagePredictor.from_pretrained("DiegoXAI-Shape/abbadon-engine") 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("DiegoXAI-Shape/abbadon-engine") 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
Download mendicant_bias_cpp.pt from DiegoXAI-Shape/abbadon-engine: direct link, hf CLI and curl.
- Browser
- Download file 13.9 MB
-
https://huggingface.co/DiegoXAI-Shape/abbadon-engine/resolve/main/mendicant_bias_cpp.pt
- Command line
-
hf download hf://DiegoXAI-Shape/abbadon-engine/mendicant_bias_cpp.pt
-
curl -L -o mendicant_bias_cpp.pt https://huggingface.co/DiegoXAI-Shape/abbadon-engine/resolve/main/mendicant_bias_cpp.pt
13.9 MB
- Xet hash:
- e4a318b1937d62a5495833632ca53d7bdd7c463f4ab20d218572133fcf943836
- Size of remote file:
- 13.9 MB
- SHA256:
- 6bf4573ac0a30bb8871031b0374764c34d454fd3a715ffeaff856c1874d878d7
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.