Instructions to use CardAnvilModels/sam2.1-hiera-tiny-ONNX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers.js
How to use CardAnvilModels/sam2.1-hiera-tiny-ONNX with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('mask-generation', 'CardAnvilModels/sam2.1-hiera-tiny-ONNX'); - sam2
How to use CardAnvilModels/sam2.1-hiera-tiny-ONNX with sam2:
# Use SAM2 with images import torch from sam2.sam2_image_predictor import SAM2ImagePredictor predictor = SAM2ImagePredictor.from_pretrained("CardAnvilModels/sam2.1-hiera-tiny-ONNX") 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("CardAnvilModels/sam2.1-hiera-tiny-ONNX") 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 onnx/vision_encoder_quantized.onnx_data from CardAnvilModels/sam2.1-hiera-tiny-ONNX: direct link, hf CLI and curl.
- Browser
- Download file 52.6 MB
-
https://huggingface.co/CardAnvilModels/sam2.1-hiera-tiny-ONNX/resolve/main/onnx/vision_encoder_quantized.onnx_data
- Command line
-
hf download hf://CardAnvilModels/sam2.1-hiera-tiny-ONNX/onnx/vision_encoder_quantized.onnx_data
-
curl -L -o vision_encoder_quantized.onnx_data https://huggingface.co/CardAnvilModels/sam2.1-hiera-tiny-ONNX/resolve/main/onnx/vision_encoder_quantized.onnx_data
52.6 MB
- Xet hash:
- 21309746332cd33abe2db59548a25df0993c6e981d1d8c8504a4abfd92520c68
- Size of remote file:
- 52.6 MB
- SHA256:
- ea1f677596dc82cef0dc317d78135d892f4b26e20a4439f899aa58d84965b324
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.