Instructions to use zeromodels/sam2_hiera_tiny with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ZeroModels
How to use zeromodels/sam2_hiera_tiny with ZeroModels:
# pip install -U zeromodels # ZeroModels is pure Keras 3, so pick a backend: "jax", "torch" or "tensorflow". import os os.environ["KERAS_BACKEND"] = "jax" from zeromodels import AutoZModel # AutoZModel reads the repo's model_type and loads the matching class. # For a task head use the matching loader, e.g. AutoZMImageClassify / AutoZMDetect / # AutoZMSemanticSegment / AutoZMTextGenerate (see zeromodels.auto). model = AutoZModel.from_weights("zeromodels/sam2_hiera_tiny") - Keras
How to use zeromodels/sam2_hiera_tiny with Keras:
# !pip install -U keras tensorflow huggingface_hub # Keras needs TensorFlow installed to read "hf://" paths, so the tensorflow backend is selected here; # "jax" and "torch" also work for computation once TensorFlow is installed. import os os.environ["KERAS_BACKEND"] = "tensorflow" import keras model = keras.saving.load_model("hf://zeromodels/sam2_hiera_tiny") - sam2
How to use zeromodels/sam2_hiera_tiny with sam2:
# Use SAM2 with images import torch from sam2.sam2_image_predictor import SAM2ImagePredictor predictor = SAM2ImagePredictor.from_pretrained("zeromodels/sam2_hiera_tiny") 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("zeromodels/sam2_hiera_tiny") 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 model.weights.h5 from zeromodels/sam2_hiera_tiny: direct link, hf CLI and curl.
- Browser
- Download file 151 MB
-
https://huggingface.co/zeromodels/sam2_hiera_tiny/resolve/main/model.weights.h5
- Command line
-
hf download hf://zeromodels/sam2_hiera_tiny/model.weights.h5
-
curl -L -o model.weights.h5 https://huggingface.co/zeromodels/sam2_hiera_tiny/resolve/main/model.weights.h5
151 MB
- Xet hash:
- 98a998f36c4d509093fb89290416d23b3a7917ccf78b48a0adeeb465a5b8848b
- Size of remote file:
- 151 MB
- SHA256:
- b91fa446ebf935273bf19fb2593fb1e785bd6670ef2cffd945a52fc6103ab86a
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.