Image Segmentation
PyTorch
sam2
semantic-segmentation
microstructure
materials-science
segment-anything-2
lora
Instructions to use WUT-AI-AI4Mat/microstructure-sam2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sam2
How to use WUT-AI-AI4Mat/microstructure-sam2 with sam2:
# Use SAM2 with images import torch from sam2.sam2_image_predictor import SAM2ImagePredictor predictor = SAM2ImagePredictor.from_pretrained(WUT-AI-AI4Mat/microstructure-sam2) 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(WUT-AI-AI4Mat/microstructure-sam2) 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
| { | |
| "model": "SAM2.1 Hiera Base+", | |
| "source_code": "https://github.com/WUT-AI-AI4Mat/Segmentation-methods-evaluation-for-quantitative-microstructure-analysis", | |
| "checkpoint_count": 7, | |
| "checkpoints": [ | |
| { | |
| "dataset": "Aachen-Heerlen", | |
| "task": "binary_segmentation", | |
| "num_classes": 2, | |
| "fine_tuning_route": "lora_and_mask_decoder", | |
| "path": "checkpoints/Aachen-Heerlen/sam2_lora_decoder_best.pth", | |
| "size_bytes": 19068232, | |
| "sha256": "da7ffbb7dcf2fa0ab7278fb88ed3654e90d1cef2fcba00b18b977ae4c5ced313", | |
| "requires_base_checkpoint": "sam2.1_hiera_base_plus.pt" | |
| }, | |
| { | |
| "dataset": "EBC", | |
| "task": "multiclass_semantic_segmentation", | |
| "num_classes": 3, | |
| "fine_tuning_route": "lora_mask_decoder_and_class_tokens", | |
| "path": "checkpoints/EBC/semantic_sam2_best.pth", | |
| "size_bytes": 19072973, | |
| "sha256": "33a37f95eb3d50485038da3e0dc8494f469bd11c5bd4e3c09ccd10956f150524", | |
| "requires_base_checkpoint": "sam2.1_hiera_base_plus.pt" | |
| }, | |
| { | |
| "dataset": "EMPS", | |
| "task": "binary_segmentation", | |
| "num_classes": 2, | |
| "fine_tuning_route": "lora_and_mask_decoder", | |
| "path": "checkpoints/EMPS/sam2_lora_decoder_best.pth", | |
| "size_bytes": 19068232, | |
| "sha256": "3551a19ecc984fb999cdb7b1475ec258776e0dfdebdd4caedb91ad102df6eb39", | |
| "requires_base_checkpoint": "sam2.1_hiera_base_plus.pt" | |
| }, | |
| { | |
| "dataset": "Grain", | |
| "task": "binary_segmentation", | |
| "num_classes": 2, | |
| "fine_tuning_route": "lora_and_mask_decoder", | |
| "path": "checkpoints/Grain/sam2_lora_decoder_best.pth", | |
| "size_bytes": 19068232, | |
| "sha256": "7bb0e3036b685eddb1c9b6d4ce3f62c3ce33d4cad971f9d6ae4913601566d37e", | |
| "requires_base_checkpoint": "sam2.1_hiera_base_plus.pt" | |
| }, | |
| { | |
| "dataset": "MetalDAM", | |
| "task": "multiclass_semantic_segmentation", | |
| "num_classes": 5, | |
| "fine_tuning_route": "lora_mask_decoder_and_class_tokens", | |
| "path": "checkpoints/MetalDAM/semantic_sam2_best.pth", | |
| "size_bytes": 19075021, | |
| "sha256": "5031b5040d1f05d65edd4b53ef8cddd135d7848ff57bab7db3ea2b6a90de7f0b", | |
| "requires_base_checkpoint": "sam2.1_hiera_base_plus.pt" | |
| }, | |
| { | |
| "dataset": "Super", | |
| "task": "multiclass_semantic_segmentation", | |
| "num_classes": 3, | |
| "fine_tuning_route": "lora_mask_decoder_and_class_tokens", | |
| "path": "checkpoints/Super/semantic_sam2_best.pth", | |
| "size_bytes": 19072973, | |
| "sha256": "d9b8fdc275efa1c58c40287777a7d2c72c0c4c9a66f71439fb946c4acfacac1d", | |
| "requires_base_checkpoint": "sam2.1_hiera_base_plus.pt" | |
| }, | |
| { | |
| "dataset": "UHCS", | |
| "task": "multiclass_semantic_segmentation", | |
| "num_classes": 7, | |
| "fine_tuning_route": "lora_mask_decoder_and_class_tokens", | |
| "path": "checkpoints/UHCS/semantic_sam2_best.pth", | |
| "size_bytes": 19077069, | |
| "sha256": "9188cfc3d8ffe9aeefa26b65129223726d2fa9742cd343b94578291e260bdd64", | |
| "requires_base_checkpoint": "sam2.1_hiera_base_plus.pt" | |
| } | |
| ] | |
| } | |