How to use KMasaki/PowerCLIP-SAM2-ViT-B-16-CC12M with OpenCLIP:
import open_clip model, preprocess_train, preprocess_val = open_clip.create_model_and_transforms('hf-hub:KMasaki/PowerCLIP-SAM2-ViT-B-16-CC12M') tokenizer = open_clip.get_tokenizer('hf-hub:KMasaki/PowerCLIP-SAM2-ViT-B-16-CC12M')
How to use KMasaki/PowerCLIP-SAM2-ViT-B-16-CC12M with sam2:
# Use SAM2 with images import torch from sam2.sam2_image_predictor import SAM2ImagePredictor predictor = SAM2ImagePredictor.from_pretrained(KMasaki/PowerCLIP-SAM2-ViT-B-16-CC12M) 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(KMasaki/PowerCLIP-SAM2-ViT-B-16-CC12M) 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): ...
nielsr