search

UX-Decoder / Semantic-SAM

[ECCV 2024] Official implementation of the paper "Semantic-SAM: Segment and Recognize Anything at Any Granularity"
2.28k stars 109 forks source link

$UNUSED$ criterion.empty_weight, Ckpt Shape: torch.Size([2]) #99

Open sunwoo76 opened 3 months ago

sunwoo76 commented 3 months ago

when i condut python script for inference.

Script...

from semantic_sam import prepare_image, plot_results, build_semantic_sam, SemanticSamAutomaticMaskGenerator
original_image, input_image = prepare_image(image_pth='examples/dog.jpg')  # change the image path to your image
#mask_generator = SemanticSamAutomaticMaskGenerator() # model_type: 'L' / 'T', depends on your checkpint
semantic_sam = build_semantic_sam(model_type='L', ckpt='./Semantic-SAM-checkpoint/swinl_only_sam_many2many.pth')
mask_generator = SemanticSamAutomaticMaskGenerator(semantic_sam, level=[3]) # [1] and [2] for semantic level.
masks = mask_generator.generate(input_image)
plot_results(masks, original_image, save_path='./vis/')  # results and original images will be saved at save_path

Error

$UNUSED$ criterion.empty_weight, Ckpt Shape: torch.Size([2])

Is there anyone to solve this error?

FengLi-ust commented 3 months ago

Hi, I believe this is not an error, is it only a warning?