search

ziqi-jin / finetune-anything

Fine-tune SAM (Segment Anything Model) for computer vision tasks such as semantic segmentation, matting, detection ... in specific scenarios
MIT License
766 stars 55 forks source link

Forecast! #12

Open HaoranRS opened 1 year ago

HaoranRS commented 1 year ago

Thank you for your warm answer! After finetuning, how do you successfully predict samples?

ziqi-jin commented 1 year ago

The test code will release later, I will make this tool part-time, Haha. If you are interested in the test function, Welcome to PR.

longyangqi commented 1 year ago

The test code will release later, I will make this tool part-time, Haha. If you are interested in the test function, Welcome to PR.

Great work! I have a question: after fine-tuning for the semantic segmentation task, do we still need a prompt to get the seg results in test?