We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Can a feature be added that allows you to extract the masks from the videos as well?
The text was updated successfully, but these errors were encountered:
Hi there, If you are still looking for it, here is a tip of enabling it in a previous issue. #26
Here, you can uncomment this line to save the maks. Track-Anything/app.py Line 380 in 57c28bc # args.mask_save = True And you can change the mask save directory here. Track-Anything/app.py Lines 278 to 285 in 57c28bc if interactive_state["mask_save"]: if not os.path.exists('./result/mask/{}'.format(video_state["video_name"].split('.')[0])): os.makedirs('./result/mask/{}'.format(video_state["video_name"].split('.')[0])) i = 0 print("save mask") for mask in video_state["masks"]: np.save(os.path.join('./result/mask/{}'.format(video_state["video_name"].split('.')[0]), '{:05d}.npy'.format(i)), mask) i+=1
Here, you can uncomment this line to save the maks.
Track-Anything/app.py
Line 380 in 57c28bc
And you can change the mask save directory here.
Lines 278 to 285 in 57c28bc
Sorry, something went wrong.
No branches or pull requests
Can a feature be added that allows you to extract the masks from the videos as well?
The text was updated successfully, but these errors were encountered: