Skip to content
New issue

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

Improve fingertip calibration performance #1218

Merged
merged 3 commits into from Jul 14, 2018

Conversation

ChingT
Copy link
Contributor

@ChingT ChingT commented Jun 25, 2018

Adopt CNN methods for hand and fingertip detector to improve the accuracy and robustness of the detection.
GPUs will be utilized if they are available.

Copy link
Contributor

@papr papr left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I would like to add a fallback mechanism in case that torch is not installed. Else we will have to force everyone to install it. See the implementation proposal in the __init__.py comment

---------------------------------------------------------------------------~(*)
'''

from . fingertip_calibration import Fingertip_Calibration
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Please use the fully qualified import instead of relative imports:

from calibration_routines.fingertip_calibration import Fingertip_Calibration

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

try:
    import torch
    from . fingertip_calibration import Fingertip_Calibration
except ImportError:
    from calibration_routines.fallback_fingertip_calibration import Fingertip_Calibration

fallback_fingertip_calibration.py would implement a dummy calibration plugin that shows an info text with a warning that torch is required for the actual plugin to work.

import torch
from .models.unet import UNet
from .models.ssd_lite import build_ssd_lite

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Please use the fully qualified import instead of relative imports as I mentioned above.

Use the fully qualified import
Follow the Best of the Best Practices (BOBP) Guide for Python
Copy link
Contributor

@papr papr left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Very nice application of yesterday's style seminar!

@mkassner mkassner merged commit 157daf2 into pupil-labs:master Jul 14, 2018
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

3 participants