figlab/eyemu

Gaze + IMU Gestures on Mobile Devices

eyemu's Issues

License

Hello there, great work!

Could you please add a license? That would help to assess whether we can also use this code.

Kind regards

Can you also let us know the TensorFlow, Keras and opencv versions used for running this? If possible, please post the requirements. txt file

Is the weight file available best one for prediction? Is it trained with millions of images, such as GazeCapture dataset?

error: invalid path 'Icon?'

Issue occured when ?

• On First Installation

Issue Recreation

• git clone https://github.com/FIGLAB/EyeMU.git
• git checkout master

Log

Cloning into 'EyeMU'...
remote: Enumerating objects: 3303, done.
remote: Counting objects: 100% (9/9), done.
remote: Compressing objects: 100% (9/9), done.
remote: Total 3303 (delta 2), reused 0 (delta 0), pack-reused 3294Receiving objects: 100% (3303/3303), 434.27 MiB | 3.13Receiving objects: 100% (3303/3303), 436.15 MiB | 2.09 MiB/s, done.

Resolving deltas: 100% (2175/2175), done.
error: invalid path 'Icon?'
fatal: unable to checkout working tree
warning: Clone succeeded, but checkout failed.
You can inspect what was checked out with 'git status'
and retry with 'git restore --source=HEAD :/'

Can you please clarify whether facial features are added for training?

In the paper, it has been mentioned that the facial features are added for training the model, but the architecture mentioned in the repo code is not asserting the claim in the paper..

Please clarify ASAP.