czero69 / acomoeye-nn Goto Github PK

I'd like to build a similar dataset, while, how to label the ground truth of the collected image?

best wishes

Hi！

1. What is affine calibration? Why the error will fall through it :)
2. For NVGaze-AR，“we gathered data from 10 subjects” from NVGaze paper，so what means "NaGaze-AR(2/40)" in your readme.md?
3. I found that in the NVGaze-AR dataset, the label is in the range of -1 to 1, but in the synthetic data set, the label is in the range of -90 to 90. Is it because the former is expressed in radians and the latter is expressed in degrees?
4. The input of the network is 127 * 127. If I want to test on the NVGaze data set, can I directly scale the image from 640 * 480 to 127 * 127?

I would be very appreciated if you can help me:)
Thanks and regards.

Hello,
In the paper they mentioned that they have created two datasets:

1. a real dataset via an eye tracker device
2. a synthetic dataset
   How they generated the second dataset (that infrared synthetic data)? Is it generated by UnityEyes?

Thank you

I am trying to follow this page and write a model in PyTorch. However, I am not sure about how to divide the NVGaze dataset for training/validation/testing. Could you give some insight into how you did it for both real and synthetic datasets?

1. Do you already have the divided txt/csv that I can use?
2. How long does it usually take to train on acomo dataset and NVGaze dataset?
3. I am new to the field and using PyTorch, is there anything I should keep in mind while porting this to PyTorch?