Comments (4)
swook
commented on August 19, 2024
Hi,
I always pick an arbitrary stopping epoch or step that is consistent across
all folds.
The reason is that in the 15-fold evaluation setting used in prior papers,
there was no validation set defined. This could not be defined as the final
test performance is on different people and thus a true validation set
should be formed of people neither in the training nor test set. Due to the
size of MPIIGaze (15 people) this isn't feasible.
The configuration in thus repository should include a good stopping
step/epoch already.
Best,
Seonwook
…On Fri, 12 Apr 2019, 06:45 thinkrc, ***@***.***> wrote:
Thanks for your work! I run the dpg_train.py and performed
leave-one-person-out evaluation on MPIIGaze. What is the reasonable way to
count the result, the mean of 15-fold final test results or the mean of
15-fold best live test results?
—
You are receiving this because you are subscribed to this thread.
Reply to this email directly, view it on GitHub
<#19>, or mute the thread
<https://github.com/notifications/unsubscribe-auth/AAuI0ruJ8Lzgj33nUxBSi5Pk7dBxDH2kks5vgA9_gaJpZM4crUci>
.
from gazeml.
thinkrc
commented on August 19, 2024
Thanks for your reply! The messages.log shows that the DPG in this repository runs final test at step 052499 across all folds. I calculated the mean angle error of 15 folds at 052499 step and reaches 4.90 degrees on MPIIGaze (not 4.63 degrees). I repeated the experiment three times and got similar results. Could you give some suggestions?
from gazeml.
swook
commented on August 19, 2024
Ach... I'm very sorry about that. I must have made a mistake in the process of making this available.
I can't promise that I can look into this ASAP, but I will try, and keep you updated.
from gazeml.
swook
commented on August 19, 2024
I went to check my experiment logs and found a discrepancy between my best configuration there, and the version committed to this repo...
Please find the changes required for a perf. boost at commit 7087b9e
from gazeml.
Related Issues (20)
- Theta and Phi
- Train-data parameter in elg-demo file
- Video_out is not defined when using record_video for testing elg demo
- Running demo elg using CPU gives overlapping frame of original image and segmented eye image instead of segmented eye image in top-left corner
- Could you share code to test on different data sets?
- can_use_eye, can_use_eyelid and can_use_iris in elg_demo.py are False HOT 1
- Stuck with --from_video option HOT 3
- Could you please tell me where the pre-training weight should be placed in the Windows system?
- The project only has elg demo. how to run dpg demo
- RuntimeError: Error deserializing object of type int64 while deserializing a floating point number.
- Some questions about the 'unityeyes.py'
- iris_centre is not mean of iris_landmarks?
- About train/test data in MPIIGaze.h5
- Collaboration offer to help progress
- Gaze Vector Accuracy HOT 1
- elgo_demo.py stucks after video is closed HOT 1
- python and tensorflow version
- [TUTORIAL] How to save ELG model to .onnx and further to TensorRT .engine HOT 1
- Long proc time when running elg_demo.py on CPU HOT 1
- Can not get pre-trained weights
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from gazeml.