Comments (5)
Hi @melgor - thanks for reporting this!
The negDist < alpha
is indeed inconsistent with the FaceNet paper.
I've updated the code to your second suggestion and added some output info about how many random
negatives are selected in the offline processing. Also posted this to the mailing list at https://groups.google.com/forum/#!topic/cmu-openface/4yk9dO1Z0ww
Interestingly the conditions with negDist < alpha
is satisfied about half the time in the early phases of training, which is what I looked at when I validated this portion of code. For the same random seed and images, Suggestion 1 gives 513 random triplets out of 1006 total triplets, Suggestion 2 gives 490, and the bug (negDist < alpha
) gives 637.
I tested this for later iterations with the nn4.v1
model and the bug is much closer to random as you mention. Suggestion 1 gives 498 random triplets out of 996 total, Suggestion 2 also gives 498, and the bug gives 974!
I've been training a new model with suggestion 1 over the past few days, interested to see how much this improves the accuracy.
-Brandon.
from openface.
Re-opening, I'm having some strange accuracy issues with this. @melgor - have you successfully trained a model with your Suggestion 2?
In the following, I switched from your Suggestion 1 to suggestion 2 at about iteration 45. I don't yet understand why suggestion 2 causes such bad performance. Any ideas?
Since suggestion 1's model was starting to perform better, I've made this the default version for now.
Iter 40
- 0.73 avg LFW accuracy
Latest Iter
- 0.51 avg LFW accuracy.
from openface.
It it really strange. I have one idea why it may work so bad, but still it
will not explain the random guess. I must look it closer.
About my tests, I do not have 12 GB on my card, so I only test 2-step
training (like in Oxford Face paper). And here the result using all three
different sampling strategy are similar and does not produce better feature
representstion than original net. So sth is wrong here.
I think that you should stay at Suggestion 1, it may be better is some
cases.
9:58 PM pon., 09.11.2015 Brandon Amos użytkownik [email protected]
napisał:
Re-opening, I'm having some strange accuracy issues with this. @melgor
https://github.com/melgor - have you successfully trained a model with
your Suggestion 2?In the following, I switched from your Suggestion 1 to suggestion 2 at
about iteration 45. I don't yet understand why suggestion 2 causes such bad
performance. Any ideas?Since suggestion 1's model was starting to perform better, I've made this
the default version for now.[image: loss]
https://cloud.githubusercontent.com/assets/707462/11046106/631a61e6-86f9-11e5-8735-ed6f87b00f15.png
Iter 40
- 0.73 avg LFW accuracy
[image: roc]
https://cloud.githubusercontent.com/assets/707462/11046189/ecfe92b0-86f9-11e5-8d99-ef577e36bb37.png
Latest Iter
- 0.51 avg LFW accuracy.
[image: roc]
https://cloud.githubusercontent.com/assets/707462/11046103/5f4e8286-86f9-11e5-83e2-9987d73330ff.png—
Reply to this email directly or view it on GitHub
#48 (comment)
.
from openface.
@melgor - suggestion 1 is working well so far. Averaging ~300 random triplets out of 1000 in the offline sampling and almost at the previous net's accuracy.
Epoch 55
Epoch 54
from openface.
Training with suggestion 1 is clearly faster as the experiment from the past week shows, closing this issue. The accuracy hasn't surpassed the existing models, but I'm going to keep the training going.
LFW Experiment, Epoch 142
- Accuracy: 0.8390
from openface.
Related Issues (20)
- File "<ipython-input-20-09d287cbe6a8>", line 3 HOT 1
- can't able to detect faces when video is passed HOT 1
- WebDemo HOT 1
- ok I have already solved it by copying the shape_predictor_68_face_landmarks.dat file in the same directory as my python file. Thanks. HOT 2
- grid_search.py error ? HOT 1
- openface.align_dlib understanding question HOT 1
- Dokerfile detection:You may setup Docker deployment run configuration following file//Dockerfile//disable this notification HOT 1
- Windows installation problems HOT 3
- I cannot find the nn4.small2.v1.t7 in the models file HOT 2
- Exception: could not convert string to float while running comparison demo
- how can i use head pose tracking or gaze tracking from python code?
- localhost:8000 says Error fetching video from webcam HOT 1
- I am getting error when trying to load the "openface.nn4.small2.v1.t7" with opencv 4.5.1
- how to resolve this issue: predictor = dlib.shape_predictor(p) RuntimeError: Unable to open shape_predictor_68_face_landmarks.dat
- RuntimeError: Unable to open shape_predictor_68_face_landmarks.dat .......i have tried to put this in the same directory also....and downloaded latest version and uncompressed it and still this issue is not getting solved. Please Help HOT 3
- in the compare.py what should i add in the path of Torch network model HOT 1
- OpenFace models in commercial use, not Dlib models
- Why getALLFaceBoundingBoxes(img) return nothing, no erorr, no result. HOT 1
- Python runtime error
- Hehe
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 openface.