Comments (10)
Hi,
Those results are a bit surprising, as the error for the IBUG dataset you obtained seems to be much lower than any paper I have seen so far. Are you sure you are measuring this correctly?
If you want, you can place the models you have in some public data storage like Dropbox and send me the link, so I can re-evaluate it. This would help rule out the possibility of measurement error.
Best regards,
Marek
from deepalignmentnetwork.
@MarekKowalski Hi, in the training phase, did you hold the learning rate fixed to be 0.001? If I use learning rate 0.001, then the loss in stage 2 cannot drop.
from deepalignmentnetwork.
Yes, the learning rate was kept the same. When you are training the second stage are you updating the parameters for both stages or just stage 2?
In my experience, if you are updating parameters of both stages at the same time, the error takes much longer to drop.
from deepalignmentnetwork.
@MarekKowalski Actually, I only update parameters for stage 2, but I can see error drop only when I lower down the learning rate.
from deepalignmentnetwork.
That's surprising, for how long are you trying to see if the error starts droping? Also, is that in your implementation or in the one in this repo?
from deepalignmentnetwork.
@MarekKowalski I mean in my implementation, I only observe error drop with my learning rate lower down. And, someone has found almost the same problem in another tensorflow implementation. I've double checked the functionality of the self defined layer and found no problem, I don't know if the Adam is implemented differently in theano, or Batch Norm is implemented differently.
from deepalignmentnetwork.
I agree that it might be because TF has a different implementation of some part of the learning algorithm or the network.
from deepalignmentnetwork.
@MarekKowalski @mariolew Hi
In my implementation on tensorflow, I have not found this problem.
i use a private dataset , and epoch is [15,45]
from deepalignmentnetwork.
i want to know if both stages share parameters in the same layer?
from deepalignmentnetwork.
No the parameter values are not shared between the stages.
Marek
from deepalignmentnetwork.
Related Issues (20)
- Question about bestFit function HOT 2
- How to get my own meanFaceShape.npz HOT 1
- about DANtesting.py problem HOT 10
- How to predict without face detection? HOT 1
- some questions about GeneratePerturbations function HOT 2
- How to train a model of 5 landmarks HOT 1
- Communication group
- Too difficult to reimplement your project ! HOT 5
- how fast in average do it predict an image without gpu HOT 2
- how compute the meanshape s0 ? HOT 4
- cannot get challengingSet.npz successfully HOT 1
- Number of trainable parameters HOT 1
- How to Get Aligned Face? HOT 4
- How to train the DAN-Tracking.npz model? HOT 3
- some other networks do not converge in the second stage. HOT 3
- ValueError: mismatch: got 47 values to set 49 parameters
- cannot run ImageDemo.py HOT 2
- About meanshape.npz HOT 7
- Memory Error, system requirement HOT 1
- Error HOT 1
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 deepalignmentnetwork.