Comments (6)
For example, we assume the output of conv1 is 12012096. We can use slice layer to divide the conv1 into conv1_1(12012048) and conv1_2(12012048) and then we use eltwise layer to get the output(12012048) by computing the max value between two groups of feature maps.
from face_verification_experiment.
Ok, I understand it now. So if I would like to train the model with ReLU layers instead of MFM, I would replace the layers convolution-pooling-slice-eltwise with convolution-pooling-ReLU, am I right?
from face_verification_experiment.
The order should be convolution-ReLU-pooling in theory, but I think it doesn't influence the results whichever orders you choose.
from face_verification_experiment.
Ok! Yes, it should be the same.
Regarding to the same paper I have another question. "The learning rate is set to 1e-3 initially and reduce to 5e-5 gradually". Did you use any specific learning rate policy (step down, exponential decay...)? Or was it a fixed learning rate (1e-3), manually decreased to 5e-5? Thanks!
from face_verification_experiment.
The policy of learning rate is fixed and I manually changed it if the loss isn't decreased for a long time.
from face_verification_experiment.
Ok, understood! Thank you very much
from face_verification_experiment.
Related Issues (20)
- There may be some errors in the 'labels' HOT 3
- Where do you get the 5 facial points for MSCELEB dataset. Do you use some other model to find the facial points ? HOT 1
- Xavier vs Gaussian HOT 1
- I feel the size of the trainning data doubt HOT 1
- no an issue but a doubt HOT 2
- about lfw labels in model C-LightenedCNN_C_lfw.mat HOT 3
- Error occurred when computing accuracy
- Query
- no such file in your clean list
- Eltwise层名字拼写错误有影响吗?
- MegaFace Evaluation: it generated 'OpenCV Error' when running experiment.py with own features HOT 1
- hello,your model A and B is small,why your model C is bigger than B by using the same cnn architecture HOT 1
- can't get the same result HOT 3
- How to use fine tuned model to do classification for an image in light CNN?
- Any architecture patent information HOT 1
- the issue about architecture
- LightenedCNN_A_deploy.prototxt
- The evaluation of CASIA-NIR2.0
- Request Pretrained lightenedCNN model in .mat format HOT 1
- Computation of rank 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 face_verification_experiment.