Comments (5)
I believe this can be done by the following steps:
- Add the 12-net layers to the 24-net .prototxt files (concatenating the fully connected layers as shown in the paper)
- Transplant the trained 12-net parameters to the multi-resolution net, and set the local learning rate to 0, as shown here
- Train the net
from cnn_face_detection.
Dear anson0910 :
Thank you for your reply!
I am sorry to trouble you again . When I train the caffemodel of 12-net, I used 18,000 positive faces collected from the AFLW datast, and about 180,000 non_face patchs, the model converge ,,,,,but when I use the 12-net caffemodel to test , the confidence of detect windows are all 0.5,,,,,,,,,then I augument the number of positives from18,000 to 54,000,,,,I get the same result,,,,,,,
Have you ever met this kind of problem?
Thank you !
from cnn_face_detection.
If during training, the accuracy on the validation set is higher than 0.9, 12-net should perform great during testing.
However, if the accuracy stays fixed at 0.5, you may need to stop the training, and start over again.
It should be an issue related to the initialized parameters' range or learning rate, but just retraining a few times should give the desired result!
from cnn_face_detection.
dear anson0910:
if i want to implement the multi-resolution net , how can i train the net?
i mean we must put a pair of images to the net, so how can we confirm that the each image in the pair can be pass into the net at the same time ?
from cnn_face_detection.
Hi,
I think you can simply create the lmdb files as before, and for example in face_24's train_val file, add a data layer specifying the data_param.
from cnn_face_detection.
Related Issues (20)
- approximate Threshold T1 and T2 HOT 4
- About the result after running HOT 4
- Number of face detected in 2002/07/19/big/img_352.jpg HOT 1
- About the training step HOT 4
- A question about the cascade cnn HOT 2
- About the face size in create_face_12c.sh HOT 6
- How to train calibration nets?
- 3000 images without any faces (negative images) HOT 2
- Speed Problem HOT 1
- AFLW new website can't find AFLW_Faces.txt HOT 1
- create negative_py HOT 9
- train_val.prototxt about FCN HOT 3
- many false face HOT 1
- calibration_AFLW.py new code HOT 5
- Resize images when creatiing LMDB file HOT 2
- About the training step HOT 1
- About the test result HOT 1
- How to get the file face12c_full_conv.caffemodel HOT 2
- How to python caffe to test the model
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 cnn_face_detection.