Comments (3)
- Given a linear predictor, concatenating features is equivalent to predicting based on individual feature and summing them up.
- I would run the detector with an image pyramid but without 2X upsampling. If you give up 2X, it should only hurt the performance on tiny-sized faces.
- That is strange. What I saw when I add hard negative mining into our detector is that results look qualitatively much nicer because of less false positives, but it does not yield much improvement in the final accuracy.
- This is what I learned from how FCN is trained. I believe they use x100 smaller learning rate when training FCN8s at once but I found x10 works fine.
- I believe there are papers initialize predictor with zero weights, such as FCN.
from tiny.
Hi @peiyunh
Thanks for your amazing work. I'm new to deep learning and am interested to pick up small faces. If I may ask a simple question on the training dataset:
Q) If I have generally large faces in my datasets (example, a face occupying 120 pixels x 70 pixels from a larger image resolution of 640 x 480), do I have to crop the face out and resize to say 30 pixels x 30 pixels for the region of interest and crop the face together with the context and resize to say 60 pixels x 60 pixels before training?
Thank you for your guidance!
from tiny.
Your idea makes sense and should fit better into a two-stage architecture, such as Faster RCNN.
from tiny.
Related Issues (20)
- How to train with my database? HOT 4
- How to pre-process the training data HOT 1
- hr_res101('train') error: vl_argparse error HOT 1
- How to speed up the process to use it with webcamera?
- Which layer can we use for face recognition params?
- Where is ellipse linear regression?
- how to convert the text file to mat file like wider face ?
- Question on train detector on my own dataset HOT 1
- Training on own data HOT 1
- Initialise Resnet model HOT 1
- Foveal descriptor HOT 1
- too much training time
- I have the same question too. It confuse me a few days. I read part of the code, it seems that the output 'score_cls' is a 25 depth matrix or tensor which corresponding to each 'templates'. I just don't understand the why?? If someone know it, I'm very thanksful to you. HOT 2
- hr_res101.mat broken link HOT 2
- Can not download model HOT 1
- new issue
- How can we use our model to detect faces with camera in real time? HOT 1
- About the function 'nms_mex' error HOT 1
- nvcc fatal: Unsupported gpu architecture 'compute_86'
- Links to pretrained weights broken? 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 tiny.