Comments (5)
Hi, here are the training parameters on hands17 dataset:
base_lr: 0.001
lr_policy: "step"
gamma: 0.1
stepsize: 200000
display: 100
max_iter: 800000
momentum: 0.9
weight_decay: 0.0005
The batch size is 128, the same with all other experiments on our paper.
We did try to triain the REN model on hands17 dataset. Now I can't remember what exactly the performance was. However, Pose-REN did consistently perform better than REN (for several millimeters, maybe) as far as I can remember.
In case you are now working on the HANDS17 challenge, it should be noted that the pre-trained models on hands17 dataset released in this repo is not exactly the one for our final entry in HANDS17 Challenge. As stated in the challenge document, we used REN as the Init-Net and there were also several improvements/tricks. The pre-trained models on hands17 dataset in this repo are not intended to reproduce our performance in the challenge, but to provide a more stable and accurate hand pose estimator for various applications.
from pose-ren.
Sorry to bother you again.
Would you please tell me the training parameters on hands17 dataset? More specifically, what is the batch size, initial learning rate, learning policy and stepsize or stepvalue, and max training epoch?
By the way, have you trained the REN model on hands17 dataset for comparison? I guess it can achieve the similar subjective performance because the training data is big enough. What's your opinion?
Thanks again.
from pose-ren.
Hi,
- We didn't conduct extensive experiments for the cube size of the cropped hand. Changing it from 300 to 250 should give similar performance, I guess.
- We did online data augmentation in training, that is, augmenting each training sample for random transformations before feeding it for training.
from pose-ren.
OK, thank you~
from pose-ren.
OK, I will try to train again and hope to get as good performance as yours. Thank you!
from pose-ren.
Related Issues (20)
- What do you mean by those icvl_center.txt and msra_center.txt files? HOT 17
- About Data Layer HOT 4
- hi HOT 1
- caffe-pose HOT 1
- the result of kinect realtime test is very terrible! HOT 4
- build demo error HOT 4
- Hi. I have some question about data augmentation and total learning time. HOT 1
- Can I test both hands? HOT 1
- what does “annotation dir” mean? I can’t find this dir in caffe-pose
- caffe-pose HOT 1
- Configurations for RealSense 415 and 435 cameras HOT 11
- About format training data
- CUDA error while loading network HOT 1
- Training code HOT 2
- Running with hands17 net HOT 1
- FPS and system specification HOT 1
- About training HOT 3
- src/testing/predict.py HOT 5
- Will the caffe be essentially first-built? HOT 3
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 pose-ren.