Comments (8)
Hi, I haven't released the training procedure, though the code is there. I plan to release the complete training code within next month. However you can already train it with the existing code, you just have to prepare the data yourself. Here are the instructions:
For pre-processing, the crucial part is the scaling of input images:
persons have to have reference height of 400px.We scale training images by scale = refHeight/(8*headSize)
refHeight is in your case 400. headSize is computed by the following
function:function headSize = util_get_head_size(rect)
SC_BIAS = 0.6;
headSize = SC_BIAS*norm([rect.x2 rect.y2] - [rect.x1 rect.y1]);In this case rect is a a rectangle around person's head.
This will result in a more or less optimal scale for our model.
At training time it also does +- 15% scale augmentation, so there is some
invariance as well.
You can also do +- 30% scale jitter.I attached the files necessary for training (train prototxt for
resnet-101), train_data.txt is the description of training
data, format is pretty easy:0 <- zero-indexed image id, sequential
/home/andriluk/IMAGES/human_pose_dataset/dataset/dataset_release_candidate1//train-v15/singlePerson/h400-deltaCrop-130-130-bCropIsolated/im00005_1.png
<- image
3 <- number of channels, always 3
391 <- image height
302 <- image width
14 <- number of keypoints present in the image
1 175 261 <- 1-indexed keypoint id, x, y in pixel coordinates
2 173 178
3 144 122
4 193 124
5 203 146
6 200 153
7 166 144
8 131 107
9 163 111
10 223 122
11 224 159
12 220 207
13 199 126
14 220 82I use SGD for training, pretrain it at LR=0.001, then raise it for 0.002
train for ~400k iters, then drop to 0.002 for 300k and then to 0.001 for
another 300k, you don't have to do it exactly the same, you can play with
it.
I attached files with training model definitions, example of a file with the training set and script how to run it. Hope it helps.
from deepcut-cnn.
Hey,
I've re-implemented this ConvNet in TensorFlow, here's the code: https://github.com/eldar/pose-tensorflow. It is more hacker-friendly and I added some training instructions. Sorry, that it took me a while :)
Cheers,
Eldar.
from deepcut-cnn.
@eldar : I am trying to re-proceduce your work.
But in file pose_data_layer.cpp, I saw that there is hard code for 'joints_stats_file'
auto joint_stats_file = this->layer_param().pose_data_param().has_joint_pairs_stats() ?
this->layer_param().pose_data_param().joint_pairs_stats() :
"/BS/eldar/work/pose/exp/mpii-all-joints-reg/data/all_stats.txt";
Could you tell me, what is the meaning of file 'all_stats.txt' and how to get it.
Thank in advance
from deepcut-cnn.
@tiepnh
Have you solved this problems? I also want to re-proceduce this amazing work!
from deepcut-cnn.
@mindcont : sorry, not yet. I still wait for @eldar 's answer. I'm trying read the code, but still cannot figure out that the all_stats.txt means
from deepcut-cnn.
Thank you for your reply, I am also working on it , any progress I will let you konw
@mindcont : sorry, not yet. I still wait for @eldar 's answer. I'm trying read the code, but still cannot figure out that the all_stats.txt means
from deepcut-cnn.
Hi @mindcont , do you have any update from this work ??
I tried to train the new network by remove joint_stats_file and also remove "regression to other part" in network. And it worked. But, there is no additional regression step
from deepcut-cnn.
Hi @tiepnh
Thanks for your notify,sorry to reply to you so late, I also working on combine network,get some inspire from
-- | -- |
---|---|
deepcut | https://github.com/eldar/deepcut |
cpm | https://github.com/shihenw/convolutional-pose-machines-release |
personalized_pose | https://github.com/jjcharles/personalized_pose |
pose-hg-demo | https://github.com/anewell/pose-hg-demo |
etc.Until now did not get good results
from deepcut-cnn.
Related Issues (19)
- Error when compile the transform_image.cpp : : āt1_pā does not name a type HOT 4
- make pycaffe issue HOT 1
- /BS/eldar/work/pose/exp/mpii-all-reg/data/all_stats.txt HOT 2
- Build in window
- How can I get array joint?
- Error in ubuntu while testing my own image HOT 4
- ResNet-50 HOT 5
- can i use your single person model to complete mulit person task?
- Problem in Demo HOT 1
- Out of memory while running demo HOT 11
- Can i know where to enable c++11 ? HOT 4
- Is it allowed to use for commercial purposes?
- make all pycaffe issue HOT 2
- does not compile under ubuntu 14.04 or 16.04 HOT 2
- confusing mix of Makefile.config.example and cmake HOT 1
- Multi-person
- ID'ing detectors
- how to crop a single person img from the src image(MPII dataset) HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
š 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. ššš
-
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 ā¤ļø Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from deepcut-cnn.