Comments (21)
With the large training dataset, the model convergence is slow. We use two Titanx (old version) and train for six days. You can change the batch size from 10 to 8 to speed it up a little bit. We did not try a batch size below 8. I will plot the loss with respect to iterations and post here.
from realtime_multi-person_pose_estimation.
Hi all, I am really sorry for my late response. I graduated from CMU so it is not easy to access the old files again. But I plot the loss for the two levels here:
All the terminal output is: https://github.com/ZheC/Realtime_Multi-Person_Pose_Estimation/blob/master/training/example_loss/output.txt
The code to plot the loss is here: https://github.com/ZheC/Realtime_Multi-Person_Pose_Estimation/blob/master/training/example_loss/plotLoss.sh
from realtime_multi-person_pose_estimation.
@ZheC Can you post the loss vs iterations curve again?
from realtime_multi-person_pose_estimation.
Thanks a lot!
from realtime_multi-person_pose_estimation.
I deleted the wrong figure posted before, this will be updated soon.
from realtime_multi-person_pose_estimation.
Hi, is this the loss of L1 or L2?
from realtime_multi-person_pose_estimation.
hi, any updates? :D
from realtime_multi-person_pose_estimation.
@yq1011 what's your final result? Was it converge? How long did you train for it? I am training this model for days, and it's not so fast as ZheC said, I use 4 GPUs trained for 2 days , and it's about 2w iterations...
from realtime_multi-person_pose_estimation.
I think we should talk in terms of epochs instead (the training is printing that). @ZheC when you mentioned that you were using 2 x Titan X with batch size of 10 that probably meant that the actual batch size was 20 (10 per gpu) ?
from realtime_multi-person_pose_estimation.
I have the same problem as you @yq1011 .
Did you get a converged loss finally?
from realtime_multi-person_pose_estimation.
@ZheC Hi, would you be able to post the loss curve again? I would like to compare with the model when I train it locally to make sure it is performing comparably. Thanks!
from realtime_multi-person_pose_estimation.
@ZheC Can you post the loss curve?
from realtime_multi-person_pose_estimation.
@ZheC at least you can tell the last loss value so that we can compare.
from realtime_multi-person_pose_estimation.
@ZheC Thanks for sharing!!
from realtime_multi-person_pose_estimation.
@ZheC Hi, I set the parameters based on your terminal output and train, but it is terminated about iteration 1200 without any log shown on the screen. Do you have any idea about this? Thanks.
from realtime_multi-person_pose_estimation.
Hi,@ZheC,thanks for your great work! I have some questions about train the pose model. In your https://github.com/ZheC/Realtime_Multi-Person_Pose_Estimation/blob/master/training/example_loss/Loss_l1.png
https://github.com/ZheC/Realtime_Multi-Person_Pose_Estimation/blob/master/training/example_loss/Loss_l2.png
,But there was only the result about iterations of # 25,0000. However, in the Openpose
https://github.com/CMU-Perceptual-Computing-Lab/openpose
the https://github.com/CMU-Perceptual-Computing-Lab/openpose/tree/master/models/pose/coco
the model was shown is pose_iter_# 440000.caffemodel, I would like to know whether it is only 250000 iterations or 440000 iterations.
Thanks for you attentions.
from realtime_multi-person_pose_estimation.
Are there someone getting the same results in the paper , and trying to train the small model only 2-stages used?
from realtime_multi-person_pose_estimation.
@yq1011 Did you get the same results as the paper?Thanks
from realtime_multi-person_pose_estimation.
@Ai-is-light I use 440000 iterations' model. I pick up the best iteration based on the evaluation score on a validation set. I keep testing the accuracy of the trained models at different iteration. The best iteration is not fixed for different models. So I think probably you want to follow the same way to pick up your trained model.
from realtime_multi-person_pose_estimation.
Hi @ZheC , I have a question that how much the effect the number of images being used in the evaluation have to the evaluation score. I saw on your paper you chosen 1160 images randomly. Why not choose the whole validation set?
from realtime_multi-person_pose_estimation.
Hello,
How to choose the stepsize for a given iteration?
The default parametrs from the author is step size=13106 for iterations=600000
Thank You
from realtime_multi-person_pose_estimation.
Related Issues (20)
- training loss is strange,for openpose body_25 model training HOT 9
- training HOT 3
- training of images with no humans HOT 1
- Retraining with lesser COCO images.
- Pretrained model? HOT 2
- Is it ok to use "CMU-Perceptual-Computing-Lab/caffe" instead of "caffe_train" for training?
- How can I find models and papers about body25?
- Problem about train on own dataset HOT 3
- Dataset problem
- Low resolution images
- Limb width is hardcoded?
- bug when generating mask
- mxnet version
- MMC demo
- Extracting keypoints to json file HOT 2
- finetuning the model HOT 12
- heatmap evaluatin metric HOT 1
- bash getData.sh wget didn't work HOT 4
- Error in gason.m
- Where can I download matconvnet_coco_openpose_model.mat ? 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 realtime_multi-person_pose_estimation.