Comments (10)
Hi @ashar-ali ,
-
For MPII on single person, there is a standard split between training and validation samples.
I uploaded the file mpii_annotations.mat with this split. -
We use soft-argmax to regress directly joint coordinates, so the method does not rely on generate GT heatmaps. Please take a look in the paper for more details.
Best,
from deephar.
Oh great,
figured out the soft-argmax thing. But can you please re-verify the link you have provided above for file download? It throws a 404: not found error for me when I click on it. also I remember you released the weights for mpii yesterday. But am not able to access them today.
Would be a great help.
Thanks @dluvizon
from deephar.
The links should work now!
from deephar.
Great,
Thanks a ton for providing these. Do you also plan to release models for pose estimation and/or actiivity recognition for penn_action dataset anytime soon?
Thanks,
from deephar.
I am planning to release the weights finetuned for action, for both Penn and NTU.
from deephar.
Thanks @dluvizon ,
As a sanity check experiment, I was also trying to train the action recognition nets independently for a few epochs.
By independently, I mean I just took the pose ground truth and tried to learn actions with categorical cross-entropy.
Similarly, I extracted the appearance features and pose heat maps offline and tried to learn action categories with hyper parameters mentioned in Appendix B of the paper.
Questions-
-
For both the above cases, I could only get the accuracy close to ~8% on the training data itself in 3-4 epochs. Is this performance expected, or should I get at least some prior accuracy with this kind of offline independent learning?
-
Do you suggest it is better to directly jump to learn jointly with pose estimator networks (after 2 epochs) as mentioned in the paper?
P.S.- all the discussion above is based on experiments I did on Penn Action dataset. Features and probability heat maps were extracted from 2d pose estimator (trained on MPII) as provided by you.
from deephar.
Hi @ashar-ali ,
-
Considering that PennAction contains 15 classes, you are getting random predictions.
In my experience, after 3-4 epochs it should be close to 80% using visual features and a bit lower using only pose. -
If your net is not learning at all, I guess that the problem is not with the pose data.
PennAction is a pretty easy dataset, so even a naive method should attain 80% relatively fast.
from deephar.
Hi @dluvizon ,
Thanks for sharing these insights. I think it could be also because I am not using any kind of data augmentation for now as I was doing a proof of concept and the architecture is not converging because of that.
Now that you have uploaded the full code for action model as well as weights, I will try and see if I can reproduce its results.
Can you please point me to the annotations.mat file for Penn Action Dataset?
If you could just verify if I am encoding the labels right that would be great-
'baseball_pitch', - 0
'baseball_swing', - 1
'bench_press', - 2
'bowl', - 3
'clean_and_jerk', - 4
'golf_swing', - 5
'jump_rope', - 6
'jumping_jacks', - 7
'pullup', - 8
'pushup', - 9
'situp', - 10
'squat', - 11
'strum_guitar', - 12
'tennis_forehand', - 13
'tennis_serve' - 14
from deephar.
Hi,
The file should be OK now at https://github.com/dluvizon/deephar/releases/download/v0.3/penn_annotations.mat
You can check the penn action labels by doing:
print (penn_seq.action_labels)
just after loading the dataset. That gives:
['baseball_pitch' 'baseball_swing' 'bench_press' 'bowl' 'clean_and_jerk'
'golf_swing' 'jump_rope' 'jumping_jacks' 'pullup' 'pushup' 'situp' 'squat'
'strum_guitar' 'tennis_forehand' 'tennis_serve']
which corresponds to your list.
from deephar.
Sounds great,
Thanks a lot for all your help @dluvizon
from deephar.
Related Issues (20)
- Testing Script File : Testing script is not Present HOT 1
- Question about action recognition on NTU HOT 11
- Training hyperparameters for train_penn_multimodel.py HOT 2
- Is the model working for multiple person on a crowded scene ? (Not issue) HOT 1
- Weights for predict bboxes on NTU HOT 2
- No weights provided for the multitask models HOT 3
- Questions regarding Pennaction folder HOT 2
- question about displaying output of pose estimation, action recognition HOT 2
- Training on my dataset HOT 1
- could the network be trained with only action video but no pose images/video? HOT 4
- a quick demo for action recognition HOT 4
- something wrong about the eval_penn_multitask.py HOT 2
- eval_penn_ar_pe_merge.py error HOT 1
- Visualization Issue
- ModuleNotFoundError
- Question about datasets and annotations HOT 2
- Training on custom dataset HOT 1
- Error while training penn mpii multimodel HOT 2
- General question with resepect to paper HOT 2
- run.sh is killed HOT 5
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 deephar.