Comments (9)
To train a model on the PoseTrack 2018 dataset, I firstly trained a model on the COCO dataset. You can download the pre-trained model in the README
. After that, renamed them from snapshot_140*
to snapshot_0*
and placed them at output/model_dump/PoseTrack/.
Finally, I ran python train.py --gpu 0-1 --continue
after changing dataset name to the PoseTrack in config.py
. No hyperparameters changed from the config.py
.
Unfortunately, I do not have a plan to implement tracking part :(
from tf-simplehumanpose.
@mks0601 Thank you for your detailed replay! After simply debug, I find that I inverted head top and head bottom horizontally by mistake. Which looks like very stupid. After a new training ...
I gets the results as follow:
Loading data
('# gt frames :', 3902)
('# pred frames:', 3902)
Evaluation of per-frame multi-person pose estimation
('saving results to', './out/total_AP_metrics.json')
Average Precision (AP) metric:
& Head & Shou & Elb & Wri & Hip & Knee & Ankl & Total\
& 88.0 & 89.2 & 84.1 & 76.2 & 81.1 & 80.5 & 75.0 & 82.4 \
from tf-simplehumanpose.
Sounds good!
from tf-simplehumanpose.
@mks0601 Hi!! pose track dataset have 15 joints(2 joints are not annotated). How did you handle this?
from tf-simplehumanpose.
Just use pre-trained model on COCO, and set loss zero for not annotated l_ear and r_ear.
from tf-simplehumanpose.
Where did you set the loss to zero in the code?
from tf-simplehumanpose.
I can't remember clearly, but
Please check L86 of main/gen_batch.py
.
joints[:,2] of those joints would be zero.
from tf-simplehumanpose.
I couldn't figure out how to set these 2 keypoints to 0 loss.
But I think its this line?
Also here:
loss = tf.reduce_mean(tf.square(heatmap_outs - gt_heatmap) * valid_mask)
from tf-simplehumanpose.
I think so. The valid mask is generated from joints[:,2]. The mask values would be zero for not annotated joints.
from tf-simplehumanpose.
Related Issues (20)
- Final validation and training loss? HOT 2
- Training stuck with no verbose logs? HOT 4
- How much AP does NMS add? HOT 1
- is it possible to convert this model to tensorflow lite? HOT 2
- where to place mpii_human_pose_v1_u12_1 HOT 4
- which human_detection.json to use? HOT 2
- NMS modules information HOT 2
- Transfer Learning for new/custom dataset HOT 4
- Human detector HOT 2
- Question about using my own data HOT 17
- some queries
- human_detection.json
- Predict keypoints on a single image
- Confuse about get_affine_transform function HOT 1
- Name of the output node
- Queries regarding my generated Test_info and Human_detection JSON files HOT 2
- tensorflow.contrib error in train.py HOT 1
- Confusion about Metrices! Need Clarification HOT 1
- Convert mpii to coco format HOT 2
- Posetrack18 dataset can not download.
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 tf-simplehumanpose.