Comments (6)
can you tell me where is that assertion?
from posefix_release.
thanks for your comment. Its' in lib/tfflat/base.py line 307!
from posefix_release.
How do you train? That block is to use testing result of any other pose estimation model on the training set. That result is used when PoseFix try to synthesize not annotated joint in the training set. For example, in COCO dataset, some joints are not annotated. So, I use other pose estimation method's result when synthesize of not annotated joint. If you place result.json
in test_on_trainset
like README, there should be no problem.
from posefix_release.
I use my own dataset, and I use the result.json of hrnet model. it emerges error like the length of gt is 7, and length of out is 6. And Actual Image has 7 objects, but test result(hrnet) of image detect the 6 objects.
from posefix_release.
You should test your method using groundtruth bbox on the training set.
from posefix_release.
thks for your coment! :)
from posefix_release.
Related Issues (20)
- About how to apply this work on my own data? HOT 17
- calculate miss_prob , jitter_prob and inv_prob on other dataset HOT 1
- Statistics on latency and throughput HOT 1
- demo for a single image HOT 4
- About Fig.5 in your paper HOT 2
- Can we directly implement Posefix on Inference phase or should we have to do it from training itself? HOT 3
- Combining all the three datasets HOT 3
- I can't use my GPU? HOT 1
- Find data HOT 6
- converting model to ONNX for C++ inference with TensorRT HOT 3
- Is there any plan to provide pre-trained weights available? HOT 2
- inefficient heavy-CPU training HOT 7
- input image normalization HOT 4
- the reason behind the usage of render_onehot_heatmap for training target instead of render_gaussian_heatmap HOT 3
- the usage of the softmaxed heatmaps as the keypoint confidence scores
- Format of result.json HOT 1
- Missing modules in requirements
- FileNotFoundError: [Errno 2] No such file or directory: 'tmp_result_0.pkl' and IndexError: list index out of range HOT 3
- tensorflow 2
- I appreciate your work!
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 posefix_release.