Comments (4)
This is a parameter used in relative-root (e.g., root keypoint is the index 0 keypoint) 3D human pose estimation since we only calculate the errors under zero-root 3d pose instead of absolute 3d positions under the camera coordination.
If you have no such constraint in your task, you can set it as False.
from smoothnet.
This is a parameter used in relative-root (e.g., root keypoint is the index 0 keypoint) 3D human pose estimation since we only calculate the errors under zero-root 3d pose instead of absolute 3d positions under the camera coordination. If you have no such constraint in your task, you can set it as False.
I would like to ask again, what is the problem that PA-MPJPE index has always been nan while other indicators are normal
from smoothnet.
This is a parameter used in relative-root (e.g., root keypoint is the index 0 keypoint) 3D human pose estimation since we only calculate the errors under zero-root 3d pose instead of absolute 3d positions under the camera coordination. If you have no such constraint in your task, you can set it as False.
It occurred to me that if I only had one feature point it would be inappropriate to use the PA-MPJPE index because there was no way to standardize it
from smoothnet.
If you do not need to evaluate PA-MPJPE, you can ignore or uncomment it.
This is a specific metric in the 3D pose. For details, you can check how PA-MPJPE calculates and find where to get the NAN.
from smoothnet.
Related Issues (20)
- Can smoothNet work with hand motion capture (such as mediapipe handlandmarker)? HOT 1
- VIBE Result is different from vibe paper HOT 1
- trian on h36m
- Motion-aware smoothnet HOT 1
- checkpoints is not a pretrained model!!!! HOT 1
- 3D pose estimator results are different from paper HOT 2
- RLE 2D,3D and other dateset HOT 1
- 该网络是否能够即插即用,兼容不同模型与数据集 HOT 1
- how to deal the differernt shape between vibe predicted and gt? HOT 1
- Replicate the Motion-aware SmoothNet HOT 1
- Can i use SmoothNet to inference in realtime video? HOT 4
- What is the experimental setup for human mesh recovery? HOT 7
- SmoothNet SMPL model input HOT 1
- SMPL parameters as input HOT 1
- On the issue of temporal processing of 3DPW datasets HOT 1
- The results of the 3dpw data set are different from your paper HOT 2
- Whether the sliding window is only set during testing?
- The SmoothNet doesn't seem to be working
- How to use?
- Fail to Set UP Environment
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 smoothnet.