Comments (5)
Thanks Nicholas, however those stats files are just generated for the example images?, not for my images? I am trying to run it on my own images. Thank you
[Short answer] You don't need to compute stats for your images in inference.py.
[Long answer] Let me give a more detailed explaination on the "stats".
-
The inputs and outputs of the 2D-to-3D lifting model are normalized, which means one can not feed the raw pixel position (e.g., the hand key-point is at (550, 450)) to the model.
-
Two ways of applying normalization are implemented in this repo. The first approach computes the statistics over the whole training dataset, while the second over a single example. This means the first way is dataset-dependent while the second is not.
-
For in-the-wild images, inference.py uses the second way so that the user does not need to compute input key-points statistics over the whole dataset. The user just need to feed the right key-point positions and the normalization is done one subject by one subject.
-
The downloaded "stats" represents the 3D statistics for output unnormalization. This does not affect the input but affects how the output will look like. Since it's computed over H36M, the output will look like the H36M style.
Finally, the repo is about single-frame inference. For extension to video input I suggest taking a look at https://github.com/facebookresearch/VideoPose3D.
from evoskeleton.
As described in the docs, the stats can be downloaded at https://drive.google.com/file/d/158oCTK-9Y8Bl9qxidoHcXfqfeeA7qT93/view
In
examples/inference.py
, how do I calculate stats passed to unNormalizeData()from evo_skeleton.dataset.h36m.data_utils import unNormalizeData
, as I am using my own images, and can't create a newstats.npy
for my images. I would eventually like to pass video to it too.Thanks in advance
from evoskeleton.
Thanks Nicholas, however those stats files are just generated for the example images?, not for my images? I am trying to run it on my own images. Thank you
from evoskeleton.
Thanks for the explanation, that clears my confusion
from evoskeleton.
Issues will be closed if there is no new discussion for more than one month. Re-open if needed.
from evoskeleton.
Related Issues (20)
- training input size and inference input size not match HOT 32
- Location of the hip/pelvis joint? HOT 6
- camera params in cameras.npy HOT 2
- generating other poses from a known pose HOT 7
- ImportError: No module named libs.hhr.config HOT 3
- AttributeError: module 'libs.utils' has no attribute 'utils' HOT 5
- 2d poses from 3d pose HOT 11
- 2D to 3D with own data HOT 6
- weird 3D Pose
- Input of the plot_distribution in anglelimits.py HOT 4
- Inconsistency between pretrained HRNet 2D detector and twoDPose_HRN.npy HOT 7
- Data Preprocessing when test on 3dhp dataset HOT 3
- Obtain 3D skeleton with 2D key-points as inputs using SMPLify by own data HOT 3
- Source of 2D keypoints when eval on 3dhp dataset HOT 1
- Preprocessed npz file of HRNet HOT 1
- About 2D anchor of the cropped image HOT 3
- Regarding h36m image HOT 5
- 模型下载问题 HOT 1
- annotate_3D.py
- Fine-tuning of HRNet 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 evoskeleton.