Comments (5)
The scale keeps the height of the person as about 200 px. You should set the scale according to the groundtruth annotation or the detection bounding boxes.
from pytorch-pose.
Hi, thanks for explaining!!
If I did not misunderstand your answer above. I should compute the bounding box height with h=200 x scale
, and with the center coordinates (c0, c1)
, I could compute the y
coordinate of the upper left point with: y1=c1-h/2
. Is this the correct story?
If I am not wrong about the heigt, what about the bounding box width? Shall I treat the bounding box as some rectangle box?
from pytorch-pose.
@CoinCheung
Hi, I also want to train this network on on my own dataset, my input picuture size is 720x1280,
but I don't know how to set the scale and center.
Can you give me some advice?
from pytorch-pose.
@bearpaw The scale keeps the height of the person as about 200 px. You should set the scale according to the groundtruth annotation or the detection bounding boxes.
-----------------Well I guss it does not have to be height, but also can be width. Actually, it should be max(h,w), Make sense?
from pytorch-pose.
@CoinCheung Have you solved this problem? About scale and center?
from pytorch-pose.
Related Issues (20)
- Question about detections_our_format.mat HOT 1
- 关于MPII训练精度问题 HOT 3
- Some problems about the running process HOT 2
- Looking hg-s2-b1
- Is there any code about Multi-scale test in this implement?
- great idea to put together these models for pose estimation HOT 1
- When I try to train with lsp,I faced some problem HOT 2
- Whats the difference between the hourglass_gn & hourglass models? HOT 1
- How to train with your own data set
- coco_annotations_2014.json HOT 1
- Bug in crop method HOT 11
- “scale” message HOT 2
- Hello, I encountered the following problems when I was training the code. What is the reason? Python: 2.7, Pytorch: 0.4.1 HOT 1
- I cannot train! HOT 1
- How do you implement a model based on a certain epoch that you have already trained and then continue to train
- There are some training issues here
- `RuntimeError` in `HourglassNet` because of possibly incorrect `scale_factor` for `F.interpolate` HOT 2
- I had train using mscoco and lsp dataset,but I don't know how to eval the pck and mAP?could you give me some suggestions?Thanks HOT 1
- Does the appended output from the show_sample method look as intended?
- Question about calculating PCK in Python
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 pytorch-pose.