Comments (4)
bruceyo
commented on July 20, 2024
It means generating the ST-ROI feature for reproducing the results. I cannot see your uploaded image.
You do not need to do so for training, as we perform random sampling.
from mmnet.
TS-CZF
commented on July 20, 2024
It means generating the ST-ROI feature for reproducing the results. I cannot see your uploaded image. You do not need to do so for training, as we perform random sampling.
@bruceyo Hello, the author. I want to know which python file specifically describes the combination of skeleton attention and RGB to generate regions of interest.Or the python files involved in generating the region of interest.Thank you very much for your reply
from mmnet.
bruceyo
commented on July 20, 2024
For different datasets, the implementations are slightly different. Please refer to the files as follows:
NTU RGB+D: segment_rgbbody_ntu.py
PKU-MMD: segment_rgbbody_pku.py
N-UCLA: segment_rgbbody_nucla.py
You can use the main function in the above files to test.
from mmnet.
TS-CZF
commented on July 20, 2024
Hello, the author. Because my code ability is really poor, with your help, after several days of exploring the code, I still haven't realized it. I took the liberty to ask you for a screen recording resource that reproduced the MMNet experiment at that time. Thank you very much!!!!!
------------------ Original ------------------
From: ***@***.***>;
Date: Tue, Oct 18, 2022 07:54 PM
To: ***@***.***>;
Cc: ***@***.***>; ***@***.***>;
Subject: Re: [bruceyo/MMNet] Generate Region of Interest (Issue #7)
For different datasets, the implementations are slightly different. Please refer to the files as follows:
NTU RGB+D: segment_rgbbody_ntu.py
PKU-MMD: segment_rgbbody_pku.py
N-UCLA: segment_rgbbody_nucla.py
You can use the main function in the above files to test.
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you authored the thread.Message ID: ***@***.***>
from mmnet.
Related Issues (20)
- Consultation on handling documents HOT 1
- RuntimeError: Given groups=1, weight of size [60, 256, 1, 1], expected input[1, 3, 1, 1] to have 256 channels, but got 3 channels instead HOT 1
- A problem about the readme.md document
- A question about feeder_rgb_fused_ntu.py
- The training accuracy of NTU120 is very low！
- Some Questions about Acc in Cross_Subject task?
- The image is black and the correct ST-ROI is not generated as shown below. Is there a solution?
- Questions about import HOT 4
- Masked depth maps HOT 2
- OpenPose extracted data are corrupt HOT 6
- can't find this file "main_bone.py"
- Project code
- can not find main_joint.py and main_bone.py
- Training RGB video (ntu60) HOT 12
- ValueError: could not broadcast input array from shape (103,25,3) into shape (197,25,3)
- Accuracy of this method:python main_rgb_fused.py recognition -c config/ntu60_xsub/test_rgb_fused.yaml HOT 16
- Prepare the RGB Modality HOT 2
- Training RGB video (ntu60 xsub) HOT 3
- couldn't find tools/data_gen/gen_fivefs_<dataset> HOT 4
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 mmnet.