Comments (9)
taozh2017
commented on July 21, 2024
The results on LFSD are:
['Evaluating----------', 'LFSD', '----------']
eval[FMeasure]:LFSD dataset with SCLNet method.
eval[EMeasure]:LFSD dataset with SCLNet method.
['MAE:', 0.07058968394994736, '----- Smeansure:', 0.8541927319765091,
'----- max_f:', 0.8809829354286194, '----- max_e:', 0.894311249256134]
clelouch ***@***.***> 于2021年9月19日周日 下午3:39写道：
… I find the performance of SPNet is relatively poor when evaluated on LFSD.
[image: image]
<https://user-images.githubusercontent.com/33519394/133919385-f35f9bd1-c5ce-46e8-bffe-40c7a54eb731.png>
i am not sure whether the evalutaion results is correct or not. Have you
evaluted the model on LFSD?
—
You are receiving this because you are subscribed to this thread.
Reply to this email directly, view it on GitHub
<#2>, or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AHT5QRMS2HWCHXUPNQABB4TUCWHUZANCNFSM5EKBUWRA>
.
Triage notifications on the go with GitHub Mobile for iOS
<https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675>
or Android
<https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub>.
--
Best,
Tao.
from spnet.
clelouch
commented on July 21, 2024
I directly use the test_produce_maps.py to generate the saliency maps and use the evaluation code. Did i do anything wrong?
it seems your results are generated by SCLNet. is it a typo?
from spnet.
taozh2017
commented on July 21, 2024
I do this test using the same steps. When I am free, I will carefully check
it. Thanks.
clelouch ***@***.***> 于2021年9月19日周日 下午3:52写道：
… I directly use the test_produce_maps.py to generate the saliency maps and
use the evaluation code <https://github.com/DengPingFan/D3NetBenchmark>.
Did i do anything wrong?
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub
<#2 (comment)>, or
unsubscribe
<https://github.com/notifications/unsubscribe-auth/AHT5QRLCKOQ54N6AQSTAYLLUCWJFJANCNFSM5EKBUWRA>
.
Triage notifications on the go with GitHub Mobile for iOS
<https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675>
or Android
<https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub>.
--
Best,
Tao.
from spnet.
clelouch
commented on July 21, 2024
Thanks for your kind help!
from spnet.
clelouch
commented on July 21, 2024
when i use the provided saliency maps on SSD for evaluation, i find the max F-measure is different from the results in the paper (i.e., 0.863 vs. 0.883) .
from spnet.
taozh2017
commented on July 21, 2024
I evaluate using the python code: test_evaluation_maps.py, can you use this code?
from spnet.
clelouch
commented on July 21, 2024
I follow your suggestion and use the python script for evaluation. The results are consistent with your paper. I am confused about the results. Could your please tell me the reason?
from spnet.
taozh2017
commented on July 21, 2024
I follow the python code from one GitHub page, and I do not investigate the
difference between the Matlab code and python code. When I tune my
implementation code, I use the python code.
clelouch ***@***.***> 于2021年9月20日周一 下午9:17写道：
… I follow your suggestion and use the python script for evaluation. The
results are consistent with your paper. I am confused about the results.
Could your please tell me the reason?
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub
<#2 (comment)>, or
unsubscribe
<https://github.com/notifications/unsubscribe-auth/AHT5QROZVVYSRVZUIG6ZYPDUC4X7TANCNFSM5EKBUWRA>
.
Triage notifications on the go with GitHub Mobile for iOS
<https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675>
or Android
<https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub>.
--
Best,
Tao.
from spnet.
clelouch
commented on July 21, 2024
Thanks for your kind help.
from spnet.
Related Issues (4)
- Different backbone HOT 1
- CIM是不是有问题啊 HOT 1
- Performance on DUT HOT 9
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 spnet.