Comments (9)
qhykwsw
commented on July 21, 2024
Hi, so sorry to bother you again. But I got a strange thing shouldn't happen.
After I did the change mentioned above, the code can run normally. However, when I finished my training process, I found the comref's results are better than the com's results on the three datasets. Logically speaking, the results after com refinement should be better than without the refinement. What do you think of it？
from deep-prior-pp.
moberweger
commented on July 21, 2024
Yes, the results with comref should be better than with com. We reported
this improvement in our paper.
from deep-prior-pp.
qhykwsw
commented on July 21, 2024
Oh, sorry, I wrote it wrongly. In fact, the comref's results are worse than the com's results on the three datasets, which nearlly 10~20%.
from deep-prior-pp.
moberweger
commented on July 21, 2024
That is strange, it should not be like that. Did you also train the comref
networks?
qianhongyi <[email protected]> schrieb am Fr., 29. Juni 2018 7:52
nachm.:
… Oh, sorry, I wrote it wrongly. In fact, the comref's results are worse
than the com's results on the three datasets, which nearlly 10~20%.
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub
<#18 (comment)>,
or mute the thread
<https://github.com/notifications/unsubscribe-auth/AKEhXJghHkvwqWHungy9lGHHPZF0IsY6ks5uBtn3gaJpZM4U5Al->
.
from deep-prior-pp.
qhykwsw
commented on July 21, 2024
Yeah, I trained the comref networks. For the ICVL dataset, I first run the main_icvl_com_refine.py and got the net_ICVL_COM_AUGMENT.pkl. Then I changed
"comref = None
docom = False"
to
"comref = "./eval/NYU_COM_AUGMENT/net_NYU_COM_AUGMENT.pkl"
docom = True"
from deep-prior-pp.
moberweger
commented on July 21, 2024
Well, do the errors of the detection decrease when training the comref?
In the code you pasted, you mixed the nyu and icvl, you need a separate
comref network for each dataset.
qianhongyi <[email protected]> schrieb am Sa., 30. Juni 2018 4:00
vorm.:
… Yeah, I trained the comref networks. For the ICVL dataset, I first run the
main_icvl_com_refine.py and got the net_ICVL_COM_AUGMENT.pkl. Then I changed
"comref = None
docom = False"
to
"comref = "./eval/NYU_COM_AUGMENT/net_NYU_COM_AUGMENT.pkl"
docom = True"
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub
<#18 (comment)>,
or mute the thread
<https://github.com/notifications/unsubscribe-auth/AKEhXM_LDDsW7sCocDFiAPAAG2BQQouPks5uB0xHgaJpZM4U5Al->
.
from deep-prior-pp.
qhykwsw
commented on July 21, 2024
Oh, sorry, it's my carelessness. I pasted the code wrongly...In fact, I didn't garble the nyu and icvl. And the errors of the detection do decrease when training.
from deep-prior-pp.
moberweger
commented on July 21, 2024
OK, this is good then. But I do not see why the joint error should not
decrease with a better detection, though.
qianhongyi <[email protected]> schrieb am Sa., 30. Juni 2018 6:36
vorm.:
… Oh, sorry, it's my carelessness. I pasted the code wrongly...In fact, I
didn't garble the nyu and icvl. And the errors of the detection do decrease
when training.
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub
<#18 (comment)>,
or mute the thread
<https://github.com/notifications/unsubscribe-auth/AKEhXFezrdMg3v2o-AIt3STGMSSWwt5hks5uB3DCgaJpZM4U5Al->
.
from deep-prior-pp.
qhykwsw
commented on July 21, 2024
Sorry , after read your code again I finally found why, I made another stupid mistake. In fact, I didn't use the 'com' mode. The better result came from the 'groundtruth' mode and the worse result came from 'comref' mode. This makes sense.
from deep-prior-pp.
Related Issues (20)
- the code be written in tensorflow HOT 2
- Estimate 3D hand pose in ASL Finger Spelling Dataset HOT 1
- Is there guide to install DepthSense SDK HOT 1
- Deep prior for RGB HOT 1
- use ICVLImporter and NYUImporter HOT 6
- reference point(center point) HOT 3
- The network for refining hand localizatoin HOT 1
- This is some woring with the code! HOT 2
- centers for custom dataset HOT 3
- I have a doubt about the hand detection algorithm. HOT 2
- Dataset issue HOT 1
- DHG-14/28 dataset center reference points
- About the joint refinement network? HOT 1
- Pretrained ICVL and NYU accuracy HOT 1
- about the openni2 and kinect HOT 1
- can it be trained without use icvl or nyu importer?
- can it be run without use icvl or nyu importer? HOT 5
- Could you provide Pretrain Model? HOT 1
- train/test split of the msra15 dataset HOT 5
- Could you provide more explanation about the input of the "RealtimeHandposePipeline" class 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 deep-prior-pp.