Comments (9)
Hi @sixgod696 thanks for using our proposal. Sorry, I may not be able to answer this question. Ww haven't come across this question before. We just replaced the edge map in the original paper with the edge map generated by TEED, and the code was not changed.
I understand, thanks for the reply.
from teed.
I used my edge diagram to carry out the sketch recognition project mentioned in the paper, and in order to convert the obtained edge diagram into a suitable MAT file, I wrote a jpg to MAT file script, but the prediction effect was very poor, how did you solve it in the first place?Looking forward to your reply!
I have solved this problem, I would like to ask what is the test data size of QMUL-shoe and QMUL-chair you use? Looking forward to your reply
from teed.
Excuse me, I have another additional question, that is, my score in top 1 is very low, but my score in top 10 is relatively good. What may be the reason for this? Looking forward to your reply!
from teed.
Hi @sixgod696 thanks for using our proposal.
Sorry, I may not be able to answer this question. Ww haven't come across this question before. We just replaced the edge map in the original paper with the edge map generated by TEED, and the code was not changed.
from teed.
Hi @sixgod696 ,I encountered some problems in the training process, can you tell me your training parameters ? Thanks very much ! Looking forward to your reply !
from teed.
Hi @sixgod696 ,I encountered some problems in the training process, can you tell me your training parameters ? Thanks very much ! Looking forward to your reply !
I've modified some parts of the network, and I'm not sure which part of your code have the problem.Maybe you can show your error log.
from teed.
Hi @sixgod696 ,I encountered some problems in the training process, can you tell me your training parameters ? Thanks very much ! Looking forward to your reply !
I've modified some parts of the network, and I'm not sure which part of you are having the problem.
Thank you for your reply!
The first image is the prediction result obtained by using the weight file obtained by my own training, and the second is the prediction result obtained by using the weight file in the source code.The difference is very big, but I don 't know where the problem is.
from teed.
Hi @sixgod696 ,I encountered some problems in the training process, can you tell me your training parameters ? Thanks very much ! Looking forward to your reply !
I've modified some parts of the network, and I'm not sure which part of you are having the problem.Thank you for your reply! The first image is the prediction result obtained by using the weight file obtained by my own training, and the second is the prediction result obtained by using the weight file in the source code.The difference is very big, but I don 't know where the problem is.
I have also encountered this problem. You may not have preprocessed the BIPED data set. There is preprocessing code in the BIPED project. After processing, the pictures will increase from hundreds to thousands, so the training time will be normal.
from teed.
Hi @sixgod696 ,I encountered some problems in the training process, can you tell me your training parameters ? Thanks very much ! Looking forward to your reply !
I've modified some parts of the network, and I'm not sure which part of you are having the problem.Thank you for your reply! The first image is the prediction result obtained by using the weight file obtained by my own training, and the second is the prediction result obtained by using the weight file in the source code.The difference is very big, but I don 't know where the problem is.
I have also encountered this problem. You may not have preprocessed the BIPED data set. There is preprocessing code in the BIPED project. After processing, the pictures will increase from hundreds to thousands, so the training time will be normal.
Because I did not expand the data set to lead to this problem. I did not pay attention to this problem. Thank you very much for taking your time to answer my question, thank you very much ! Wish you have a good day.
from teed.
Related Issues (20)
- this code is not run HOT 3
- import dataset error HOT 9
- Application scenarios for edge images HOT 1
- sizes not match HOT 2
- Evaluation ODS/OIS/AP HOT 1
- The setting problem of TEED training parameters HOT 2
- Question about Fmish in DoubleFusion HOT 1
- Why are your edge maps finer HOT 1
- is that possible to use onnx? HOT 3
- Some problem of training process
- When I run main.py, it tells me that I don't have utils.AF, where should I find that file or the library HOT 1
- What are the meanings of each of the 8 models given in the document? HOT 1
- Can i extract xy coordinates of detected edge? HOT 1
- Hello, have you ever tried to reason with openvino or libtorch?
- Fine-tuning TEED Model with Custom Dataset for Diverse Object Outlines HOT 1
- I found out that the train_pair0.lst file and BIPED don't match. HOT 1
- BIPED datase HOT 2
- evaluation
- evaluation HOT 14
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 teed.