Comments (5)
N is the number of stn matrix in paper.
from stn-ocr.
Hi,
N
does not change during training. It is set to the maximum amount of text regions you want your network to extract. Naturally, it will happen that some words are shorter than N
. IN this case you must make sure that the these extra timesteps are labelled with the blank
label, so that the network learns to predict the correct number of characters/words in the image.
Let's have a look at your example: Let's assume the 16
is in the top-left corner of the image and the 18
is in the bottom-right corner of the image. Since we always assumed that we read from left to right and top to bottom, we would say that the first label is 16
and the second label is 18
. With this way of defining our labels, we tell the network to put the first prediction always close to the most top-left word and all other predictions following the reading direction.
from stn-ocr.
@Bartzi,thanks for your reply. Maybe I didn`t explain my question 1 clearly. for question 2,I got it. About the N,it seems that you explain it as CTC loss. My question is that ,for example,now the N is set as 3,it means we can get 3 prediction text regions. if the number of ground truth labels is only 2,like “16” and "18" as above,you mean that we must make sure the label of extra prediction region is blank?Am I right?
from stn-ocr.
Yes, that's it!
from stn-ocr.
@Bartzi Thanks a lot ! Hope everything goes well with you !
from stn-ocr.
Related Issues (20)
- compiling on Windows HOT 2
- Stop Iteration exception raised while training. HOT 1
- test on dataset of my own HOT 1
- train accuracy on svhn dataset doesn't improve HOT 9
- i read the paper and have a question: what is the order of the labels? HOT 2
- no file /train/0.png HOT 4
- StopIteration HOT 12
- Install error HOT 8
- Shape error eval_svhn_model.py for SVHN demos. HOT 8
- opencv error HOT 4
- Training HOT 9
- Training does not end. HOT 9
- question about the N grids in paper HOT 3
- ctc_loss.cpp:509:10: fatal error: 'ctc.h' file not found HOT 15
- can you just give a pretrained model to us? Or a runnable demo that no need for us to train HOT 1
- Evaluation fail! HOT 6
- Train text recognition fail
- train original svhn datasets HOT 1
- load pretrained model error 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 stn-ocr.