Comments (3)
I don't think what you suggest is the right approach. Two issues come to mind. CTC ignores the location of the individual elements in the input image, so I cannot see how you would practically target individual sequence items. If you could, one ex post facto way to adjust your prior in a learned conditional model to use Bayes' rule.
P(class|obs) = P(obs|class) * P(class) / P(obs)
P'(class|obs) = P(obs|class) * P'(class) / P(obs) = P(class|obs) * P'(class) / P(class)
That is, you can adjust your discriminant function (in a non-sequential model) by rescaling with the ratio of training data to test data distributions.
from cnn_lstm_ctc_ocr.
Thanks for answering!
So, if I get you right, we may have 100 ‘q’ in training set and we know that it is not enough. In the test data it may be 10,000 ‘q’. So let say we have trained our model with what we have, and on the last step, we run the model and just multiply output probability ‘q’ by P’(q)/P(q)
where
P’(q) is 10,000/total_number_of_symbols_in_test
and
P(q) is 100/total_number_of_symbols_in_train
So, in that way we a little bit increase/decrease output probability of ‘q’.
It sounds tricky to me. Could you please tell if i understand you right?
And what you can say about MJSynth dataset imbalance? The class/symbols in that dataset not balanced either. Isn’t it affect to the results when we test the model trained on MJsynth on the other datasets?
from cnn_lstm_ctc_ocr.
There are no easy solutions. Any sequence model, such as the one in this repo, will perform best on test data with the same statistics (as captured by the model) as the training data.
from cnn_lstm_ctc_ocr.
Related Issues (20)
- Training error HOT 9
- How to deal with single character input HOT 2
- Using Multiple GPU as a train_device HOT 3
- ctc_loss_calculator.cc Not a valid path HOT 3
- are there any pretrain model file HOT 3
- Input shapes: [72,357,1], [4] and with input tensors computed HOT 3
- It's possible to use a pre-trained model? HOT 1
- CuDnn 7.2.1 HOT 1
- get not good result, HOT 2
- FineTune ! HOT 3
- Model learns nothing about certain characters. HOT 1
- TypeError HOT 4
- Fixed sequence length HOT 1
- Training Error when using my data HOT 1
- 0% GPU-Util when testing HOT 1
- Train on vertical patches HOT 1
- Question Regarding End Model HOT 3
- confidence on sess passing HOT 6
- How to convert .ckpt model to SavedModel .pb format for hosting with Tensorflow Model Serving? HOT 6
- How to batch inference? HOT 5
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 cnn_lstm_ctc_ocr.