Comments (2)
Thank you for your interest in our work.
In our implementation:
we follow a common practice in scene text recognition of resizing the cropped text image to 32x128 pixels, regardless of its original size. Since we don't use padding, we don't have the issue that you mentioned about "null" frames.I believe that this setting can handle most of the cropped words, especially of the academic datasets. However, it can be sub-optimal for really long words, such as url address. In such cases, you should probably use a different resizing technique to a wider image. That said, for the pretraining stage of SeqCLR the current resizing should be satisfying.
Aviad
from semimtr-text-recognition.
Ok, I get it. Thanks for your response!
from semimtr-text-recognition.
Related Issues (14)
- Question about training time. HOT 1
- The shape of projector's input HOT 5
- Question about frame-to-instance implemenation HOT 1
- semimtr_finetune without language model use HOT 2
- About EMA HOT 3
- I run !pip install -r requirements.txt then i config for mine then i run into this error.
- Is there an implementation of Seqclr? HOT 3
- Question about other languages support HOT 1
- NaN in input tensor HOT 2
- Why still calculate loss when conducting evaluation? and IndexError reported also HOT 5
- imgaug augmenters HOT 1
- Training stopped after 5 epochs while Semimtr finetuning HOT 2
- Evaluation results? 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 semimtr-text-recognition.