Comments (6)
Hi,
there may be many reasons causing such results,
like too-few training samples, wrong mapping from original predicting vectors to final text results, or unsuitable alphabet(check if all chars are included in the alphabet),
you can check the output predicting results and compare these with the ground-truth,
if they are similar, you can training more time, or add more training data.
from ocr.pytorch.
Actually its not predicting anything after every epoch. And by the way what should be the size of the dataset? i am training it on 1200 images
from ocr.pytorch.
Actually its not predicting anything after every epoch. And by the way what should be the size of the dataset? i am training it on 1200 images
1200 seems not enough, 10000+ or more will be better, you can add some synthetic data to overcome under-fitting.
from ocr.pytorch.
Can you please provide me with your dataset. Actually this will help me a lot to go through the dataset.
Mine email id is [email protected]
from ocr.pytorch.
I won't be commercializing it, just needed it for personal work
from ocr.pytorch.
Can you please provide me with your dataset. Actually this will help me a lot to go through the dataset.
Mine email id is [email protected]
Hi, actually most of my training are synthetic data,
you can combine part of your real data with synthetic data as total training data, and another part real data for test,
a lot of repos on GitHub are able to generate large-scale synthetic data, such as .
from ocr.pytorch.
Related Issues (20)
- inference for batch?
- 提供的CRNN模型不可用
- CRNN数据集
- CRNN出现str不可用,不知道该怎么修改,求赐教 HOT 7
- crnn训练的时候出现损失在140多,精度为0 HOT 1
- 关于重新训练自己的数据集,预测为空的问题 HOT 1
- I made a pytorch-lightning implementation of your CTPN HOT 2
- crnn.py中看到有好几个不同的crnn模型 HOT 2
- 能否说说怎么返回识别出的文字的在原图中的坐标位置?
- CRNN可以用在Khmer语言吗? HOT 1
- CRNN这个是怎么回事?Aborted (core dumped)
- 请问用合成数据集训练新的模型时,遇到无法读取infofile中的fname和label的问题怎么解决呢?
- Is there any option for language?
- need help for training with custom images
- 你好,有没有日文的crnn checkpoints ?微信nlanguage?
- CRNN数据集制作方法 HOT 2
- 请问crnn识别的准确率怎么看啊
- 在运行demo的时候遇到了一个问题,输出的都是大写英文字母
- export to onnx model
- Is pretrained CRNN bias towards Chinese character?
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 ocr.pytorch.