Comments (4)
Thanks a lot for sharing the awesome work :)
Here I'm a little confused about the padding tokens, from the paper, it seems the author uses only one token to pad the sentence to the batch_max_length, and I also experimented it with your implementation, however, it turns out that your implementation with two tokens produces much better result.
So I'm wondering if there is any specific reason why we chose the two-token method? Any information will be greatly appreciated.
Do you reach the paper's accuracy? I experimented and modified it as paper in some detail,however still can not get a good result,especially on the CUBE80 dataset.
from srn.pytorch.
@miaomi1994 nope, I was first doing quick test using my own dataset.
from srn.pytorch.
Hello, is the data format of training and testing model in MDB or other forms? Thank you very much for your reply.
from srn.pytorch.
Hello, is the data format of training and testing model in MDB or other forms? Thank you very much for your reply.
Based on dataset.py in this repo, the implementation uses lmdb dataset, you can also refer to https://github.com/clovaai/deep-text-recognition-benchmark/blob/master/create_lmdb_dataset.py script for creating your lmdb dataset (the author of this SRN repo already gave the reference in the README page)
from srn.pytorch.
Related Issues (20)
- 已有参考
- The PVAM module is different with paddleOcr
- GSRB中的argmax模块是否可导? 应该不可导吧 HOT 1
- 训练PAD问题
- File "SRN_modules.py", line 65, in forward return x + self.pos_table[:, :x.size(1)].clone().detach() RuntimeError: The size of tensor a (320) must match the size of tensor b (256) at non-singleton dimension 1 HOT 4
- pytorch模型转pt时,发生错误
- 用百度中文数据不收敛
- 关于论文中的attention map 可视化 HOT 2
- 论文中使用的TRW15测试集能上传下吗?数据集无法下载
- 你好,想问一下从头开始训练,数据集的格式应该是什么样的呢
- 没达到论文的acc是因为训练集?
- How to change module to fix more image size. HOT 1
- acc is always 0
- What is your license? HOT 1
- 和腾讯的2DAttentionalIrregularSceneTextRecognizer HOT 1
- where can download the "BAIDU" datasets?
- why don't use resnet50FPN?
- copying a param with shape torch.Size([38, 512]) from checkpoint, the shape in current model is torch.Size([39, 512]). HOT 4
- Alternative to download pre-trained model HOT 3
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 srn.pytorch.