Comments (13)
MichalBusta
commented on August 28, 2024
1
pondělí 8. července 2019 Alex Lee <[email protected]> napsal(a):
@MichalBusta <https://github.com/MichalBusta> I also have some questions
regarding your text recognition model.
1/ For latin languages, did you train your text recognition models with
single word images only (i.e. no text lines)?
most of the images in used datasets are word level, some of the generated
images are line-level
2/ How many images did you train your text recognition model with?
sorry I'm travelling so I can not give you exact number but it will be
about 500k
3/ Your text recognition model seems to use a ResNet like structure.
no - text detection is resnet-like. recognition is plain vgg style.
Since this project focus on real-time, have you tried to train your text
recognition model with a MobileNet backbone?
no - it is about the hardware - we were targeting low-end GPUs.
… —
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub
<#30?email_source=notifications&email_token=AA7KHMBNKZJHN5VBB7HNKVLP6MGUVA5CNFSM4HI6T3FKYY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGODZMTZBY#issuecomment-509164679>,
or mute the thread
<https://github.com/notifications/unsubscribe-auth/AA7KHMBKI7Q4ILDNOGM7G7LP6MGUVANCNFSM4HI6T3FA>
.
from e2e-mlt.
MichalBusta
commented on August 28, 2024
1
+/- : we have used more real latin and chinese data since there are a
datasets. For synth equal split.
středa 10. července 2019 Alex Lee <[email protected]> napsal(a):
… Thanks @MichalBusta <https://github.com/MichalBusta> ! One more thing,
for the 500k images, it consists of an equal share between Arabic, Bangla,
Chinese, Japanese, Korean and Latin (i.e. ~80k images for each script)?
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub
<#30?email_source=notifications&email_token=AA7KHMB3S4M2WPH4W2NTMXTP6VVLNA5CNFSM4HI6T3FKYY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGODZSJ2SA#issuecomment-509910344>,
or mute the thread
<https://github.com/notifications/unsubscribe-auth/AA7KHMDUJNUH37FR3L3JAB3P6VVLNANCNFSM4HI6T3FA>
.
from e2e-mlt.
coorful
commented on August 28, 2024
from e2e-mlt.
MichalBusta
commented on August 28, 2024
Line 140 in 1fb74ea
you can add:
import sys, traceback
traceback.print_exc(file=sys.stdout)
after 'except:'
to see what is going on
from e2e-mlt.
coorful
commented on August 28, 2024
Thank you so much for your reply,it seems that in ocr_test_utils.py
this fuction needs four outputs but just unpack three,when i add one output
det_text, conf, dec_s, _=print_seq_ext()
the problem solves!
thanks you ~
from e2e-mlt.
coorful
commented on August 28, 2024
besides, i have one question to ask for your help~
can i just use the ocr model to train a seperate word recognition model(just to achieve recognition task).if i can do like this,how large dataset should i have?(i just want to test on icdar2015 word recognition dataset )
thank you ! @MichalBusta
from e2e-mlt.
coorful
commented on August 28, 2024
Could you please give me some advice?Thanks a lot~ @MichalBusta
from e2e-mlt.
MichalBusta
commented on August 28, 2024
Hi,
On 29/04/2019 06:08, cooooor wrote:
besides, i have one questions to ask for your help~
can i just use the ocr model to train a seperate word recognition
model(just to achieve recognition task).
sure, there is
https://github.com/MichalBusta/E2E-MLT/blob/master/train_ocr.py script
just for training ocr module.
if i can do like this,how large dataset should i have?(i just want to
test on icdar2015 word recognition dataset )
hard to say - depends on data - (sythetic images - VGG group have been
using *9 million images*covering*90k English words* for ICDAR 2013
dataset, real images ~ 100000 from icdar2015 and icdar2017 MLT will give
you quite good baseline ... )
…
thank you ! @MichalBusta <https://github.com/MichalBusta>
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub
<#30 (comment)>,
or mute the thread
<https://github.com/notifications/unsubscribe-auth/AA7KHMBDMF7FKWEYNRYEKO3PSZYFLANCNFSM4HI6T3FA>.
from e2e-mlt.
coorful
commented on August 28, 2024
hello，when i use the dataset from IC15、IC17MLT&IC19MLT(only use the latin words，about 70000word images)，and only run the train_ocr.py，but the accuracy on ic15 test word dataset can just achieve 56.3% accuracy ，the batchsize i used equals to 4，could you please give me some advice why the accuracy is so low，and what should i do to improve it ?
Thanks a lot~
@MichalBusta
from e2e-mlt.
MichalBusta
commented on August 28, 2024
No easy answer sorry :)
- so low accuracy compared to who ( Baidu IDL, Alibaba PAI, Baidu VIS )?
what can help: - data, data, data ... (google PhotoOCR ~= 3mil manually annotated images, you should expect log scale dependency)
- language modeling
- more complicated model(s) (this project focus on real-time text detection), so you can go to seq-to-seq models ... good starer paper: http://openaccess.thecvf.com/content_cvpr_2016/html/Lee_Recursive_Recurrent_Nets_CVPR_2016_paper.html - quite old, but still good
from e2e-mlt.
coorful
commented on August 28, 2024
ok，i will try.thanks so much for your reply~
from e2e-mlt.
alwc
commented on August 28, 2024
@MichalBusta I also have some questions regarding your text recognition model.
1/ For latin languages, did you train your text recognition models with single word images only (i.e. no text lines)?
2/ How many images did you train your text recognition model with?
3/ Your text recognition model seems to use a ResNet like structure. Since this project focus on real-time, have you tried to train your text recognition model with a MobileNet backbone?
from e2e-mlt.
alwc
commented on August 28, 2024
Thanks @MichalBusta ! One more thing, for the 500k images, it consists of an equal share between Arabic, Bangla, Chinese, Japanese, Korean and Latin (i.e. ~80k images for each script)?
from e2e-mlt.
Related Issues (20)
- Need English Result instead of Chinese HOT 1
- RuntimeError: Cannot compile nms: /home/miteng/E2E-MLT-master/nms
- RuntimeError: Cannot compile nms: HOT 3
- How to evaluate E2E-MLT？ HOT 1
- Error While running demo script HOT 7
- The problem of "-ocr_feed_list" config HOT 4
- Missing license
- the problem of seg_loss HOT 1
- how to generate synth data for bangla and hindi languages?
- the problem about input_size HOT 1
- the problem about process_boxes HOT 4
- What is the structure of the dataset? HOT 1
- How did you happen use the data from SynthText HOT 6
- train_ocr.py training details
- Error Reloading the model from a checkpoint model HOT 1
- can i convert the model by torchscript?
- Data Link not working HOT 1
- 3 times call to function net.forward_ocr in method process_boxes HOT 2
- All loss values become nan HOT 2
- Affine grid parameters to crop predicted Bounding Boxes without transformation
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 e2e-mlt.