Skip to content

Commit

Permalink
Pytorch has to be 0.4.1 since MSELoss uses reduction arg
Browse files Browse the repository at this point in the history
  • Loading branch information
alwc committed Nov 7, 2018
1 parent edde5ed commit d754ad2
Showing 1 changed file with 16 additions and 16 deletions.
32 changes: 16 additions & 16 deletions README.md
Original file line number Diff line number Diff line change
@@ -1,32 +1,32 @@
# E2E-MLT
E2E-MLT - an Unconstrained End-to-End Method for Multi-Language Scene Text

code base for: https://arxiv.org/abs/1801.09919


## Requirements

- python3.x with
- python3.x with
- opencv-python
- pytorch 0.4
- pytorch 0.4.1
- torchvision
- warp-ctc (https://github.com/SeanNaren/warp-ctc/)
- warp-ctc (https://github.com/SeanNaren/warp-ctc/)

## Pretrained Models

[e2e-mlt](http://ptak.felk.cvut.cz/public_datasets/SyntText/e2e-mlt.h5)

```
wget http://ptak.felk.cvut.cz/public_datasets/SyntText/e2e-mlt.h5
```
## Running Demo

## Running Demo

```
python3 demo.py -model=e2e-mlt.h5
```
## Data

## Data

- [ICDAR MLT Dataset](http://rrc.cvc.uab.es/?ch=8&com=introduction)
- [ICDAR 2015 Dataset](http://rrc.cvc.uab.es/?ch=4&com=introduction)
Expand All @@ -35,23 +35,23 @@ python3 demo.py -model=e2e-mlt.h5

![MLT SynthSet](images/synth.png)

Synthetic text has been generated using [Synthetic Data for Text Localisation in Natural Images](https://github.com/ankush-me/SynthText), with minor changes for Arabic and Bangla script rendering.
Synthetic text has been generated using [Synthetic Data for Text Localisation in Natural Images](https://github.com/ankush-me/SynthText), with minor changes for Arabic and Bangla script rendering.

What we have found useful:
- for generating Arabic Scene Text: https://github.com/mpcabd/python-arabic-reshaper
- for generating Arabic Scene Text: https://github.com/mpcabd/python-arabic-reshaper
- for generating Bangla Scene Text: PyQt4
- having somebody who can read non-latin scripts: we would like to thank Ali Anas for reviewing generated Arabic scene text.


## Trainnig
## Trainnig

```
python3 train.py -train_list=sample_train_data/MLT/trainMLT.txt -batch_size=8 -num_readers=5 -debug=0 -input_size=512 -ocr_batch_size=256 -ocr_feed_list=sample_train_data/MLT_CROPS/gt.txt
```

## Acknowledgments
Code borrows from [EAST](https://github.com/argman/EAST) and [DeepTextSpotter](https://github.com/MichalBusta/DeepTextSpotter)

Code borrows from [EAST](https://github.com/argman/EAST) and [DeepTextSpotter](https://github.com/MichalBusta/DeepTextSpotter)

## TODO
- update arxiv with current paper status

0 comments on commit d754ad2

Please sign in to comment.