GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → chenjun2hao → Bert_ocr.pytorch

chenjun2hao / Bert_ocr.pytorch

Unofficial PyTorch implementation of 2D Attentional Irregular Scene Text Recognizer

Programming Languages

python
139335 projects - #7 most used programming language

Labels

pytorchocrtransformer

Projects that are alternatives of or similar to Bert ocr.pytorch

LaTeX-OCR
pix2tex: Using a ViT to convert images of equations into LaTeX code.
Stars: ✭ 1,566 (+1450.5%)
Mutual labels:  ocr, transformer
Transformer-ocr
Handwritten text recognition using transformers.
Stars: ✭ 92 (-8.91%)
Mutual labels:  ocr, transformer
Sightseq
Computer vision tools for fairseq, containing PyTorch implementation of text recognition and object detection
Stars: ✭ 116 (+14.85%)
Mutual labels:  ocr, transformer
Vedastr
A scene text recognition toolbox based on PyTorch
Stars: ✭ 290 (+187.13%)
Mutual labels:  ocr, transformer
Eqtransformer
EQTransformer, a python package for earthquake signal detection and phase picking using AI.
Stars: ✭ 95 (-5.94%)
Mutual labels:  transformer
Smiles Transformer
Original implementation of the paper "SMILES Transformer: Pre-trained Molecular Fingerprint for Low Data Drug Discovery" by Shion Honda et al.
Stars: ✭ 86 (-14.85%)
Mutual labels:  transformer
Pytorch Openai Transformer Lm
🐥A PyTorch implementation of OpenAI's finetuned transformer language model with a script to import the weights pre-trained by OpenAI
Stars: ✭ 1,268 (+1155.45%)
Mutual labels:  transformer
Typescript Transform Macros
Typescript Transform Macros
Stars: ✭ 85 (-15.84%)
Mutual labels:  transformer
Etagger
reference tensorflow code for named entity tagging
Stars: ✭ 100 (-0.99%)
Mutual labels:  transformer
Njunmt Tf
An open-source neural machine translation system developed by Natural Language Processing Group, Nanjing University.
Stars: ✭ 97 (-3.96%)
Mutual labels:  transformer
Remarks
Extract highlights, scribbles, and annotations from PDFs marked with the reMarkable tablet. Export to Markdown, PDF, PNG, and SVG
Stars: ✭ 94 (-6.93%)
Mutual labels:  ocr
Keras Ctpn
keras复现场景文本检测网络CPTN: 《Detecting Text in Natural Image with Connectionist Text Proposal Network》；欢迎试用，关注，并反馈问题...
Stars: ✭ 89 (-11.88%)
Mutual labels:  ocr
Tre
[AKBC 19] Improving Relation Extraction by Pre-trained Language Representations
Stars: ✭ 95 (-5.94%)
Mutual labels:  transformer
Transformer Based Pretrained Model For Event Extraction
使用基于Transformer的预训练模型在ACE2005数据集上进行事件抽取任务
Stars: ✭ 88 (-12.87%)
Mutual labels:  transformer
Image text reader
The module extracts text from image using the tesseract-OCR engine. Generally, text present in the images are blur or are of uneven sizes. The image is pre-processed for better comprehension by OCR. This module first makes bounding box for text in images and then normalizes it to 300 dpi, suitable for OCR engine to read.
Stars: ✭ 97 (-3.96%)
Mutual labels:  ocr
Penteract Ocr
⭐️ The native node.js bindings to the Tesseract OCR project.
Stars: ✭ 86 (-14.85%)
Mutual labels:  ocr
Ngx Dynamic Form Builder
FormBuilder + class-transformer + class-validator = dynamic form group builder for Angular10+
Stars: ✭ 93 (-7.92%)
Mutual labels:  transformer
Setr Pytorch
Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers
Stars: ✭ 96 (-4.95%)
Mutual labels:  transformer
Vision Transformer
Tensorflow implementation of the Vision Transformer (An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale)
Stars: ✭ 90 (-10.89%)
Mutual labels:  transformer
Nanonets Ocr Sample Python
NanoNets OCR API Example for Python
Stars: ✭ 92 (-8.91%)
Mutual labels:  ocr
View All Similar Projects ➔

2D Attentional Irregular Scene Text Recognizer

Unofficial PyTorch implementation of the paper, which transforms the irregular text with 2D layout to character sequence directly via 2D attentional scheme. They utilize a relation attention module to capture the dependencies of feature maps and a parallel attention module to decode all characters in parallel.

At present, the accuracy of the paper cannot be achieved. And i borrowed code from deep-text-recognition-benchmark

model

result
Test on ICDAR2019 with only 51.15%, will continue to improve.

Feature

  1. Output image string once not like the seqtoseq model

Requirements

Pytorch >= 1.1.0

Test

  1. download the pretrained model Baidu password: kdah.

  2. test on images which in demo_image folder

python demo.py --image_folder demo_image --saved_model <model_path/best_accuracy.pth>
  1. some examples
demo images Bert_OCR
available
shakesshack
london
greenstead
toast
merry
underground
ronaldo
bally
university
  1. result on benchmark data sets
IIIT5k_3000 SVT IC03_860 IC03_867 IC13_857 IC13_1015 IC15_1811 IC15_2077 SVTP CUTE80
84.367 79.907 91.860 91.465 88.448 86.010 65.654 63.215 68.527 81.185

total_accuracy: 78.423

Train

  1. I prepared a small dataset for train.The image and labels are in ./dataset/BAIDU.
python train.py --root ./dataset/BAIDU/images/ --train_csv ./dataset/BAIDU/small_train.txt --val_csv ./dataset/BAIDU/small_train.txt

Reference

  1. deep-text-recognition-benchmark
  2. 2D Attentional Irregular Scene Text Recognizer
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].