All Projects → zhiqwang → Sightseq

zhiqwang / Sightseq

Licence: mit
Computer vision tools for fairseq, containing PyTorch implementation of text recognition and object detection

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to Sightseq

Tensornets
High level network definitions with pre-trained weights in TensorFlow
Stars: ✭ 982 (+746.55%)
Mutual labels:  object-detection, mobilenet, faster-rcnn, densenet
insightocr
MXNet OCR implementation. Including text recognition and detection.
Stars: ✭ 100 (-13.79%)
Mutual labels:  ocr, text-recognition, crnn
Text recognition toolbox
text_recognition_toolbox: The reimplementation of a series of classical scene text recognition papers with Pytorch in a uniform way.
Stars: ✭ 114 (-1.72%)
Mutual labels:  ctc, ocr, text-recognition
Tf Object Detection
Simpler app for tensorflow object detection API
Stars: ✭ 91 (-21.55%)
Mutual labels:  object-detection, mobilenet, faster-rcnn
CRNN-OCR-lite
Lightweight CRNN for OCR (including handwritten text) with depthwise separable convolutions and spatial transformer module [keras+tf]
Stars: ✭ 130 (+12.07%)
Mutual labels:  ocr, mobilenet, crnn
CRNN.tf2
Convolutional Recurrent Neural Network(CRNN) for End-to-End Text Recognition - TensorFlow 2
Stars: ✭ 131 (+12.93%)
Mutual labels:  ocr, ctc, crnn
Crnn attention ocr chinese
CRNN with attention to do OCR,add Chinese recognition
Stars: ✭ 315 (+171.55%)
Mutual labels:  attention, crnn, ocr
Deep Text Recognition Benchmark
Text recognition (optical character recognition) with deep learning methods.
Stars: ✭ 2,665 (+2197.41%)
Mutual labels:  crnn, ocr, text-recognition
Tf Faster Rcnn
Tensorflow Faster RCNN for Object Detection
Stars: ✭ 3,604 (+3006.9%)
Mutual labels:  object-detection, mobilenet, faster-rcnn
Neural sp
End-to-end ASR/LM implementation with PyTorch
Stars: ✭ 408 (+251.72%)
Mutual labels:  attention, ctc, transformer
Cnn lstm ctc ocr
Tensorflow-based CNN+LSTM trained with CTC-loss for OCR
Stars: ✭ 464 (+300%)
Mutual labels:  ctc, ocr, text-recognition
Adelaidet
AdelaiDet is an open source toolbox for multiple instance-level detection and recognition tasks.
Stars: ✭ 2,565 (+2111.21%)
Mutual labels:  object-detection, ocr, text-recognition
Asr syllable
基于卷积神经网络的语音识别声学模型的研究
Stars: ✭ 127 (+9.48%)
Mutual labels:  attention, densenet, ctc
Crnn With Stn
implement CRNN in Keras with Spatial Transformer Network
Stars: ✭ 83 (-28.45%)
Mutual labels:  crnn, ocr, text-recognition
Ocr.pytorch
A pure pytorch implemented ocr project including text detection and recognition
Stars: ✭ 196 (+68.97%)
Mutual labels:  crnn, ocr, text-recognition
Vedastr
A scene text recognition toolbox based on PyTorch
Stars: ✭ 290 (+150%)
Mutual labels:  ocr, text-recognition, transformer
Crnn.pytorch
crnn实现水平和垂直方向中文文字识别, 提供在3w多个中文字符训练的水平识别和垂直识别的预训练模型; 欢迎关注,试用和反馈问题... ...
Stars: ✭ 145 (+25%)
Mutual labels:  crnn, ocr, text-recognition
Megreader
A research project for text detection and recognition using PyTorch 1.2.
Stars: ✭ 332 (+186.21%)
Mutual labels:  ctc, ocr, text-recognition
Tr
Free Offline OCR 离线的中文文本检测+识别SDK
Stars: ✭ 598 (+415.52%)
Mutual labels:  crnn, ocr, text-recognition
Caffe ocr
主流ocr算法研究实验性的项目,目前实现了CNN+BLSTM+CTC架构
Stars: ✭ 1,156 (+896.55%)
Mutual labels:  densenet, ctc, ocr

🔭sightseq

Now, Let's go sightseeing by vision and sequence language multimodal around the deep learning world.

What's New:

  • July 30, 2019: Add faster rcnn models. And I rename this repo from image-captioning to sightseq, this is the last time I rename this repo, I promise.
  • June 11, 2019: I rewrite the text recognition part base on fairseq. Stable version refer to branch crnn, which provides pre-trained model checkpoints. Current branch is work in process. Very pleasure for suggestion and cooperation in the fairseq text recognition project.

Features:

sightseq provides reference implementations of various deep learning tasks, including:

Additionally:

  • All features of fairseq
  • Flexible to enable convolution layer, recurrent layer in CRNN
  • Positional Encoding of images

General Requirements and Installation

  • PyTorch (There is a bug in nn.CTCLoss which is solved in nightly version)
  • Python version >= 3.5
  • Fairseq version >= 0.7.1
  • torchvision version >= 0.3.0
  • For training new models, you'll also need an NVIDIA GPU and NCCL

Pre-trained models and examples

License

sightseq is MIT-licensed. The license applies to the pre-trained models as well.

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].