Displaying 1 to 13 from 13 results

Screenshot-to-code-in-Keras - A neural network that transforms a screenshot into a static website

  •    Jupyter

This is the code for the article 'Turning design mockups into code with deep learning' on FloydHub's blog. Within three years deep learning will change front-end development. It will increase prototyping speed and lower the barrier for building software.

Simple Binary Encoding - Simple Binary Encoding (SBE) - High Performance Message Codec

  •    Java

SBE is an OSI layer 6 presentation for encoding and decoding binary application messages for low-latency financial applications. This repository contains the reference implementations in Java, C++, Golang, and C#. The Java and C++ SBE implementations are designed with work very efficiently with the Aeron messaging system for low-latency and high-throughput communications. The Java SBE implementation has a dependency on Agrona for its buffer implementations.

sockeye - Sequence-to-sequence framework with a focus on Neural Machine Translation based on Apache MXNet

  •    Python

Felix Hieber, Tobias Domhan, Michael Denkowski, David Vilar, Artem Sokolov, Ann Clifton and Matt Post (2017): Sockeye: A Toolkit for Neural Machine Translation. In eprint arXiv:cs-CL/1712.05690.If you are interested in collaborating or have any questions, please submit a pull request or issue. You can also send questions to sockeye-dev-at-amazon-dot-com.

neuralmonkey - An open-source tool for sequence learning in NLP built on TensorFlow.

  •    Python

The Neural Monkey package provides a higher level abstraction for sequential neural network models, most prominently in Natural Language Processing (NLP). It is built on TensorFlow. It can be used for fast prototyping of sequential models in NLP which can be used e.g. for neural machine translation or sentence classification. The higher-level API brings together a collection of standard building blocks (RNN encoder and decoder, multi-layer perceptron) and a simple way of adding new building blocks implemented directly in TensorFlow.




Speech_Recognition_with_Tensorflow - Implementation of a seq2seq model for Speech Recognition using the latest version of TensorFlow

  •    Jupyter

I uploaded three .py files and one .ipynb file. The .py files contain the network implementation and utilities. The Jupyter Notebook is a demo of how to apply the model. Seq2Seq model As I mentioned above the model architecture is similar to the one used in "Listen, Attend and Spell", i.e. we are using pyramidal bidirectional LSTMs in the encoder. This reduces the time resolution and enhances the performance on longer sequences.

Text_Summarization_with_Tensorflow - Implementation of a seq2seq model for summarization of textual data

  •    Jupyter

Implementation of a seq2seq model for summarization of textual data using the latest version of tensorflow. Demonstrated on amazon reviews, github issues and news articles. I tried the network on three different datasets.

DeepHarmonization - Demo code of the paper: "Deep Image Harmonization", Y

  •    Python

Deep Image Harmonization Yi-Hsuan Tsai, Xiaohui Shen, Zhe Lin, Kalyan Sunkavalli, Xin Lu and Ming-Hsuan Yang IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017. This is the authors' demo code described in the above paper. Please cite our paper if you find it useful for your research.


text-summarization-tensorflow - Tensorflow seq2seq Implementation of Text Summarization.

  •    Python

Simple Tensorflow implementation of text summarization using seq2seq library. Encoder-Decoder model with attention mechanism.

decoder-ring - CLI tool for decoding/encoding from common formats

  •    Go

Decoder-ring is a CLI tool for decoding/encoding from common formats. First install Go.

frontend-regression-validator - Visual regression tool used to compare baseline and updated instances of a website in a deployment pipeline

  •    Python

The visual analysis computes the Normalized Mean Squared error and the Structural Similarity Index on the screenshots of the baseline and updated sites, while the visual AI looks at layout and content changes independently by applying image segmentation Machine Learning techniques to recognize high-level text and image visual structures. This reduces the impact of dynamic content yielding false positives. FRED is designed to be scalable. It has an internal queue and can process websites in parallel depending on the amount of RAM and CPUs (or GPUs) available.

basecrack - Decode All Bases - Base Scheme Decoder

  •    Python

BaseCrack is a tool written in Python that can decode all alphanumeric base encoding schemes. This tool can accept single user input, multiple inputs from a file, input from argument, multi-encoded bases, bases in image EXIF data, bases on images with OCR and decode them incredibly fast. Decode Base16, Base32, Base36, Base58, Base62, Base64, Base64Url, Base85, Ascii85, Base91, Base92 and more with the best base encoding scheme decoding tool in town. It's useful for CTFs, Bug Bounty Hunting, and Cryptography (NOTE: Base Encoding is not an "Encryption" hence it doesn't fall under the Cryptography category, it's useful as base scheme encoding are often used in cryptography tools/projects/challenges).

json - Drop-in replacement for Golang encoding/json with additional features.

  •    Go

Drop-in replacement for Golang encoding/json with additional features. Same usage as Golang encoding/json.






We have large collection of open source products. Follow the tags from Tag Cloud >>


Open source products are scattered around the web. Please provide information about the open source projects you own / you use. Add Projects.