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 → iwangjian → Textsum Gan

iwangjian / Textsum Gan

Tensorflow re-implementation of GAN for text summarization

Programming Languages

python
139335 projects - #7 most used programming language

Labels

tensorflowgenerative-adversarial-networktext-summarization

Projects that are alternatives of or similar to Textsum Gan

Text Summarizer
Python Framework for Extractive Text Summarization
Stars: ✭ 96 (-13.51%)
Mutual labels:  text-summarization
Gaal Based Outlier Detection
GAAL-based Outlier Detection
Stars: ✭ 102 (-8.11%)
Mutual labels:  generative-adversarial-network
Stylegan2 Projecting Images
Projecting images to latent space with StyleGAN2.
Stars: ✭ 102 (-8.11%)
Mutual labels:  generative-adversarial-network
Tagan
An official PyTorch implementation of the paper "Text-Adaptive Generative Adversarial Networks: Manipulating Images with Natural Language", NeurIPS 2018
Stars: ✭ 97 (-12.61%)
Mutual labels:  generative-adversarial-network
Lsd Seg
Learning from Synthetic Data: Addressing Domain Shift for Semantic Segmentation
Stars: ✭ 99 (-10.81%)
Mutual labels:  generative-adversarial-network
Natsr
Natural and Realistic Single Image Super-Resolution with Explicit Natural Manifold Discrimination (CVPR, 2019)
Stars: ✭ 105 (-5.41%)
Mutual labels:  generative-adversarial-network
Sprint gan
Privacy-preserving generative deep neural networks support clinical data sharing
Stars: ✭ 92 (-17.12%)
Mutual labels:  generative-adversarial-network
Pytorch Gan Timeseries
GANs for time series generation in pytorch
Stars: ✭ 109 (-1.8%)
Mutual labels:  generative-adversarial-network
Spectralnormalizationkeras
Spectral Normalization for Keras Dense and Convolution Layers
Stars: ✭ 100 (-9.91%)
Mutual labels:  generative-adversarial-network
Unet Stylegan2
A Pytorch implementation of Stylegan2 with UNet Discriminator
Stars: ✭ 106 (-4.5%)
Mutual labels:  generative-adversarial-network
Lggan
[CVPR 2020] Local Class-Specific and Global Image-Level Generative Adversarial Networks for Semantic-Guided Scene Generation
Stars: ✭ 97 (-12.61%)
Mutual labels:  generative-adversarial-network
Chemgan Challenge
Code for the paper: Benhenda, M. 2017. ChemGAN challenge for drug discovery: can AI reproduce natural chemical diversity? arXiv preprint arXiv:1708.08227.
Stars: ✭ 98 (-11.71%)
Mutual labels:  generative-adversarial-network
Faceaging By Cyclegan
Stars: ✭ 105 (-5.41%)
Mutual labels:  generative-adversarial-network
Doppelganger
[IMC 2020 (Best Paper Finalist)] Using GANs for Sharing Networked Time Series Data: Challenges, Initial Promise, and Open Questions
Stars: ✭ 97 (-12.61%)
Mutual labels:  generative-adversarial-network
Exermote
Using Machine Learning to predict the type of exercise from movement data
Stars: ✭ 108 (-2.7%)
Mutual labels:  generative-adversarial-network
Porousmediagan
Reconstruction of three-dimensional porous media using generative adversarial neural networks
Stars: ✭ 94 (-15.32%)
Mutual labels:  generative-adversarial-network
Deligan
This project is an implementation of the Generative Adversarial Network proposed in our CVPR 2017 paper - DeLiGAN : Generative Adversarial Networks for Diverse and Limited Data. DeLiGAN is a simple but effective modification of the GAN framework and aims to improve performance on datasets which are diverse yet small in size.
Stars: ✭ 103 (-7.21%)
Mutual labels:  generative-adversarial-network
Stylegan Web
A web porting for NVlabs' StyleGAN.
Stars: ✭ 112 (+0.9%)
Mutual labels:  generative-adversarial-network
Transformersum
Models to perform neural summarization (extractive and abstractive) using machine learning transformers and a tool to convert abstractive summarization datasets to the extractive task.
Stars: ✭ 107 (-3.6%)
Mutual labels:  text-summarization
Pixel2style2pixel
Official Implementation for "Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation"
Stars: ✭ 1,395 (+1156.76%)
Mutual labels:  generative-adversarial-network
View All Similar Projects ➔

GAN for Text Summarization

Tensorflow re-implementation of Generative Adversarial Network for Abstractive Text Summarization.

Requirements

  • Python3
  • Tensorflow >= 1.4 (tested on Tensorflow 1.4.1)
  • numpy
  • tqdm
  • sklearn
  • rouge
  • pyrouge

You can use the python package manager of your choice (pip/conda) to install the dependencies. The code is tested on Ubuntu 16.04 operating system.

Quickstart

  • Dataset

    Please follow the instructions here for downloading and preprocessing the CNN/DailyMail dataset. After that, store data files train.bin, val.bin, test.bin and vocabulary file vocab into specified data directory, e.g., ./data/.

  • Prepare negative samples for discriminator

    You can download the prepared data discriminator_train_data.npz for discriminator from dropbox and store into specified data directory, e.g., ./data/.

  • Train the full model

    python3 main.py --mode=train --data_path=./data/train.bin --vocab_path=./data/vocab --log_root=./log --pretrain_dis_data_path=./data/discriminator_train_data.npz --restore_best_model=False

  • Decode

    python3 main.py --mode=decode --data_path=./data/test.bin --vocab_path=./data/vocab --log_root=./log --single_pass=True

References

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].