Code for training and evaluation of the model from "Language Generation with Recurrent Generative Adversarial Networks without Pre-training"

Overview

Language Generation with Recurrent Generative Adversarial Networks without Pre-training

Code for training and evaluation of the model from "Language Generation with Recurrent Generative Adversarial Networks without Pre-training".

A short summary of the paper is available here.

Sample outputs (32 chars)

" There has been to be a place w
On Friday , the stories in Kapac
From should be taken to make it 
He is conference for the first t
For a lost good talks to ever ti

Training

To start training the CL+VL+TH model, first download the dataset, available at http://www.statmt.org/lm-benchmark/, and extract it into the ./data directory.

Then use the following command:

python curriculum_training.py

The following packages are required:

  • Python 2.7
  • Tensorflow 1.1
  • Scipy
  • Matplotlib

The following parameters can be configured:

LOGS_DIR: Path to save model checkpoints and samples during training (defaults to './logs/')
DATA_DIR: Path to load the data from (defaults to './data/1-billion-word-language-modeling-benchmark-r13output/')
CKPT_PATH: Path to checkpoint file when restoring a saved model
BATCH_SIZE: Size of batch (defaults to 64)
CRITIC_ITERS: Number of iterations for the discriminator (defaults to 10)
GEN_ITERS: Number of iterations for the geneartor (defaults to 50)
MAX_N_EXAMPLES: Number of samples to load from dataset (defaults to 10000000)
GENERATOR_MODEL: Name of generator model (currently only 'Generator_GRU_CL_VL_TH' is available)
DISCRIMINATOR_MODEL: Name of discriminator model (currently only 'Discriminator_GRU' is available)
PICKLE_PATH: Path to PKL directory to hold cached pickle files (defaults to './pkl')
ITERATIONS_PER_SEQ_LENGTH: Number of iterations to run per each sequence length in the curriculum training (defaults to 15000)
NOISE_STDEV: Standard deviation for the noise vector (defaults to 10.0)
DISC_STATE_SIZE: Discriminator GRU state size (defaults to 512)
GEN_STATE_SIZE: Genarator GRU state size (defaults to 512)
TRAIN_FROM_CKPT: Boolean, set to True to restore from checkpoint (defaults to False)
GEN_GRU_LAYERS: Number of GRU layers for the genarator (defaults to 1)
DISC_GRU_LAYERS: Number of GRU layers for the discriminator (defaults to 1)
START_SEQ: Sequence length to start the curriculum learning with (defaults to 1)
END_SEQ: Sequence length to end the curriculum learning with (defaults to 32)
SAVE_CHECKPOINTS_EVERY: Save checkpoint every # steps (defaults to 25000)
LIMIT_BATCH: Boolean that indicates whether to limit the batch size  (defaults to true)

Parameters can be set by either changing their value in the config file or by passing them in the terminal:

python curriculum_training.py --START_SEQ=1 --END_SEQ=32

Generating text

The generate.py script will generate BATCH_SIZE samples using a saved model. It should be run using the parameters used to train the model (if they are different than the default values). For example:

python generate.py --CKPT_PATH=/path/to/checkpoint/seq-32/ckp --DISC_GRU_LAYERS=2 --GEN_GRU_LAYERS=2

(If your model has not reached stage 32 in the curriculum, make sure to change the '32' in the path above to the maximal stage in the curriculum that your model trained on.)

Evaluating text

To evaluate samples using our %-IN-TEST-n metrics, use the following command, linking to a txt file where each row is a sample:

python evaluate.py --INPUT_SAMPLE=/path/to/samples.txt

Reference

If you found this code useful, please cite the following paper:

@article{press2017language,
  title={Language Generation with Recurrent Generative Adversarial Networks without Pre-training},
  author={Press, Ofir and Bar, Amir and Bogin, Ben and Berant, Jonathan and Wolf, Lior},
  journal={arXiv preprint arXiv:1706.01399},
  year={2017}
}

Acknowledgments

This repository is based on the code published in Improved Training of Wasserstein GANs.

Awesome Transformers in Medical Imaging

This repo supplements our Survey on Transformers in Medical Imaging Fahad Shamshad, Salman Khan, Syed Waqas Zamir, Muhammad Haris Khan, Munawar Hayat,

Fahad Shamshad 666 Jan 06, 2023
CTF Challenge for CSAW Finals 2021

Terminal Velocity Misc CTF Challenge for CSAW Finals 2021 This is a challenge I've had in mind for almost 15 years and never got around to building un

Jordan 6 Jul 30, 2022
RodoSol-ALPR Dataset

RodoSol-ALPR Dataset This dataset, called RodoSol-ALPR dataset, contains 20,000 images captured by static cameras located at pay tolls owned by the Ro

Rayson Laroca 45 Dec 15, 2022
Self-Supervised depth kalilia

Self-Supervised depth kalilia

24 Oct 15, 2022
Python calculations for the position of the sun and moon.

Astral This is 'astral' a Python module which calculates Times for various positions of the sun: dawn, sunrise, solar noon, sunset, dusk, solar elevat

Simon Kennedy 169 Dec 20, 2022
So-ViT: Mind Visual Tokens for Vision Transformer

So-ViT: Mind Visual Tokens for Vision Transformer        Introduction This repository contains the source code under PyTorch framework and models trai

Jiangtao Xie 44 Nov 24, 2022
Implementation of the paper "Language-agnostic representation learning of source code from structure and context".

Code Transformer This is an official PyTorch implementation of the CodeTransformer model proposed in: D. Zügner, T. Kirschstein, M. Catasta, J. Leskov

Daniel Zügner 131 Dec 13, 2022
Weakly-Supervised Semantic Segmentation Network with Deep Seeded Region Growing (CVPR 2018).

Weakly-Supervised Semantic Segmentation Network with Deep Seeded Region Growing (CVPR2018) By Zilong Huang, Xinggang Wang, Jiasi Wang, Wenyu Liu and J

Zilong Huang 245 Dec 13, 2022
Automatic detection and classification of Covid severity degree in LUS (lung ultrasound) scans

Final-Project Final project in the Technion, Biomedical faculty, by Mor Ventura, Dekel Brav & Omri Magen. Subproject 1: Automatic Detection of LUS Cha

Mor Ventura 1 Dec 18, 2021
The Pytorch implementation for "Video-Text Pre-training with Learned Regions"

Region_Learner The Pytorch implementation for "Video-Text Pre-training with Learned Regions" (arxiv) We are still cleaning up the code further and pre

Rui Yan 0 Mar 20, 2022
[ICLR 2022 Oral] F8Net: Fixed-Point 8-bit Only Multiplication for Network Quantization

F8Net Fixed-Point 8-bit Only Multiplication for Network Quantization (ICLR 2022 Oral) OpenReview | arXiv | PDF | Model Zoo | BibTex PyTorch implementa

Snap Research 76 Dec 13, 2022
D2LV: A Data-Driven and Local-Verification Approach for Image Copy Detection

Facebook AI Image Similarity Challenge: Matching Track —— Team: imgFp This is the source code of our 3rd place solution to matching track of Image Sim

16 Dec 25, 2022
Translation-equivariant Image Quantizer for Bi-directional Image-Text Generation

Translation-equivariant Image Quantizer for Bi-directional Image-Text Generation Woncheol Shin1, Gyubok Lee1, Jiyoung Lee1, Joonseok Lee2,3, Edward Ch

Woncheol Shin 7 Sep 26, 2022
The source code for Adaptive Kernel Graph Neural Network at AAAI2022

AKGNN The source code for Adaptive Kernel Graph Neural Network at AAAI2022. Please cite our paper if you think our work is helpful to you: @inproceedi

11 Nov 25, 2022
EFENet: Reference-based Video Super-Resolution with Enhanced Flow Estimation

EFENet EFENet: Reference-based Video Super-Resolution with Enhanced Flow Estimation Code is a bit messy now. I woud clean up soon. For training the EF

Yaping Zhao 19 Nov 05, 2022
A flag generation AI created using DeepAIs API

Vex AI or Vexiology AI is an Artifical Intelligence created to generate custom made flag design texts. It uses DeepAIs API. Please be aware that you must include your own DeepAI API key. See instruct

Bernie 10 Apr 06, 2022
Shape Matching of Real 3D Object Data to Synthetic 3D CADs (3DV project @ ETHZ)

Real2CAD-3DV Shape Matching of Real 3D Object Data to Synthetic 3D CADs (3DV project @ ETHZ) Group Member: Yue Pan, Yuanwen Yue, Bingxin Ke, Yujie He

24 Jun 22, 2022
Implementation of popular SOTA self-supervised learning algorithms as Fastai Callbacks.

Self Supervised Learning with Fastai Implementation of popular SOTA self-supervised learning algorithms as Fastai Callbacks. Install pip install self-

Kerem Turgutlu 276 Dec 23, 2022
Pytorch code for "State-only Imitation with Transition Dynamics Mismatch" (ICLR 2020)

This repo contains code for our paper State-only Imitation with Transition Dynamics Mismatch published at ICLR 2020. The code heavily uses the RL mach

20 Sep 08, 2022
A neuroanatomy-based augmented reality experience powered by computer vision. Features 3D visuals of the Atlas Brain Map slices.

Brain Augmented Reality (AR) A neuroanatomy-based augmented reality experience powered by computer vision that features 3D visuals of the Atlas Brain

Yasmeen Brain 10 Oct 06, 2022