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 → drckf → Paysage

drckf / Paysage

Licence: other
Unsupervised learning and generative models in python/pytorch.

Programming Languages

python
139335 projects - #7 most used programming language

Labels

machine-learningunsupervised-learninggenerative-model

Projects that are alternatives of or similar to Paysage

Dragan
A stable algorithm for GAN training
Stars: ✭ 189 (+73.39%)
Mutual labels:  unsupervised-learning, generative-model
srVAE
VAE with RealNVP prior and Super-Resolution VAE in PyTorch. Code release for https://arxiv.org/abs/2006.05218.
Stars: ✭ 56 (-48.62%)
Mutual labels:  generative-model, unsupervised-learning
Variational Ladder Autoencoder
Implementation of VLAE
Stars: ✭ 196 (+79.82%)
Mutual labels:  unsupervised-learning, generative-model
Awesome Vaes
A curated list of awesome work on VAEs, disentanglement, representation learning, and generative models.
Stars: ✭ 418 (+283.49%)
Mutual labels:  unsupervised-learning, generative-model
naru
Neural Relation Understanding: neural cardinality estimators for tabular data
Stars: ✭ 76 (-30.28%)
Mutual labels:  generative-model, unsupervised-learning
Discogan Pytorch
PyTorch implementation of "Learning to Discover Cross-Domain Relations with Generative Adversarial Networks"
Stars: ✭ 961 (+781.65%)
Mutual labels:  unsupervised-learning, generative-model
Pysad
Streaming Anomaly Detection Framework in Python (Outlier Detection for Streaming Data)
Stars: ✭ 87 (-20.18%)
Mutual labels:  unsupervised-learning
Ddflow
DDFlow: Learning Optical Flow with Unlabeled Data Distillation
Stars: ✭ 101 (-7.34%)
Mutual labels:  unsupervised-learning
Pointglr
Global-Local Bidirectional Reasoning for Unsupervised Representation Learning of 3D Point Clouds (CVPR 2020)
Stars: ✭ 86 (-21.1%)
Mutual labels:  unsupervised-learning
Attend infer repeat
A Tensorfflow implementation of Attend, Infer, Repeat
Stars: ✭ 82 (-24.77%)
Mutual labels:  generative-model
Psgan
Periodic Spatial Generative Adversarial Networks
Stars: ✭ 108 (-0.92%)
Mutual labels:  generative-model
Dmm
Deep Markov Models
Stars: ✭ 103 (-5.5%)
Mutual labels:  generative-model
Giqa
Pytorch implementation of Generated Image Quality Assessment
Stars: ✭ 100 (-8.26%)
Mutual labels:  generative-model
Self Supervised Relational Reasoning
Official PyTorch implementation of the paper "Self-Supervised Relational Reasoning for Representation Learning", NeurIPS 2020 Spotlight.
Stars: ✭ 89 (-18.35%)
Mutual labels:  unsupervised-learning
Spectralnormalizationkeras
Spectral Normalization for Keras Dense and Convolution Layers
Stars: ✭ 100 (-8.26%)
Mutual labels:  generative-model
Vae For Image Generation
Implemented Variational Autoencoder generative model in Keras for image generation and its latent space visualization on MNIST and CIFAR10 datasets
Stars: ✭ 87 (-20.18%)
Mutual labels:  generative-model
Self Supervised Speech Recognition
speech to text with self-supervised learning based on wav2vec 2.0 framework
Stars: ✭ 106 (-2.75%)
Mutual labels:  unsupervised-learning
Grounder
Implementation of Grounding of Textual Phrases in Images by Reconstruction in Tensorflow
Stars: ✭ 83 (-23.85%)
Mutual labels:  unsupervised-learning
Lggan
[CVPR 2020] Local Class-Specific and Global Image-Level Generative Adversarial Networks for Semantic-Guided Scene Generation
Stars: ✭ 97 (-11.01%)
Mutual labels:  generative-model
Back2future.pytorch
Unsupervised Learning of Multi-Frame Optical Flow with Occlusions
Stars: ✭ 104 (-4.59%)
Mutual labels:  unsupervised-learning
View All Similar Projects ➔

Note: this repository has not been under active development for quite some time

Paysage

Paysage is library for unsupervised learning and probabilistic generative models written in Python. The library is still in the early stages and is not yet stable, so new features will be added frequently.

Currently, paysage can be used to train things like:

  • Bernoulli Restricted Boltzmann Machines
  • Gaussian Restricted Boltzmann Machines
  • Hopfield Models

Using advanced mean field and Markov Chain Monte Carlo methods.

Physics-inspired machine learning

  • Better performance through better algorithms. We are focused on making better Monte Carlo samplers, initialization methods, and optimizers that allow you to train Boltzmann machines without emptying your wallet for a new computer.
  • Stay close to Python. Everybody loves Python, but sometimes it is too slow to get the job done. We want to minimize the amount of computation that gets shifted to the backend by targeting efforts for acceleration to the main bottlenecks in training.

Installation:

We recommend using paysage with Anaconda3. Simply,

  1. Clone this git repo
  2. Move into the directory with setup.py
  3. Run “pip install -e .”

Running the examples requires a file mnist.h5 containing the MNIST dataset of handwritten images. The script download_mnist.py in the mnist/ folder will fetch the file from the web.

Using PyTorch

Paysage uses one of two backends for performing computations. By default, computations are performed using numpy/numexpr/numba on the CPU. If you have installed PyTorch, then you can switch to the pytorch backend by changing the setting in paysage/backends/config.json to pytorch. If you have a CUDA enabled version of pytorch, you can change the setting in paysage/backends/config.json from cpu to gpu to run on the GPU.

System Dependencies

  • hdf5, 1.8 required required by tables
  • llvm, llvm-config required by scikit-learn

About the name:

Boltzmann machines encode information in an "energy landscape" where highly probable states have low energy and lowly probable states have high energy. The name "landscape" was already taken, but the French translation "paysage" was not.

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].