All Projects → ikostrikov → Pytorch Flows

ikostrikov / Pytorch Flows

Licence: mit
PyTorch implementations of algorithms for density estimation

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to Pytorch Flows

Tf 2.0 Hacks
Contains my explorations of TensorFlow 2.x
Stars: ✭ 369 (-15.95%)
Mutual labels:  neural-networks
Neuralmonkey
An open-source tool for sequence learning in NLP built on TensorFlow.
Stars: ✭ 400 (-8.88%)
Mutual labels:  neural-networks
Cn Deep Learning
Stars: ✭ 423 (-3.64%)
Mutual labels:  neural-networks
Lambdanet
Purely functional artificial neural network library implemented in Haskell.
Stars: ✭ 376 (-14.35%)
Mutual labels:  neural-networks
Nnom
A higher-level Neural Network library for microcontrollers.
Stars: ✭ 382 (-12.98%)
Mutual labels:  neural-networks
Neural Backed Decision Trees
Making decision trees competitive with neural networks on CIFAR10, CIFAR100, TinyImagenet200, Imagenet
Stars: ✭ 411 (-6.38%)
Mutual labels:  neural-networks
Easy Deep Learning With Keras
Keras tutorial for beginners (using TF backend)
Stars: ✭ 367 (-16.4%)
Mutual labels:  neural-networks
Ruby Fann
Ruby library for interfacing with FANN (Fast Artificial Neural Network)
Stars: ✭ 425 (-3.19%)
Mutual labels:  neural-networks
Lasagne
Lightweight library to build and train neural networks in Theano
Stars: ✭ 3,800 (+765.6%)
Mutual labels:  neural-networks
Deep Learning Resources
由淺入深的深度學習資源 Collection of deep learning materials for everyone
Stars: ✭ 422 (-3.87%)
Mutual labels:  neural-networks
Start Machine Learning In 2020
A complete guide to start and improve in machine learning (ML), artificial intelligence (AI) in 2021 without ANY background in the field and stay up-to-date with the latest news and state-of-the-art techniques!
Stars: ✭ 357 (-18.68%)
Mutual labels:  neural-networks
Deep Reinforcement Learning
Repo for the Deep Reinforcement Learning Nanodegree program
Stars: ✭ 4,012 (+813.9%)
Mutual labels:  neural-networks
Nn playground
Experimental keras implementation of novel neural network structures
Stars: ✭ 414 (-5.69%)
Mutual labels:  neural-networks
Cs224n Winter Together
an Open Course Platform for Stanford CS224n (2020 Winter)
Stars: ✭ 374 (-14.81%)
Mutual labels:  neural-networks
Learning To Learn
Learning to Learn in TensorFlow
Stars: ✭ 4,038 (+819.82%)
Mutual labels:  neural-networks
Nn vis
A project for processing neural networks and rendering to gain insights on the architecture and parameters of a model through a decluttered representation.
Stars: ✭ 343 (-21.87%)
Mutual labels:  neural-networks
Simgan
Implementation of Apple's Learning from Simulated and Unsupervised Images through Adversarial Training
Stars: ✭ 406 (-7.52%)
Mutual labels:  neural-networks
Geneticalgorithmpython
Source code of PyGAD, a Python 3 library for building the genetic algorithm and training machine learning algorithms (Keras & PyTorch).
Stars: ✭ 435 (-0.91%)
Mutual labels:  neural-networks
Deepxde
Deep learning library for solving differential equations and more
Stars: ✭ 420 (-4.33%)
Mutual labels:  neural-networks
Edward2
A simple probabilistic programming language.
Stars: ✭ 419 (-4.56%)
Mutual labels:  neural-networks

pytorch-flows

A PyTorch implementations of Masked Autoregressive Flow and some other invertible transformations from Glow: Generative Flow with Invertible 1x1 Convolutions and Density estimation using Real NVP.

For MAF, I'm getting results similar to ones reported in the paper. GLOW requires some work.

Run

python main.py --dataset POWER

Available datasets are POWER, GAS, HEPMASS, MINIBONE and BSDS300. For the moment, I removed MNIST and CIFAR10 because I have plans to add pixel-based models later.

Datasets

The datasets are taken from the original MAF repository. Follow the instructions to get them.

Tests

Tests check invertibility, you can run them as

pytest flow_test.py
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].