aravindsrinivas / Flowpp
Licence: mit
Code for reproducing Flow ++ experiments
Stars: ✭ 137
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Flowpp
Pytorch Model Zoo
A collection of deep learning models implemented in PyTorch
Stars: ✭ 125 (-8.76%)
Mutual labels: neural-networks
Pysnn
Efficient Spiking Neural Network framework, built on top of PyTorch for GPU acceleration
Stars: ✭ 129 (-5.84%)
Mutual labels: neural-networks
Deep Learning With Python
Example projects I completed to understand Deep Learning techniques with Tensorflow. Please note that I do no longer maintain this repository.
Stars: ✭ 134 (-2.19%)
Mutual labels: neural-networks
Gon
Gradient Origin Networks - a new type of generative model that is able to quickly learn a latent representation without an encoder
Stars: ✭ 126 (-8.03%)
Mutual labels: neural-networks
Keras2cpp
it's a small library for running trained Keras 2 models from a native C++ code.
Stars: ✭ 124 (-9.49%)
Mutual labels: neural-networks
Pytorch 101 Tutorial Series
PyTorch 101 series covering everything from the basic building blocks all the way to building custom architectures.
Stars: ✭ 136 (-0.73%)
Mutual labels: neural-networks
Scarpet Nn
Tools and libraries to run neural networks in Minecraft ⛏
Stars: ✭ 129 (-5.84%)
Mutual labels: neural-networks
Ed4
Computational Cognitive Neuroscience, Fourth Edition
Stars: ✭ 133 (-2.92%)
Mutual labels: neural-networks
Jsnet
Javascript/WebAssembly deep learning library for MLPs and convolutional neural networks
Stars: ✭ 126 (-8.03%)
Mutual labels: neural-networks
Machine Learning Flappy Bird
Machine Learning for Flappy Bird using Neural Network and Genetic Algorithm
Stars: ✭ 1,683 (+1128.47%)
Mutual labels: neural-networks
Chainer Cifar10
Various CNN models for CIFAR10 with Chainer
Stars: ✭ 134 (-2.19%)
Mutual labels: neural-networks
Astronn
Deep Learning for Astronomers with Tensorflow
Stars: ✭ 125 (-8.76%)
Mutual labels: neural-networks
Persephone
A tool for automatic phoneme transcription
Stars: ✭ 130 (-5.11%)
Mutual labels: neural-networks
Ncrfpp
NCRF++, a Neural Sequence Labeling Toolkit. Easy use to any sequence labeling tasks (e.g. NER, POS, Segmentation). It includes character LSTM/CNN, word LSTM/CNN and softmax/CRF components.
Stars: ✭ 1,767 (+1189.78%)
Mutual labels: neural-networks
Ml Agents
Unity Machine Learning Agents Toolkit
Stars: ✭ 12,134 (+8756.93%)
Mutual labels: neural-networks
Dnw
Discovering Neural Wirings (https://arxiv.org/abs/1906.00586)
Stars: ✭ 133 (-2.92%)
Mutual labels: neural-networks
Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design
This repository contains Tensorflow implementation of experiments from the paper Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design - Jonathan Ho, Xi Chen, Aravind Srinivas, Yan Duan, Pieter Abbeel
Dependencies
- python3.6
- Tensorflow v1.10.1
- horovod v0.14.1
Horovod GPU setup instructions
Usage Instructions
We trained our models using 8 GPUs with data-parallelism using Horovod.
CIFAR 10
mpiexec -n 8 python3.6 run_cifar.py
Imagenet
Data for Imagenet Experiments:
Script to create dataset here
Imagenet 32x32
mpiexec -n 8 python3.6 -m flows_imagenet.launchers.imagenet32_official
Imagenet 64x64
mpiexec -n 6 python3.6 -m flows_imagenet.launchers.imagenet64_official
mpiexec -n 6 python3.6 -m flows_imagenet.launchers.imagenet64_5bit_official
CelebA-HQ 64x64
Data:
Download links in README
mpiexec -n 8 python3.6 -m flows_celeba.launchers.celeba64_5bit_official
mpiexec -n 8 python3.6 -m flows_celeba.launchers.celeba64_3bit_official
Contact
Please open an issue
Credits
flowpp was originally developed by Jonathan Ho (UC Berkeley), Peter Chen (UC Berkeley / covariant.ai), Aravind Srinivas (UC Berkeley), Yan Duan (covariant.ai), and Pieter Abbeel (UC Berkeley / covariant.ai).
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].