Light

neocxi / pixelsnail-public Goto Github PK

View Code? Open in Web Editor NEW

124.0 5.0 23.0 604 KB

License: MIT License

Python 100.00%

pixelsnail-public's Introduction

PixelSNAIL

This is a Python3 / Tensorflow implementation of PixelSNAIL.

This code base is based on OpenAI's PixelCNN++ code.

Setup

To run this code you need the following:

a machine with multiple GPUs
Python3
Numpy, TensorFlow

Training the model

Use the train.py script to train the model.

Pretrained model checkpoint

You can download our pretrained (TensorFlow) CIFAR10 model and ImageNet model

CIFAR10

python train.py \
       --data_set=cifar \
       --model=h12_noup_smallkey \
       --nr_logistic_mix=10 \
       --nr_filters=256 \
       --batch_size=8 \
       --init_batch_size=8 \
       --dropout_p=0.5 \
       --polyak_decay=0.9995 \
       --save_interval=10

ImageNet

python train.py \
       --data_set=imagenet \
       --model=h12_noup_smallkey \
       --nr_logistic_mix=32 \
       --nr_filters=256 \
       --batch_size=8 \
       --init_batch_size=8 \
       --learning_rate=0.001 \
       --dropout_p=0.0 \
       --polyak_decay=0.9997 \
       --save_interval=1

pixelsnail-public's People

Contributors

Stargazers

Watchers

pixelsnail-public's Issues

Condition generative model on labels

would it work if I remove "raise NotImplementedError"?

Code and paper don't match at all.

faint

How long should it take to train on CIFAR 10?

How many GPUs of what model were used to train the authors' CIFAR 10 model? How long did it take?

missing data folder

The pixelCNN++ code here has a "data" folder that this code also seems to rely on (I just copied it from that repo and it seemed to work). That code has imageio as an additional dependency.

Generating new data

Hanging after make_template

I am trying to train a vanilla CIFAR-10 Pixel-SNAIL model using the command given in the README.

In Tensorflow 1.9, the code is hanging at these lines:

model = tf.make_template('model', getattr(pxpp_models, args.model + "_spec"))
with tf.device('/gpu:0'):
gen_par = model(x_init, h_init, init=True,
dropout_p=args.dropout_p, **model_opt)

Is this a known issue that can be resolved? Which version of Tensorflow has been tested?

Recommend Projects

React

A declarative, efficient, and flexible JavaScript library for building user interfaces.
Vue.js

🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript

TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
TensorFlow

An Open Source Machine Learning Framework for Everyone
Django

The Web framework for perfectionists with deadlines.
Laravel

A PHP framework for web artisans
D3

Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

javascript

JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
web

Some thing interesting about web. New door for the world.
server

A server is a program made to process requests and deliver data to clients.
Machine learning

Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Visualization

Some thing interesting about visualization, use data art
Game

Some thing interesting about game, make everyone happy.

Recommend Org

Facebook

We are working to build community through open source technology. NB: members must have two-factor auth.
Microsoft

Open source projects and samples from Microsoft.
Google

Google ❤️ Open Source for everyone.
Alibaba

Alibaba Open Source for everyone
D3

Data-Driven Documents codes.
Tencent

China tencent open source team.