All Projects → reiinakano → Neural Painters

reiinakano / Neural Painters

Licence: cc-by-4.0

Projects that are alternatives of or similar to Neural Painters

Guided Evolutionary Strategies
Guided Evolutionary Strategies
Stars: ✭ 245 (-0.81%)
Mutual labels:  jupyter-notebook
Pomegranate
Fast, flexible and easy to use probabilistic modelling in Python.
Stars: ✭ 2,789 (+1029.15%)
Mutual labels:  jupyter-notebook
Wav2mid
Automatic Music Transcription with Deep Neural Networks
Stars: ✭ 246 (-0.4%)
Mutual labels:  jupyter-notebook
Link Prediction
Representation learning for link prediction within social networks
Stars: ✭ 245 (-0.81%)
Mutual labels:  jupyter-notebook
Jupyter Tips And Tricks
Using Project Jupyter for data science.
Stars: ✭ 245 (-0.81%)
Mutual labels:  jupyter-notebook
Bigquery Oreilly Book
Source code accompanying: BigQuery: The Definitive Guide by Lakshmanan & Tigani to be published by O'Reilly Media
Stars: ✭ 246 (-0.4%)
Mutual labels:  jupyter-notebook
Delf Pytorch
PyTorch Implementation of "Large-Scale Image Retrieval with Attentive Deep Local Features"
Stars: ✭ 245 (-0.81%)
Mutual labels:  jupyter-notebook
Spinzero Jupyter Theme
A minimal Jupyter Notebook theme
Stars: ✭ 246 (-0.4%)
Mutual labels:  jupyter-notebook
Exploratory computing with python
Stars: ✭ 245 (-0.81%)
Mutual labels:  jupyter-notebook
Mltrain Nips 2017
This repository contains all the material for the MLTrain NIPS workshop
Stars: ✭ 246 (-0.4%)
Mutual labels:  jupyter-notebook
Zhihu
知乎看山杯 第二名 解决方案
Stars: ✭ 245 (-0.81%)
Mutual labels:  jupyter-notebook
Conceptualsearch
Train a Word2Vec model or LSA model, and Implement Conceptual Search\Semantic Search in Solr\Lucene - Simon Hughes Dice.com, Dice Tech Jobs
Stars: ✭ 245 (-0.81%)
Mutual labels:  jupyter-notebook
Audio Classification
Code for YouTube series: Deep Learning for Audio Classification
Stars: ✭ 245 (-0.81%)
Mutual labels:  jupyter-notebook
Yolo Series
A series of notebooks describing how to use YOLO (darkflow) in python
Stars: ✭ 245 (-0.81%)
Mutual labels:  jupyter-notebook
Bayesian Optimization
Python code for bayesian optimization using Gaussian processes
Stars: ✭ 245 (-0.81%)
Mutual labels:  jupyter-notebook
Recmetrics
A library of metrics for evaluating recommender systems
Stars: ✭ 244 (-1.21%)
Mutual labels:  jupyter-notebook
Recsys core
[电影推荐系统] Based on the movie scoring data set, the movie recommendation system is built with FM and LR as the core(基于爬取的电影评分数据集,构建以FM和LR为核心的电影推荐系统).
Stars: ✭ 245 (-0.81%)
Mutual labels:  jupyter-notebook
Ml finance codes
Machine Learning in Finance: From Theory to Practice Book
Stars: ✭ 245 (-0.81%)
Mutual labels:  jupyter-notebook
Parametric T Sne
Running parametric t-SNE by Laurens Van Der Maaten with Octave and oct2py.
Stars: ✭ 246 (-0.4%)
Mutual labels:  jupyter-notebook
Scipy 2018 Sklearn
Scipy 2018 scikit-learn tutorial by Guillaume Lemaitre and Andreas Mueller
Stars: ✭ 247 (+0%)
Mutual labels:  jupyter-notebook

Neural Painters: A learned differentiable constraint for generating brushstroke paintings

https://arxiv.org/abs/1904.08410

Abstract

We explore neural painters, a generative model for brushstrokes learned from a real non-differentiable and non-deterministic painting program. We show that when training an agent to "paint" images using brushstrokes, using a differentiable neural painter leads to much faster convergence. We propose a method for encouraging this agent to follow human-like strokes when reconstructing digits. We also explore the use of a neural painter as a differentiable image parameterization. By directly optimizing brushstrokes to activate neurons in a pre-trained convolutional network, we can directly visualize ImageNet categories and generate "ideal" paintings of each class. Finally, we present a new concept called intrinsic style transfer. By minimizing only the content loss from neural style transfer, we allow the artistic medium, in this case, brushstrokes, to naturally dictate the resulting style.

banner

Notebooks

NOTE: THERE ARE NEWER AND MORE READABLE NOTEBOOKS + A LIBRARY AVAILABLE AT https://github.com/reiinakano/neural-painters-pytorch

There are runnable notebooks for the paper in the notebooks/ folder.

To completely reproduce the paper from scratch, there is technically a logical order in which to run these notebooks.

However, since most people will probably only be interested in certain parts of the paper, we have designed them so you will be able to run each part as standalone notebooks. For example, we have provided pre-trained neural painters so you can run the style transfer notebook without having to train your own neural painter.

Note on code quality - I will be the first to tell you that the code quality of these notebooks is not production-level. If you have any questions or trouble understanding the code, please feel free to open an issue and ask.

Notebook descriptions

  • generate_stroke_examples.ipynb - This notebook contains code to generate pre-calculated mappings from action space to brushstroke image. If you don't want to run this, you can always just use the ones we uploaded to Kaggle.

  • train_vae_painter.ipynb and train_gan_painter.ipynb - These notebooks contain code to train VAE and GAN neural painters, respectively. Requires the output from generate_stroke_examples.ipynb.

vae gan

  • recreating_spiral.ipynb - Contains code for the "Recreating SPIRAL Results" section in the paper. Requires a neural painter. We provide pre-trained neural painters if you don't want to train your own.

spiral

  • learning_human_strokes.ipynb - Contains code for the "Towards Learning Human Strokes" section of the paper. Requires a neural painter. We provide pre-trained neural painters if you don't want to train your own.

  • visualizing_imagenet_classes.ipynb - Contains code for the "Visualizing ImageNet Classes" subsection of the paper. Requires a neural painter. We provide pre-trained neural painters if you don't want to train your own.

visualize_imagenet

  • intrinsic_style_transfer.ipynb - Contains code for the "Intrinsic Style Transfer" subsection of the paper. Requires a neural painter. We provide pre-trained neural painters if you don't want to train your own.

intrinsic

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].