.. image:: docs/OldStation_example.gif
Example #1 — Old Station:
view comparison <http://184.108.40.206:4141/w/0f5177f4-9ce6-11e6-992c-c86000be451f/view> in 24-bit HD,
original photo <https://flic.kr/p/oYhbBv> CC-BY-SA @siv-athens.
As seen on TV! <https://www.youtube.com/watch?v=LhF_56SxrGk>_ What if you could increase the resolution of your photos using technology from CSI laboratories? Thanks to deep learning and
#NeuralEnhance, it's now possible to train a neural network to zoom in to your images at 2x or even 4x. You'll get even better results by increasing the number of neurons or training with a dataset similar to your low resolution image.
The catch? The neural network is hallucinating details based on its training from example images. It's not reconstructing your photo exactly as it would have been if it was HD. That's only possible in Holywood — but using deep learning as "Creative AI" works and its just as cool! Here's how you can get started...
Examples & Usage <#1-examples--usage>_
Background & Research <#3-background--research>_
Frequent Questions <#5-frequent-questions>_
|Python Version| |License Type| |Project Stars|
.. image:: docs/EnhanceCSI_example.png
1. Examples & Usage
The main script is called
enhance.py, which you can run with Python 3.4+ once it's
setup <#2-installation--setup>_ as below. The
--device argument that lets you specify which GPU or CPU to use. For the samples above, here are the performance results:
- GPU Rendering HQ — Assuming you have CUDA setup and enough on-board RAM to fit the image and neural network, generating 1080p output should complete in 5 seconds, or 2s per image if multiple at the same time.
- CPU Rendering HQ — This will take roughly 20 to 60 seconds for 1080p output, however on most machines you can run 4-8 processes simultaneously given enough system RAM. Runtime depends on the neural network size.
The default is to use
--device=cpu, if you have NVIDIA card setup with CUDA already try
--device=gpu0. On the CPU, you can also set environment variable to
OMP_NUM_THREADS=4, which is most useful when running the script multiple times in parallel.
1.a) Enhancing Images
.. code:: bash
# Run the super-resolution script for one image. python3 enhance.py example.png # Also process multiple files with a single run. python3 enhance.py file1.jpg file2.jpg # Display output images that were given `_ne4x.png` suffix. open *_ne4x.png
1.b) Training Super-Resolution
Pre-trained models are provided in the GitHub releases. Training your own is a delicate process that may require you to pick parameters based on your image dataset.
.. code:: bash
# Remove the model file as don't want to reload the data to fine-tune it. rm -f ne4x*.pkl.bz2 # Pre-train the model using perceptual loss from paper  below. python3.4 enhance.py --train "data/*.jpg" --model custom --scales=2 --epochs=50 \ --perceptual-layer=conv2_2 --smoothness-weight=1e7 --adversary-weight=0.0 \ --generator-blocks=4 --generator-filters=64 # Train the model using an adversarial setup based on  below. python3.4 enhance.py --train "data/*.jpg" --model custom --scales=2 --epochs=250 \ --perceptual-layer=conv5_2 --smoothness-weight=2e4 --adversary-weight=2e5 \ --generator-start=5 --discriminator-start=0 --adversarial-start=5 \ --discriminator-size=64 # The newly trained model is output into this file... ls ne4x-custom-*.pkl.bz2
.. image:: docs/BankLobby_example.gif
Example #2 — Bank Lobby:
view comparison <http://220.127.116.11:4141/w/38d10880-9ce6-11e6-becb-c86000be451f/view> in 24-bit HD,
original photo <https://flic.kr/p/6a8cwm> CC-BY-SA @benarent.
2. Installation & Setup
2.a) Using Docker Image [recommended]
The easiest way to get up-and-running is to
install Docker <https://www.docker.com/>. Then, you should be able to download and run the pre-built image using the
docker command line tool. Find out more about the
alexjc/neural-enhance image on its
Docker Hub <https://hub.docker.com/r/alexjc/neural-enhance/> page.
We recommend you setup an alias called
enhance to automatically expose your
images folder from the current directory so the script can access files and store results where you can access them. This is how you can do it in your terminal console on OSX or Linux:
.. code:: bash
# Setup the alias. Put this in your .bash_rc or .zshrc file so it's available at startup. alias enhance="docker run -v $(pwd)/images:/ne/images -it alexjc/neural-enhance" # Now run any of the examples above using this alias, without the `.py` extension. enhance images/example.jpg
If you want to run on your NVIDIA GPU, you can instead use the image
alexjc/neural-enhance:gpu which comes with CUDA and CUDNN pre-installed in the image. Then run it within
nvidia-docker <https://github.com/NVIDIA/nvidia-docker>_ and it should use your physical hardware!
2.b) Manual Installation [developers]
This project requires Python 3.4+ and you'll also need
scipy (numerical computing libraries) as well as
python3-dev installed system-wide. If you want more detailed instructions, follow these:
Linux Installation of Lasagne <https://github.com/Lasagne/Lasagne/wiki/From-Zero-to-Lasagne-on-Ubuntu-14.04>_ (intermediate)
Mac OSX Installation of Lasagne <http://deeplearning.net/software/theano/install.html#mac-os>_ (advanced)
Windows Installation of Lasagne <https://github.com/Lasagne/Lasagne/wiki/From-Zero-to-Lasagne-on-Windows-7-%2864-bit%29>_ (expert)
Afterward fetching the repository, you can run the following commands from your terminal to setup a local environment:
.. code:: bash
# Create a local environment for Python 3.x to install dependencies here. python3 -m venv pyvenv --system-site-packages # If you're using bash, make this the active version of Python. source pyvenv/bin/activate # Setup the required dependencies simply using the PIP module. python3 -m pip install --ignore-installed -r requirements.txt
After this, you should have
lasagne installed in your virtual environment. You'll also need to download this
pre-trained neural network <https://github.com/alexjc/neural-doodle/releases/download/v0.0/vgg19_conv.pkl.bz2>_ (VGG19, 80Mb) and put it in the same folder as the script to run. To de-install everything, you can just delete the
.. image:: docs/Faces_example.png
Example #3 — Specialized super-resolution for faces, trained on HD examples of celebrity faces only. The quality is significantly higher when narrowing the domain from "photos" in general.
3. Background & Research
This code uses a combination of techniques from the following papers, as well as some minor improvements yet to be documented (watch this repository for updates):
Perceptual Losses for Real-Time Style Transfer and Super-Resolution <http://arxiv.org/abs/1603.08155>_
Real-Time Super-Resolution Using Efficient Sub-Pixel Convolution <https://arxiv.org/abs/1609.05158>_
Deeply-Recursive Convolutional Network for Image Super-Resolution <https://arxiv.org/abs/1511.04491>_
Photo-Realistic Super-Resolution Using a Generative Adversarial Network <https://arxiv.org/abs/1609.04802>_
Special thanks for their help and support in various ways:
- Eder Santana — Discussions, encouragement, and his ideas on
sub-pixel deconvolution <https://github.com/Tetrachrome/subpixel>_.
- Andrew Brock — This sub-pixel layer code is based on
his project repository <https://github.com/ajbrock/Neural-Photo-Editor>_ using Lasagne.
- Casper Kaae Sønderby — For suggesting a more stable alternative to sigmoid + log as GAN loss functions.
4. Troubleshooting Problems
Can't install or Unable to find pgen, not compiling formal grammar.
There's a Python extension compiler called Cython, and it's missing or inproperly installed. Try getting it directly from the system package manager rather than PIP.
sudo apt-get install cython3
NotImplementedError: AbstractConv2d theano optimization failed.
This happens when you're running without a GPU, and the CPU libraries were not found (e.g.
libblas). The neural network expressions cannot be evaluated by Theano and it's raising an exception.
sudo apt-get install libblas-dev libopenblas-dev
TypeError: max_pool_2d() got an unexpected keyword argument 'mode'
You need to install Lasagne and Theano directly from the versions specified in
requirements.txt, rather than from the PIP versions. These alternatives are older and don't have the required features.
python3 -m pip install -r requirements.txt
ValueError: unknown locale: UTF-8
It seems your terminal is misconfigured and not compatible with the way Python treats locales. You may need to change this in your
.bash_rc or other startup script. Alternatively, this command will fix it once for this shell instance.
.. image:: docs/StreetView_example.gif
Example #4 — Street View:
view comparison <http://18.104.22.168:4141/w/3b3c8054-9d00-11e6-9558-c86000be451f/view> in 24-bit HD,
original photo <https://flic.kr/p/gnxcXH> CC-BY-SA @cyalex.
|Python Version| |License Type| |Project Stars|
.. |Python Version| image:: http://aigamedev.github.io/scikit-neuralnetwork/badge_python.svg
.. |License Type| image:: https://img.shields.io/badge/license-AGPL-blue.svg
.. |Project Stars| image:: https://img.shields.io/github/stars/alexjc/neural-enhance.svg?style=flat