Fast Style Transfer in TensorFlow

Add styles from famous paintings to any photo in a fraction of a second! You can even style videos!

It takes 100ms on a 2015 Titan X to style the MIT Stata Center (1024×680) like Udnie, by Francis Picabia.

Our implementation is based off of a combination of Gatys' A Neural Algorithm of Artistic Style, Johnson's Perceptual Losses for Real-Time Style Transfer and Super-Resolution, and Ulyanov's Instance Normalization.

Sponsorship

Please consider sponsoring my work on this project!

Video Stylization

Here we transformed every frame in a video, then combined the results. Click to go to the full demo on YouTube! The style here is Udnie, as above.

See how to generate these videos here!

Image Stylization

We added styles from various paintings to a photo of Chicago. Click on thumbnails to see full applied style images.

Implementation Details

Our implementation uses TensorFlow to train a fast style transfer network. We use roughly the same transformation network as described in Johnson, except that batch normalization is replaced with Ulyanov's instance normalization, and the scaling/offset of the output tanh layer is slightly different. We use a loss function close to the one described in Gatys, using VGG19 instead of VGG16 and typically using "shallower" layers than in Johnson's implementation (e.g. we use relu1_1 rather than relu1_2). Empirically, this results in larger scale style features in transformations.

Virtual Environment Setup (Anaconda) - Windows/Linux

Tested on | Spec | | |-----------------------------|-------------------------------------------------------------| | Operating System | Windows 10 Home | | GPU | Nvidia GTX 2080 TI | | CUDA Version | 11.0 | | Driver Version | 445.75 |

Step 1：Install Anaconda

https://docs.anaconda.com/anaconda/install/

Step 2：Build a virtual environment

Run the following commands in sequence in Anaconda Prompt: conda create -n tf-gpu tensorflow-gpu=2.1.0 conda activate tf-gpu conda install jupyterlab jupyter lab Run the following command in the notebook or just conda install the package: !pip install moviepy==1.0.2 Follow the commands below to use fast-style-transfer

Documentation

Training Style Transfer Networks

Use style.py to train a new style transfer network. Run python style.py to view all the possible parameters. Training takes 4-6 hours on a Maxwell Titan X. More detailed documentation here. Before you run this, you should run setup.sh. Example usage:

python style.py --style path/to/style/img.jpg \
  --checkpoint-dir checkpoint/path \
  --test path/to/test/img.jpg \
  --test-dir path/to/test/dir \
  --content-weight 1.5e1 \
  --checkpoint-iterations 1000 \
  --batch-size 20

Evaluating Style Transfer Networks

Use evaluate.py to evaluate a style transfer network. Run python evaluate.py to view all the possible parameters. Evaluation takes 100 ms per frame (when batch size is 1) on a Maxwell Titan X. More detailed documentation here. Takes several seconds per frame on a CPU. Models for evaluation are located here. Example usage:

python evaluate.py --checkpoint path/to/style/model.ckpt \
  --in-path dir/of/test/imgs/ \
  --out-path dir/for/results/

Stylizing Video

Use transform_video.py to transfer style into a video. Run python transform_video.py to view all the possible parameters. Requires ffmpeg. More detailed documentation here. Example usage:

python transform_video.py --in-path path/to/input/vid.mp4 \
  --checkpoint path/to/style/model.ckpt \
  --out-path out/video.mp4 \
  --device /gpu:0 \
  --batch-size 4

Requirements

You will need the following to run the above: - TensorFlow 0.11.0 - Python 2.7.9, Pillow 3.4.2, scipy 0.18.1, numpy 1.11.2 - If you want to train (and don't want to wait for 4 months): - A decent GPU - All the required NVIDIA software to run TF on a GPU (cuda, etc) - ffmpeg 3.1.3 if you want to stylize video