资源算法fast-neural-style.tf

fast-neural-style.tf

2020-02-07 | |  49 |   0 |   0

fast-neural-style.tf

An implementation of [1][2].

Time: 0.05 seconds on NVIDIA TITAN X GPU for at resolution of 1200x630.

图片.png

图片.png

图片.png

Requirement

Tensorflow(>= r0.11), Numpy, Scipy, Pillow

Usage

python render.py --input $INPUT_IMAGE --output $OUTPUT_FILE_NAME --model $MODEL_NAME --arch $GENERATOR_ARCH

Training

Coming soon.

License

MIT

Reference

[1] Johnson, Justin, Alexandre Alahi, and Li Fei-Fei. "Perceptual losses for real-time style transfer and super-resolution." arXiv preprint arXiv:1603.08155.

[2] Ulyanov, Dmitry, Andrea Vedaldi, and Victor Lempitsky. "Instance Normalization: The Missing Ingredient for Fast Stylization." arXiv preprint arXiv:1607.08022.

[3] Gatys, Leon A., Alexander S. Ecker, and Matthias Bethge. "A neural algorithm of artistic style." arXiv preprint arXiv:1508.06576.


上一篇:Fast-Neural-Style-Transfer

下一篇:fast-neural-style-keras

用户评价
全部评价

热门资源

  • Keras-ResNeXt

    Keras ResNeXt Implementation of ResNeXt models...

  • seetafaceJNI

    项目介绍 基于中科院seetaface2进行封装的JAVA...

  • spark-corenlp

    This package wraps Stanford CoreNLP annotators ...

  • capsnet-with-caps...

    CapsNet with capsule-wise convolution Project ...

  • inferno-boilerplate

    This is a very basic boilerplate example for pe...