gsurma / Style_transfer
Licence: mit
CNN image style transfer π¨.
Stars: β 210
Programming Languages
python
139335 projects - #7 most used programming language
Labels
Projects that are alternatives of or similar to Style transfer
Human Activity Recognition Using Cnn
Convolutional Neural Network for Human Activity Recognition in Tensorflow
Stars: β 382 (+81.9%)
Mutual labels: jupyter-notebook, notebook, convolutional-neural-networks, cnn
Image classifier
CNN image classifier implemented in Keras Notebook πΌοΈ.
Stars: β 139 (-33.81%)
Mutual labels: jupyter-notebook, notebook, convolutional-neural-networks, cnn
Tensorflow 101
TensorFlow 101: Introduction to Deep Learning for Python Within TensorFlow
Stars: β 642 (+205.71%)
Mutual labels: jupyter-notebook, convolutional-neural-networks, style-transfer
Tensorflow Tutorial
TensorFlow and Deep Learning Tutorials
Stars: β 748 (+256.19%)
Mutual labels: notebook, convolutional-neural-networks, cnn
Deep Learning With Python
Deep learning codes and projects using Python
Stars: β 195 (-7.14%)
Mutual labels: jupyter-notebook, convolutional-neural-networks, cnn
Zhihu
This repo contains the source code in my personal column (https://zhuanlan.zhihu.com/zhaoyeyu), implemented using Python 3.6. Including Natural Language Processing and Computer Vision projects, such as text generation, machine translation, deep convolution GAN and other actual combat code.
Stars: β 3,307 (+1474.76%)
Mutual labels: jupyter-notebook, convolutional-neural-networks, style-transfer
Food Recipe Cnn
food image to recipe with deep convolutional neural networks.
Stars: β 448 (+113.33%)
Mutual labels: jupyter-notebook, convolutional-neural-networks, cnn
Svhn Cnn
Google Street View House Number(SVHN) Dataset, and classifying them through CNN
Stars: β 44 (-79.05%)
Mutual labels: jupyter-notebook, convolutional-neural-networks, cnn
Yann
This toolbox is support material for the book on CNN (http://www.convolution.network).
Stars: β 41 (-80.48%)
Mutual labels: jupyter-notebook, convolutional-neural-networks, cnn
Cnn Interpretability
π₯ Visualizing Convolutional Networks for MRI-based Diagnosis of Alzheimerβs Disease
Stars: β 68 (-67.62%)
Mutual labels: jupyter-notebook, convolutional-neural-networks, cnn
Gtsrb
Convolutional Neural Network for German Traffic Sign Recognition Benchmark
Stars: β 65 (-69.05%)
Mutual labels: jupyter-notebook, convolutional-neural-networks, cnn
Pytorch Learners Tutorial
PyTorch tutorial for learners
Stars: β 97 (-53.81%)
Mutual labels: jupyter-notebook, convolutional-neural-networks, cnn
Pytorch Image Classification
Tutorials on how to implement a few key architectures for image classification using PyTorch and TorchVision.
Stars: β 272 (+29.52%)
Mutual labels: jupyter-notebook, convolutional-neural-networks, cnn
Music recommender
Music recommender using deep learning with Keras and TensorFlow
Stars: β 528 (+151.43%)
Mutual labels: jupyter-notebook, convolutional-neural-networks, cnn
Convisualize nb
Visualisations for Convolutional Neural Networks in Pytorch
Stars: β 57 (-72.86%)
Mutual labels: jupyter-notebook, convolutional-neural-networks, cnn
Keras transfer cifar10
Object classification with CIFAR-10 using transfer learning
Stars: β 120 (-42.86%)
Mutual labels: jupyter-notebook, convolutional-neural-networks, cnn
Practical Machine Learning With Python
Master the essential skills needed to recognize and solve complex real-world problems with Machine Learning and Deep Learning by leveraging the highly popular Python Machine Learning Eco-system.
Stars: β 1,868 (+789.52%)
Mutual labels: jupyter-notebook, notebook, convolutional-neural-networks
Depression Detect
Predicting depression from acoustic features of speech using a Convolutional Neural Network.
Stars: β 187 (-10.95%)
Mutual labels: convolutional-neural-networks, cnn
Bilinear Cnn Tensorflow
This is an implementation of Bilinear CNN for fine grained visual recognition using TensorFlow.
Stars: β 187 (-10.95%)
Mutual labels: convolutional-neural-networks, cnn
Nbinteract
Create interactive webpages from Jupyter Notebooks
Stars: β 189 (-10%)
Mutual labels: jupyter-notebook, notebook
Style Transfer
Style Transfer is a process in which we strive to modify the style of an image while preserving its content. Given an input image and a style image, we can compute an output image with the original content but a new style.
Check out corresponding Medium article:
Style Transfer - Styling Images with Convolutional Neural Networks
How does it work?
- We take input image and style images and resize them to equal shapes.
- We load a pre-trained CNN (VGG16).
- Knowing that we can distinguish layers that are responsible for the style (basic shapes, colors etc.) and the ones responsible for the content (image-specific features), we can separate the layers to independently work on the content and style.
- Then we set our task as an optimization problem where we are going to minimize:
- content loss (distance between the input and output images - we strive to preserve the content)
- style loss (distance between the style and output images - we strive to apply a new style)
- total variation loss (regularization - spatial smoothness to denoise the output image)
- Finally, we set our gradients and optimize with the L-BFGS algorithm.
Results
Input
Style
Output
1 iteration
2 iterations
5 iterations
10 iterations
15 iterations
Other examples
Author
Greg (Grzegorz) Surma
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].