Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/rakibhhridoy/neuralstyletransfer-tensorflow

One of the curious outcome of data science revolution is neural style transfer where nst algorithm merge two images, content and style, creating a artistic image of content image. Here TensorFlow is used to process images and lastly used nst algorithm.
https://github.com/rakibhhridoy/neuralstyletransfer-tensorflow

deep-learning deep-neural-networks machine-learning neural-style-transfer neuralstyletransfer nst python tensorflow

Last synced: 13 days ago
JSON representation

One of the curious outcome of data science revolution is neural style transfer where nst algorithm merge two images, content and style, creating a artistic image of content image. Here TensorFlow is used to process images and lastly used nst algorithm.

Awesome Lists containing this project

README

        

# *Neural Style Transfer Learning In Tensorflow*

![nst](Images/nst.jpg)


*The image showed is not actual outcome. It was personal project thus actual image can't be showed here.*

##### *The Art Of Deep Learning*
### *The Image size can be easily kept as it was by using ```opencv``` python library.*
> open notebook, before training the model resize you image as you want. Add a cell in notebook and resize image using following code:
```python
import cv2
import os

height = None #change as you need
width = None #change as you need
url = ('style image url')

image = cv2.resize(url, height = height, width = width)

## Now use it..
```

### Environment
Make sure you have all necessery python library installed. For this projects you need
* Numpy
* TensorFlow
* Keras

if you don't have these libraries go to python or anaconda prompt and paste these:
```bash
pip install numpy
pip install tensorflow
pip install keras
```

### Get touch with Me
Connect- [Linkedin](https://linkedin.com/in/rakibhhridoy)

Website- [RakibHHridoy](https://rakibhhridoy.github.io)