Convolutional Neural Networks
Deeplearning.AI | Coursera
All of the code is in Tensorflow and Python 3. The model is trained to mix content image with style image using neural style transfer!
With all dependencies installed, jupyter notebook is provided in the course but if you want to run it on local machine (cuz you are curious to test it on gpu).
I recommend to install the Python bundle Anaconda. All the assignments have been done with Python 3, so download the installation script accordingly. You can then install Jupyter Notebook from conda.
The next step is to install TensorFlow. At the time of writing, the latest release is r0.9, after several upgrades during the course. You can refer to the official documentation. Here is the list of commands:
$ conda create -n tensorflow
$ source activate tensorflow
(tensorflow)$ conda install -c conda-forge tensorflow
(tensorflow)$ pip install --upgrade tensorflow-hub
To run it using gpu you need to additionally install cuda & cudann.
To train the agent, start jupyter notebook, open Art_Generation_with_Neural_Style_Transfer_v3a.ipynb and execute! For more information, please check instructions inside the notebook.