This project makes image classification using convolutional networks.
See the jupyter notebook
Understand convolutional networks.
- Python 3 - Language
- Anaconda - Python Data Science Platform
- Jupyter notebook - Web application that allows to create documents that contain live code
CIFAR 10 dataset.
- Download and install Anaconda
- Update Anaconda
$ conda upgrade conda $ conda upgrade --all
- Clone and enter into the project's root directory by command line
$ git clone https://github.com/machine-learning-experiments/image-classification-by-cifar-10.git
- Create and activate enviroment
$ conda env create -f enviroment.yaml $ conda activate image-classification-by-cifar-10
or
conda create --name image-classification-by-cifar-10 python=3 source activate image-classification-by-cifar-10 conda install numpy jupyter notebook tqdm tensorflow matplotlib scikit-learn
- Start jupyter notebook
$ jupyter notebook
- Your browser will open showing a list of files, click on the dlnd_image_classification.ipynb notebook file
This project was developed during the deep-learning nanodegree from Udacity