Using the MNIST dataset to determine numbers from handwritten images.
- Go to https://www.anaconda.com/download and download the Python 3.6 version for your system
- Open the terminal and run conda info to ensure this was done
- Run conda create - makers python=3.5
- On windows, run activate makers OR on unix systems, source activate makers
- Make sure pip is installed with pip -v
- If it's not, go to https://pip.pypa.io/en/stable/installing/ and install it
- On windows, run pip install --ignore-installed --upgrade tensorflow OR on unix systems, pip install tensorflow
- Check that this worked by typing python and then import tensorflow as tf
- Run conda install scikit-learn
- Check that this worked by typing python then import sklearn
- Check numpy with python then import numpy as np
- Run python -mpip install -U pip
- Run python -mpip install -U matplotlib
- Run pip install keras
- Run pip install keras-tqdm
- Run jupyter nbextension enable --py --sys-prefix widgetsnbextension
- Launch notebook with jupyter notebook
Fill in missing lines in Makers_AI_Tutorial_InProgress.ipynb