Semester 1 2018/19
Xavier Bresson
CE7454: Deep Learning for Data Science Running Python notebooks without local Python installation
Run the notebooks from the cloud using Binder: Simply click here.
Local Python installation
Follow the following instructions to install Miniconda and create a Python environment for the course:
-
Download the Python 3.6 installer for Windows, macOS, or Linux from https://conda.io/miniconda.html and install with default settings. Note for Windows: If you don't know if your operating system is 32-bit or 64-bit, then open Settings-System-About-System type to find out your xx-bit system.
- Windows: Double-click on the
Miniconda3-latest-MacOSX-x86_64.exe
file. - macOS: Run
bash Miniconda3-latest-MacOSX-x86_64.sh
in your terminal. - Linux: Run
bash Miniconda3-latest-Linux-x86_64.sh
in your terminal.
- Windows: Double-click on the
-
Windows: Open the Anaconda Prompt terminal from the Start menu. MacOS, Linux: Open a terminal.
-
Install git:
conda install git
. -
Download the GitHub repository of the course:
git clone https://github.com/xbresson/CE7454_2018
. -
Go to folder CE7454_2018 with
cd CE7454_2018
, and create a Python virtual environment with the packages required for the course:conda env create -f environment.yml
. Note that the environment installation may take some time.Notes:
The installed conda packages can be listed withconda list
.
Some useful Conda commands arepwd
,cd
,ls -al
,rm -r -f folder/
Add a python library to the Python environment:conda install -n CE7454_2018 numpy
(for example)
Read Conda command lines for packages and environments
Read managing Conda environments
Running local Python notebooks
-
Windows: Open the Anaconda Prompt terminal from the Start menu. MacOS, Linux: Open a terminal.
-
Activate the environment. Windows:
activate deeplearn_course
, macOS, Linux:source activate deeplearn_course
. -
Download the python notebooks by direct downloads from the next section or with GitHub with the command
git pull
. -
Start Jupyter with
jupyter notebook
. The command opens a new tab in your web browser. -
Go to the exercise folder, for example
CE7454_2018/codes/lab01_python
.Notes:
Windows: Folder CE7454_2018 is located atC:\Users\user_name\CE7454_2018
. MacOS, Linux:/Users/user_name/CE7454_2018
.
Python notebooks of the course
Note: The datasets are too large for GitHub. They will be automatically downloaded when running the codes, or you can directly download the datasets from CE7454_2018/codes/data
or the zip file Download datasets.
Labs lecture 03: Python and PyTorch
Labs lecture 04: Vanilla Neural Networks Part 1
Labs lecture 06: Vanilla Neural Networks Part 2
Labs lecture 07: Multi-Layer Perceptron Part 1
Labs lecture 08: Multi-Layer Perceptron Part 2
Labs lecture 10: Convolutional Neural Networks
Labs lecture 13: Recurrent Neural Networks
Labs lecture 17: Introduction to Graph Science
Labs lecture 18: Graph Neural Networks Part 1
Labs lecture 19: Graph Neural Networks Part 2
Labs lecture 20: Deep Reinforcement Learning