https://github.com/arnaudmiribel/deeplearning_fundamentals

CEPE - Les fondamentaux du Deep Learning
https://github.com/arnaudmiribel/deeplearning_fundamentals

Last synced: 24 days ago
JSON representation

CEPE - Les fondamentaux du Deep Learning

• Host: GitHub
• URL: https://github.com/arnaudmiribel/deeplearning_fundamentals
• Owner: arnaudmiribel
• Created: 2018-11-21T23:16:31.000Z (about 6 years ago)
• Default Branch: master
• Last Pushed: 2018-11-22T08:01:29.000Z (about 6 years ago)
• Last Synced: 2024-11-03T09:42:14.508Z (2 months ago)
• Language: Jupyter Notebook
• Size: 13.3 MB
• Stars: 0
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Get started

## Environment

If we didn't solve the git issue, download https://framadrop.org/r/zLXsNA4csN#rwdyzM9G/rqbs8bn5aqPPbbVFxKt1UYgd+2pbk4/YPg= and unzip !

First create the proper Anaconda environment using :

`conda env create -f deepenv.yml`

This will normally install more than necessary packages for you that concern either deep learning (Keras, Tensorflow) or regular packages for data science (pandas, sklearn, ...).

Usually, the environment we like to prototype models using Python is Jupyter Notebooks. It's an interactive python session with a great interface. You can run this using :

`jupyter notebook`

And it should open a web browser on a locally hosted server :-)

## Data

You may download ASAP one of the datasets we'll use (cats vs dogs !) 

- Sample of 1K images / class : https://framadrop.org/r/9ebeOxTas7#VumhlR4Ct4J+E1BGjgQ2e+G8tozax2uUjvp1Yhzndmo= (link dies in 7 days)

- Sample of 5K images / class : https://framadrop.org/r/QkeS-hLvt3#GpZDIyQrSBiRGJ5znS/LBWoEsQzOF44G+pIYGSSOyqg= (link dies in 24 hours)