- Make Deep Learning easier (minimal code).
- Minimise required mathematics.
- Make it practical (runs on laptops).
- Open Source Deep Learning Learning.
- Grow a collaborating practical community around DL.
- Memes: No seriously. Make DL fun and interactive, this means more Trump tweets.
There's a few ways you can support this initiative:
- Right now this is very much a self funded project. If you wish to see more and more high quality tutorials and videos support us at: https://www.patreon.com/deepschoolio
- Subscribe to our YouTube channel here.
- Star this repository and share it!
The following contents are each contained within a folder:
- Data Science (eg. Pandas)
- Deep Learning (Keras)
- Bayesian Learning (PyMC3)
If you are a beginner (haven't done CNNs yet) simply click this link instead of following the installation comands below. It launches a live notebook server with these notebooks using binder:
- Install Docker https://www.docker.com/
- Use the following commands to run from docker1.
git clone https://github.com/sachinruk/deepschool.io.git
cd deepschool.io
bash run.sh
- Now go to
localhost:9000
on your browser to start using the jupyter notebooks. - (Optional) If you are on a mac/windows some of the examples may not work because the docker image may run out of memory. Hence under preferences in docker there is the option to increase the allocated memory. I have set it to 8GB. Run
bash run.sh
again if you reset memory.
See here for installing on windows.
You can ask questions and join the development discussion:
- On the DeepSchool-io Google group. Long detailed questions go here.
- On the DeepSchool-io Slack channel. Use this link to request an invitation to the channel.
First meetup node: https://www.meetup.com/DeepSchool-io/
Find the corresponding video tutorial here (not all notebooks have an associated video) https://www.youtube.com/playlist?list=PLIx9QCwIhuRS1SPS9LHF7VjvZyM1g2Swz
1: Refer to this Dockerfile and this for information on how the docker image was built.