Repository for the Zero to Deep Learning Video Course
|size (curr.)||6694 kB|
Zero to Deep Learning® Video Course
Welcome to the Zero to Deep Learning® Video Course repository.
Get started guide
Clone this repository on your local computer
git clone https://github.com/Dataweekends/zero_to_deep_learning_video.git
Download and Install Anaconda Python 3.7
Change to course folder
Create the course environment
conda env create
wait for the environment to create.
Activate the environment (Mac/Linux)
conda activate ztdl
Activate the environment (Windows)
conda activate ztdl
Check that your prompt changed to
Launch Jupyter Notebook
Open your browser to
Run the Check environment Notebook
Go to the course folder, open the notebook
0_Check_Environment.ipynb and run it. If you see the message:
Houston we are go!
You are good to go! Enjoy!
If for some reason you don’t see
Houston we are go!, the simplest solution is to delete the environment and start from scratch again.
To remove the environment:
- close the browser and go back to your terminal
- stop jupyter notebook (CTRL-C)
- deactivate the environment (Mac/Linux):
- deactivate the environment (Windows 10):
- delete the environment:
conda remove -y -n ztdl --all
- restart from environment creation and make sure that each steps completes till the end.
One thing you can also try is to update your conda executable. This may help if you already had Anaconda installed on your system.
conda update conda
These instructions have been tested on:
- Mac OSX Sierra 10.14.1
- Ubuntu 18.04
- Windows 10
Running the course on Google Colaboratory with free GPU support
Google offers a free platform to run Jupyter notebooks called Google Colaboratory. You need a Gmail or Google Apps email address to use it.
Follow these steps:
- Open your browser and go to https://colab.research.google.com/
- Choose the GITHUB tab and paste the repository address:
https://github.com/Dataweekends/zero_to_deep_learning_videoin the search bar.
- Click on the notebook you would like to run
- Enable GPU support in the
Edit -> Notebook Settingsmenu
- Enjoy running the notebook with GPU support!
- If the notebook loads data from the repo you will have to download the data too. Follow these steps to do that:
- Create a code cell at the top of the notebook
- Clone the repository in Colab:
!git clone https://github.com/Dataweekends/zero_to_deep_learning_video.git
- Replace the
zero_to_deep_learning_video/datain the cell that loads the data.
Running the course on Floyd with GPU support
FloydHub provides a zero-install platform-as-a-service for training and deploying DL models in the cloud. Here are the steps to run the course on Floyd:
Sign-up on FloydHub
Go to: www.floydhub.com and register.
Install or update Floyd
In the terminal, with the activated
ztdl environment, run:
pip install -U floyd-cli
Login into Floyd
This will open a browser and you will have to log in with your User/Password. Then copy the token to the terminal and hit ENTER.
Initialize the current project
floyd init zerotodeeplearning
Run a notebook with GPU support
floyd run --mode jupyter --env tensorflow --gpu --data ghegoo/datasets/crowdflower-male-female/1
Wait for the notebook to come online and then navigate to the url
Enjoy GPU power
Run a notebook and experience the awesome power of a GPU!
When you are finished, remember to STOP the floyd environment so that you don’t incur in charges.
floyd stop <PROJECT-ID>
Make sure that you have stopped the project by checking the floyd page.