Skip to content

README.md

Latest commit

 

History

History
25 lines (17 loc) · 1.66 KB

README.md

File metadata and controls

25 lines (17 loc) · 1.66 KB
Raw

MNIST-CNN

MiniProject 3: Multi-label Classification of Image Data COMP 551 (001/002), Fall 2020, McGill University

Importing the MNIST_synthetic.h5 Dataset

  1. Please un-zip the MNIST_synthetic.zip file in this repository.
  2. Upload the H5PY dataset directly to the home directory of your Goole Drive.
  3. Open the Jupyter Notebook in Google Colab. Make sure you use the same Google account as the previous step.
  4. Run the Jupyter Notebook in Google Colab. Please follow the instrcutions given by Google Colab at runtime in order to grant the program access to the H5PY dataset saved in your Google Drive.

Loading Private Notebooks

Loading a notebook from a private GitHub repository is possible, but requires an additional step to allow Colab to access your files. Do the following:

  1. Navigate to http://colab.research.google.com/github.
  2. Click the "Include Private Repos" checkbox.
  3. In the popup window, sign-in to your Github account and authorize Colab to read the private files.
  4. Your private repositories and notebooks will now be available via the github navigation pane.

Saving Notebooks To GitHub or Drive

Any time you open a GitHub hosted notebook in Colab, it opens a new editable view of the notebook. You can run and modify the notebook without worrying about overwriting the source.

If you would like to save your changes from within Colab, you can use the File menu to save the modified notebook either to Google Drive or back to GitHub. Choose File→Save a copy in Drive or File→Save a copy to GitHub and follow the resulting prompts. To save a Colab notebook to GitHub requires giving Colab permission to push the commit to your repository.