/MXNet-GluonCV-AWS-Coursera

This repo includes my solutions to the Coursera course offered by AWS titled "AWS Computer Vision: Getting Started with GluonCV", in addition to more tutorials and in-depth handson labs. Please :star2: the repo if you like it :point_up: Create an Issue or preferably a PR for any improvement. :rocket:

Primary LanguageJupyter NotebookGNU General Public License v3.0GPL-3.0

MXNet-GluonCV-AWS-Coursera

This repo will include some of my solutions to the Coursera course offered by AWS titled "AWS Computer Vision: Getting Started with GluonCV" with some modifications, in addition to more tutorials and in-depth handson labs.

Warning

This is not a solution notebook, so copying the files and submiting won't work and is against Coursera's Honor Code.

a. DO NOT Email me error messages,

b. DO NOT Create an issue in Github, for your own code, such issues will be closed.

c. DO NOT Request edit access to my colab notebooks, to edit/run please use Open in Playgroung mode from the top-left.

Desciption

There are no programming exercises for modules 1 and 2, so it starts from 3 here.

In case the module notebooks aren't loading on your browser due to large file sizes, you can either download them or simply check them out on Jupyter NBviewer (View only) or Colab (View + Edit):

  1. Module 3: NBviewer link and Colab link

  2. Module 4: NBviewer link and Colab link

  3. Module 5: NBviewer link and Colab link

  4. Module 6: NBviewer link and Colab link

You don't need to request access for any Colab link, just press Open in Playgroung mode from the top-left to run it.

In all these notebooks, I've not modified the code required to pass the assignmnets, but I've added separate ways to load the data and some personal touches as extra functions at the end of the notebook. Some of the added functionality includes:

  1. Testing on multiple images
  2. Testing on images uploaded from User.
  3. Improved and more accurate visualization based on object detection threshold.

I'd love to merge PRs if you discover any of the content stops working in future or if you have a better idea on how to improve this repo, maybe through tutorials and labs 🔥