Image Captioning
Project Overview
In this project, you will create a neural network architecture to automatically generate captions from images.
After using the Microsoft Common Objects in COntext (MS COCO) dataset to train your network, you will test your network on novel images!
Project Instructions
The project is structured as a series of Jupyter notebooks that are designed to be completed in sequential order:
- 0_Dataset.ipynb
- 1_Preliminaries.ipynb
- 2_Training.ipynb
- 3_Inference.ipynb
You can find these notebooks in the Udacity workspace that appears in the concept titled Project: Image Captioning. This workspace provides a Jupyter notebook server directly in your browser.
You can read more about workspaces (and how to toggle GPU support) in the following concept (Introduction to GPU Workspaces). This concept will show you how to toggle GPU support in the workspace.
You MUST enable GPU mode for this project.
Evaluation
Your project will be reviewed by a Udacity reviewer against the CNN project rubric. Review this rubric thoroughly, and self-evaluate your project before submission. All criteria found in the rubric must meet specifications for you to pass.
Ready to submit your project?
You may only submit from the workspace for this project, linked here. Please delete any large files and model checkpoints in the home directory of of your workspace. Then click Submit , a button that appears on the bottom right of the workspace, to submit your project.
Project Submission Checklist
Before submitting your project, please review and confirm the following items.
I am confident all rubric items have been met and my project will pass as submitted.
Project builds correctly without errors and runs.
All required functionality exists and my project behaves as expected per the project's specifications.
Once you have checked all these items, you are ready to submit!