The objective of this project is to build a Fully Connected Convolutional Neural Net to identify the road in a collection of pictures. The encoding of the FCN will be provided by a pre-trained VGG16 model and the decoder will be built using 1x1 convolutions, upscaling and layer skipping.
This project is part of Udacity's Self Driving Car Nanodegree Course.
- Ensure you've passed all the unit tests. [X]
- Ensure you pass all points on the rubric. [X]
Frameworks and Packages
Make sure you have the following is installed:
Implement the code in the
main.py module indicated by the "TODO" comments.
The comments indicated with "OPTIONAL" tag are not required to complete.
Run the following command to run the project: