Skip to content

jane212/CarND-Semantic-Segmentation

Repository files navigation

Semantic Segmentation

Introduction

In this project, we use Fully Convolutional Network (FCN) to classify every pixel in an image to be road or not road. It is a basic step in scene understanding. This project implements the idea from this paper: Fully Convolutional Networks for Semantic Segmentation

Setup

Frameworks and Packages

Make sure you have the following is installed:

Dataset

Download the Kitti Road dataset from here. Extract the dataset in the data folder. This will create the folder data_road with all the training and test images.

Model

Hyperparameter

  • number of epochs: 50
  • batch size: 16
  • keep_prob: 0.75
  • learning_rate: 0.0001

Run

Run the following command to run the project:

python main.py

Results

Loss over training

The loss is decreasing over training and converge at the end. The loss value vs. training time is shown below.

Inference on test

Several sample images with labeled pixels are shown below.

About

No description or website provided.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages