kcbighuge / SDCND-Semantic-Segmentation

Image segmentation of road images using a Fully Convolutional Network (FCN)

Semantic Segmentation

Introduction

In this project, we label the pixels of a road in images using a Fully Convolutional Network (FCN).

Setup

Frameworks and Packages

Make sure to have the following is installed:

• Python 3
• TensorFlow
• NumPy
• SciPy

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 a test images.

Run

Use the following command to run the project:

python main.py

Note If running this in Jupyter Notebook, system messages (such as those regarding test status) may appear in the terminal rather than the notebook.

Submission

This project was originated from the Advanced Deep Learning project created by Udacity. The project was implemented to pass these rubric points.

Tips

• The link for the frozen VGG16 model is hardcoded into helper.py. The model can be found here
• The model is not vanilla VGG16, but a fully convolutional version, which already contains the 1x1 convolutions to replace the fully connected layers. Please see this forum post for more information. A summary of additional points, follow.
• The original FCN-8s was trained in stages. The authors later uploaded a version that was trained all at once to their GitHub repo. The version in the GitHub repo has one important difference: The outputs of pooling layers 3 and 4 are scaled before they are fed into the 1x1 convolutions. As a result, some students have found that the model learns much better with the scaling layers included. The model may not converge substantially faster, but may reach a higher IoU and accuracy.
• When adding l2-regularization, setting a regularizer in the arguments of the tf.layers is not enough. Regularization loss terms must be manually added to your loss function. otherwise regularization is not implemented.

---