Skip to content

Latest commit

 

History

History
38 lines (27 loc) · 1.69 KB

README.md

File metadata and controls

38 lines (27 loc) · 1.69 KB

Fully Convolutional Neural Networks for Image Segmentation of the CamVid dataset

Table of Contents

General Information

  • The goal of the project is to develop a model to perform image segmentation CamVid dataset
  • I will train the model on a custom dataset prepared by divamgupta. This contains video frames from a moving vehicle and is a subsample of the CamVid dataset.

Decoder

  • I am using a Unet neural network architecture which consists of an encoder and decoder section. This architecture is also a fully convolutional network:

Decoder

  • I will be using a pretrained VGG-16 network for the feature extraction path, then followed by an FCN-8 network for upsampling and generating the predictions. The output will be a label map (i.e. segmentation mask) with predictions for 12 classes.
  • The model achieves an accuracy of 84% on the validation set after 170 epochs.
  • I ran the notebook on Arizona State University's supercomputing cluster using one Tesla V100 GPUs. The information regarding the GPUs is included at the end of the notebook.

Results

Example screenshot

Technologies Used

  • Python
  • Tensorflow
  • Pandas
  • Matplotlib
  • Keras

Contact

Created by Miralireza Nabavi - feel free to contact me!