Skip to content

FCNs & U-Net for Semantic Segmentation on Carvana Dataset

Notifications You must be signed in to change notification settings

gohurali/carvana-segmentation

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Semantic Segmentation on Carvana Dataset

In this project, I use an adaptation of U-Net with residual connections. This particular implementation of U-Net is lighter as well.

Image with Predictions!

Network Architecture

I utilized the general structure of the network with the same number of downsamples with 3 skip-connections. Both of my implementations will down sample by a factor of 32.

unet arch!

Each block additionally contains a residual connection as well to pass previous information along throughout the network for improvements. The general procedure for a residual connection can be found here:

Residual connections!

Training

I primilarily utilized Google Colab for training thus was restricted to utilizing a NVIDIA Tesla K80 GPU.

Run the training with the following:

python -m train -gpu -logdir training_logs/ --save-every 2 \
--model unet --epochs 10 --batch-size 64 -lr 1e-3 --optimizer Adam \
--scheduler Reduce --workers 2 --resize 256

Referenced Papers:

Many ideas were formulated from the following papers:

Fully Convolutional Networks for Semantic Segmentation
Deep Residual Learning for Image Recognition
U-Net: Convolutional Networks for Biomedical Image Segmentation

About

FCNs & U-Net for Semantic Segmentation on Carvana Dataset

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published