Skip to content

Deepak2405/Efficient-Convolutional-Neural-Network-for-Semantic-Segmentation

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

26 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Efficient-Convolutional-Neural-Network-for-Semantic-Segmentation

This code is inspired from paper "ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation" by Adam Paszke, Abhishek Chaurasia, Sangpil Kim, Eugenio Culurciello

Dataset : CamVid Dataset Library : Keras for Deep Learning, OpenCV for Reading/writing images

Batchsize : Standard Batchsize is 10, Set to 1 ( my PC has 8GB RAM , multiple batchsize does not run in my current PC settings)

Current PC Settings

GPU: RTX2080Ti RAM : 8GB

Command to train the model

python3 trainEnet.py

trained Data saved as ENet.h5 Command to test the model

python3 predict.py

Prediction on CamVid standard video

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages