Skip to content

I've worked on a research project implementing Double Convolution Neural Network using, lasagne, theano, Caffe, and Matlab using PYTHON.

Notifications You must be signed in to change notification settings

Aryan05/DCNN-ComputerVision

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Doubly Convolutional Neural Network

Project by

Aryan Karn - 20185106 MNNIT-Allahabad ECE

Original Paper

Doubly Convolutional Neural Networks (NIPS 2016) by Shuangfei Zhai, Yu Cheng, Weining Lu and Zhongfei (Mark) Zhang

Repository Content

  • Final Project contains main DCNN code written in python
  • Forword Pass contains Matlab code of forword pass for understanding and proof of concept
  • Correlation contains python code to extract weights from caffee model, matlab code to find averaged max transalation correlation of a layer, ploted results
  • Presentation Raw files, images, graphs for Presentation

Pre-requisites

Code is written in python and would require following libraries:

  • numpy
  • theano (tensor)
  • lasagne

Our Code is tested on Windows10 intel(i7)64 and MaC without CUDA but should run on any OS satisfying above pre-requisites.

Setting Various Parameters

Default Parameters:

num_epochs = 100
learning_rate = 1e-2 
metafilter_shape = [(2, 1, 6, 6), (4, 2, 6, 6)]
image_shape = (1, 28, 28)
kernel_size = 5
kernel_pool_size = 2
learning_decay = 1e-5
dropout_rate = 0.5
batch_size = 200

These parameters can be found and changed just below main function declaration.

Running the code

You can run the code using following command inside final project.

sudo python main_final.py

Note: sudo access is required is to write results in a file

Architecture

DCNN and CNN Architecture

Results

Test Error vs Epoch

Links

About

I've worked on a research project implementing Double Convolution Neural Network using, lasagne, theano, Caffe, and Matlab using PYTHON.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published