vimsu99.blogspot.com

developerstation.org

DeveloperStation.ORG: About Me

http://www.developerstation.org/p/rahul-kavi-my-reserach-page.html

Video Lectures and Talks. I'm a grad student. I write on DeveloperStation. This blog) to keep a "dairy" of some sort to look-up for myself in the future and to help others in the process. I always like to keep a track of present trends in Technology, Programming. You can follow me on Google Plus. My research publications are listed on my Google Scholar page. Paulo Coelho: I have learned. My Amazon Wish List. Subscribe to: Posts (Atom). Fav Networking, Linux, Computer Vision Blogs.

developerstation.org

DeveloperStation.ORG: very basic intro to Caffe

http://www.developerstation.org/2015/08/intro-to-caffe-tutorial.html

Video Lectures and Talks. Monday, August 10, 2015. Very basic intro to Caffe. This tutorial just gives you a basic idea of what Caffe can do (not for advanced use of Caffe through defining your own layers, using C /Python API) for defining your own network to solve a Computer Vision task. I'm assuming you already have a background in Machine Learning, Statistical Pattern Recognition and have built Neural Networks in the past using some programming language. Create train.txt and test.txt with file...You t...

developerstation.org

DeveloperStation.ORG: February 2014

http://www.developerstation.org/2014_02_01_archive.html

Video Lectures and Talks. Wednesday, February 5, 2014. Fun with my Raspberry Pi. I ordered a Raspberry Pi recently. I've heard so much about this device in the recent past, I decide to try it out. I was reminded of few microprocessor(fun class) and electrical engineering(not so fun time) classes that I took in my undergrad. I wrote a simple program that could turn a Stepper Motor using a motor controller. Connected to a Raspberry Pi. HDMI cable to connect to a TV or monitor. For powering the stepper motor.

developerstation.org

DeveloperStation.ORG: simple Convolutional Neural Net based object recognition

http://www.developerstation.org/2016/03/simple-convolutional-neural-net-based.html

Video Lectures and Talks. Wednesday, March 9, 2016. Simple Convolutional Neural Net based object recognition. I made a simple object recognition module over the last weekend. I wrote a Theano. Based convolutional neural network. I wrote a simple OpenCV. Based image segmentation program. The output from the image segmentation program is passed to the Theano based Convolutional Neural Network. I used 10,000 images for training and 16,000 images for testing. Posted by Rahul Kavi. On the way to Virtual World.

developerstation.org

DeveloperStation.ORG: June 2013

http://www.developerstation.org/2013_06_01_archive.html

Video Lectures and Talks. Sunday, June 9, 2013. Logisitic Regression in OpenCV. I finished writing a Logistic Regression classifier in OpenCV. I've seen a lot of posts on the web asking for OpenCV's version of the same but its not available. Its easy to write your own logistic regression classifier. I separated out the cost function and gradient descent algorithm (Batch Gradient Descent). You can replace it with your own optimization algorithm. I posted it on my Github page. You can check it out:.

developerstation.org

DeveloperStation.ORG: August 2015

http://www.developerstation.org/2015_08_01_archive.html

Video Lectures and Talks. Monday, August 10, 2015. Very basic intro to Caffe. This tutorial just gives you a basic idea of what Caffe can do (not for advanced use of Caffe through defining your own layers, using C /Python API) for defining your own network to solve a Computer Vision task. I'm assuming you already have a background in Machine Learning, Statistical Pattern Recognition and have built Neural Networks in the past using some programming language. Create train.txt and test.txt with file...You t...

developerstation.org

DeveloperStation.ORG: March 2016

http://www.developerstation.org/2016_03_01_archive.html

Video Lectures and Talks. Sunday, March 13, 2016. Simple Autoencoder on MNIST dataset. So, I had fun with Theano and trained an Autoencoder on a MNIST dataset. More about Autoencoders is available here. More variants of Autoencoders exist (Sparse, Contractive, etc.) are available with different constraints on the hidden layer representation. I trained an vanilla Autoencoder for 100 epochs with 16 mini batch size and learning rate of 0.01. Posted by Rahul Kavi. Wednesday, March 9, 2016. The output from th...

developerstation.org

DeveloperStation.ORG: December 2012

http://www.developerstation.org/2012_12_01_archive.html

Video Lectures and Talks. Sunday, December 23, 2012. Review: Mastering OpenCV with Practical Computer Vision Projects. I got hold of this new book titled " Mastering OpenCV with Practical Computer Vision Projects. I personally liked the part on Point Cloud Library and OpenCV. I liked the Chapter 9 where they discussed Kinect and OpenCV. This chapter was provided as a digital download (as a link). Before trying this book. Posted by Rahul Kavi. Monday, December 17, 2012. Neural Networks in Octave. Review: ...

developerstation.org

DeveloperStation.ORG: Simple Autoencoder on MNIST dataset

http://www.developerstation.org/2016/03/simple-autoencoder-on-mnist-dataset.html

Video Lectures and Talks. Sunday, March 13, 2016. Simple Autoencoder on MNIST dataset. So, I had fun with Theano and trained an Autoencoder on a MNIST dataset. More about Autoencoders is available here. More variants of Autoencoders exist (Sparse, Contractive, etc.) are available with different constraints on the hidden layer representation. I trained an vanilla Autoencoder for 100 epochs with 16 mini batch size and learning rate of 0.01. Posted by Rahul Kavi. Subscribe to: Post Comments (Atom).

developerstation.org

DeveloperStation.ORG: January 2014

http://www.developerstation.org/2014_01_01_archive.html

Video Lectures and Talks. Thursday, January 30, 2014. Setting up Ad-hoc network in Ubuntu 12.04 or Debian. I had a hard time looking for setting up an Ad-hoc network. This post explains to setup an ad-hoc network in one of the most easiest ways. The basic idea behind setting this up is, set up an ad-hoc network on your both (or more) computers individually and let them talk (or ping) to each other. You will have to do the following in both(or more, replace the ip addresses) of the computers. Comp Vision ...