Image segmentation example image

Image Segmentation using deconvolution layer in Tensorflow

by koustubh • May 30, 2017

 In this series of post, we shall learn the algorithm for image segmentation and implementation of the same using Tensorflow. This is the first part of the series where we shall focus on understanding and be implementing a deconvolutional/fractional-strided-convolutional layer in Tensorflow.   Why is deconvolutional layer so important? Image segmentation is just one of […]

Continue Reading
Keras tensorflow tutorial

Keras Tensorflow tutorial: Practical guide from getting started to developing complex deep neural network

by Ankit Sachan • May 16, 2017

Keras is a high-level python API which can be used to quickly build and train neural networks using either Tensorflow or Theano as back-end. This tutorial assumes that you are slightly familiar with Tensorflow and convolutional neural networks. Otherwise, please follow the 10 minutes quick tensorflow tutorial and/or convolutional neural network tutorial and come back here. […]

Continue Reading
Deep Learning on Raspberry Pi

Accelerating Convolutional Neural Networks on Raspberry Pi

by koustubh • April 5, 2017

Unless you have been living under the rock, you must have heard of the revolution that deep learning and convolutional neural networks have brought in computer vision. Computers have achieved near-human level accuracy for most of the tasks. However, most of the top performing neural networks for state of the art image recognition problem suffer […]

Continue Reading
Tensorflow tutorial for deep learning

Quick complete Tensorflow tutorial to understand and run Alexnet, VGG, Inceptionv3, Resnet and squeezeNet networks

by Ankit Sachan • March 31, 2017

 This Tensorflow tutorial for convolutional neural networks has three parts: 1. We shall look at some of the most successful convolutional neural network architectures like Inception, AlexNet, Resnet etc. 2. In the second part, we shall take a quick tutorial of a popular high-level and light-weight Tensorflow library called TensorFlow-Slim(TF-Slim). 3. Finally, using TF-Slim, we […]

Continue Reading
Tensorflow tutorials

A quick complete tutorial to save and restore Tensorflow models

by Ankit Sachan • March 20, 2017

In this Tensorflow tutorial, I shall explain: How does a Tensorflow model look like? How to save a Tensorflow model? How to restore a Tensorflow model for prediction/transfer learning? How to work with imported pretrained models for fine-tuning and modification This tutorial assumes that you have some idea about training a neural network. Otherwise, please […]

Continue Reading

Tensorflow Tutorial 2: image classifier using convolutional neural network

by Ankit Sachan • February 26, 2017

In this Tensorflow tutorial, we shall build a convolutional neural network based image classifier using Tensorflow. If you are just getting started with Tensorflow, then it would be a good idea to read the basic Tensorflow tutorial here. To demonstrate how to build a convolutional neural network based image classifier, we shall build a 6 […]

Continue Reading

TensorFlow Tutorial: 10 minutes Practical TensorFlow lesson for quick learners

by Ankit Sachan • February 8, 2017

This TensorFlow tutorial is for someone who has basic idea about machine learning and trying to get started with TensorFlow. You would need to have TensorFlow installed. You can follow this tutorial to install TensorFlow. This tensorflow tutorial is divided into two parts; in first part we explain the basics with example; in second part […]

Continue Reading

Install Tensorflow-1.0 with GPU on ubuntu 14.04 on AWS P2.xlarge

by koustubh • February 8, 2017

This post is for you if you are looking to install TensorFlow 1.0 from source on ubuntu 14.04 on AWS machine with GPU support(CUDA). Quick Summary of setup: OS: ubuntu 14.04 Cloud: AWS P2.xlarge instance TensorFlow version: 1.0.0-rc1 Bazel Version: 0.4.4 CuDNN: 5.1 CUDA: 8.0 Once you have launched an AWS P2.xlarge instance with ubuntu […]

Continue Reading
Show attend and tell, a communication system

Show, attend and tell: Fine details of how state-of-the-art deep learning systems generate image captions

by koustubh • January 13, 2017

How would YOU communicate with Aliens ? How would you teach them your language ? The way we teach children right ? By showing them pictures of various objects and their names. Basically Associating the Image and the Text. That’s the goal of automatic image captioning. It is an extensive topic and decades of research has gone into […]

Continue Reading

Case-Study: Better HAAR feature-based Eye Detector using OpenCV

by koustubh • January 11, 2017

Motivation behind this post: Opencv object detectors which are built using Haar feature-based cascade classifiers is at least a decade old. OpenCV framework provides a default pre-built haar and lbp based cascade classifiers for face and eye detection which are very good quality detectors. However, I had never measured the accuracy of these face and […]

Continue Reading