EfficientNets: The Free lunch of 2019 for convolutional neural networks

by Ankit Sachan • November 7, 2019

Neural network architecture design is one of the key hyperparameters in solving problems using deep learning and computer vision. Various neural networks are compared on two key factors i.e. accuracy and computational requirement. In general, as we aim to design more accurate neural networks, the computational requirement increases. The term ‘Efficient’ in Efficient Net strongly […]

Continue Reading

Real time deep learning based face detection with MTCNN

by Ankit Sachan • October 13, 2019

Today, we are going to use deep learning to detect faces in images and videos using Tensorflow. You guys might have seen a lot of demos of face detection online. Most of these demos or projects are built using Haar cascade in OpenCV. Haar cascades have a lot of issues when applied to real-world videos. They […]

Continue Reading

Detailed Guide to Understand and Implement ResNets

by Ankit Sachan • September 17, 2019

ResNet is one of the most powerful deep neural networks which has achieved fantabulous performance results in the ILSVRC 2015 classification challenge. ResNet has achieved excellent generalization performance on other recognition tasks and won the first place on ImageNet detection, ImageNet localization, COCO detection and COCO segmentation in ILSVRC and COCO 2015 competitions. There are […]

Continue Reading

Developer Guide to Key Differences between Python 2 and 3

by Ankit Sachan • August 8, 2019

The Python 3 programming language was released in December 2008 and served as the next version intended to improve upon and replace Python 2. It introduced many syntactic revisions along with a much larger standard library to improve Python’s usability and programming experience. Due to these changes, Python 3 is not directly backward compatible with […]

Continue Reading

NSFW Tensorflow: Identifying objectionable content using Deep Learning

by Utkarsh Gupta • June 25, 2019

In today’s post, we would learn how to identify not safe for work images using Deep Learning. Not-Safe-For-Work images can be described as any images which can be deemed inappropriate in a workplace primarily because it may contain: Sexual or pornographic images Violence Extreme graphics like gore or abusive Suggestive content For example, LinkedIn is […]

Continue Reading