RESUNET Implementation in PyTorch

This tutorial focuses on implementing the image segmentation architecture called Deep Residual UNET (RESUNET) in the PyTorch framework. It’s an encoder-decoder architecture developed by Zhengxin Zhang et al. for semantic segmentation. It was initially used for road extraction from high-resolution aerial images in the field of remote sensing image analysis. Original Paper: Road Extraction Continue Reading

UNET Implementation in PyTorch

This tutorial focus on the implementation of the image segmentation architecture called UNET in the PyTorch framework. It’s a simple encoder-decoder architecture developed by Olaf Ronneberger et al. for Biomedical Image Segmentation in 2015 at the University of Freiburg, Germany. What is Image Segmentation? An image consists of multiple objects Continue Reading

UNET Implementation in TensorFlow using Keras API

In this post, you will learn how to implement UNET architecture in TensorFlow using Keras API. The post helps you to learn about UNET, and how to use it for your research. UNET is one of the most popular semantic segmentation architecture. Olaf Ronneberger et al. developed this network for Continue Reading

What is RESUNET

RESUNET refers to Deep Residual UNET. It’s an encoder-decoder architecture developed by Zhengxin Zhang et al. for semantic segmentation. It was initially used for the road extraction from the high-resolution aerial images in the field of remote sensing image analysis. Later, it was adopted by researchers for multiple other applications Continue Reading

DCGAN – Implementing Deep Convolutional Generative Adversarial Network in TensorFlow

In this tutorial, we are going to implement a Deep Convolutional Generative Adversarial Network (DCGAN) on Anime faces dataset. The code is written in TensorFlow 2.2 and Python3.8 .  According to Yann LeCun, the director of Facebook AI, GAN is the “most interesting idea in the last 10 years of Continue Reading

UNET Segmentation with Pretrained MobileNetV2 as Encoder

In this tutorial, we are going to work on UNet segmentation and use it for biomedical image segmentation tasks. This time we are going to use pre-trained MobileNetV2 as the encoder for the UNet architecture. We are going to integrate the pre-trained MobileNetV2 with the UNet and have an efficient Continue Reading