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 Biomedical Image Segmentation in 2015.

To know more, read the article: What is UNET?


In this first part of the post, you need to import all classes required for the implementation of the UNET architecture.

from tensorflow.keras.layers import Conv2D, BatchNormalization, Activation, MaxPool2D, Conv2DTranspose, Concatenate, Input
from tensorflow.keras.models import Model


The current era started to move towards Artificial Intelligence, which massively impacted the world with its ability to achieve the tasks that were a dream of humanity. All of these achievements are mainly due to the research and development in the field of Deep Learning and Neural Network, which are a part of Artificial Intelligence.

What is the GPU?

A graphics processing unit or GPU is a single-chip processor designed for the parallel processing that can be used to accelerate a wide variety of tasks such as video rendering, gaming and machine learning.

A GPU is designed for handling specialized computations, whereas a CPU…

In this post, we are going to learn and build a python program where we are going to extract and save frames from videos using the OpenCV library.

OpenCV is one of the most commonly used libraries for computer vision tasks, such as reading and saving images, face recognition, segmentation, etc. It provides us with a list of powerful functions that can be used in image and video analysis.

Related Article


Here, we are going to load all the modules and function that we are going to use…

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 such as polyp segmentation, brain tumour segmentation, human image segmentation, and many more.

Original Paper: Road Extraction by Deep Residual U-Net

RESUNET is a fully convolutional neural network that is designed to get high performance with fewer parameters. It is an improvement over the existing UNET architecture. …

UNET is an architecture developed by Olaf Ronneberger et al. for Biomedical Image Segmentation in 2015 at the University of Freiburg, Germany. It is one of the most popularly used approaches in any semantic segmentation task today. It is a fully convolutional neural network that is designed to learn from fewer training samples. It is an improvement over the existing FCN — “Fully convolutional networks for semantic segmentation” developed by Jonathan Long et al. in (2014).

UNET — Network Architecture

UNET is a U-shaped encoder-decoder network architecture, which consists of four encoder blocks and four decoder blocks that are connected via a bridge. The…

All the technological advancements in the field of Artificial Intelligence (AI) is facilitated due to the availability large amount of dataset and the computational hardware’s like GPU’s and TPU’s. In some fields like medical imaging, the availability of the huge amount of data is not possible, as it takes a good amount of efforts to collect the data and then labelling it requires the domain expertise. To, solve this issue, we use data augmentation. In this article, we will go through the process of applying data augmentation to any semantic segmentation dataset.


  1. What is Data Augmentation?
  2. Why do we…

We are going to continue our journey on the autoencoders. In this article, we are going to build a convolutional autoencoder using the convolutional neural network (CNN) in TensorFlow 2.0.

Let us first revise, what are autoencoders?

Autoencoders are neural networks that attempt to mimic its input as closely as possible to its output. It aims to take an input, transform it into a reduced representation called code or embedding. Then, this code or embedding is transformed back into the original input. The code is also called the latent-space representation.

For more: Introduction to Autoencoders

In this article, we are…

In today’s article, we are going to discuss a neural network architecture called autoencoders. This article is aimed at Machine Learning and Deep Learning beginners who are interested in getting a brief understanding of the underlying concepts behind autoencoders. So let’s dive in and get familiar with the concept of autoencoders.

In this article, we are going to explore the following topics:

  1. What is autoencoders
  2. Architecture of autoencoders
  3. Loss used in autoencoders
  4. Types of autoencoders.
  5. Applications of autoencoders.
  6. Conclusion
  7. Sources

What are Autoencoders

Autoencoders are a type of neural network that attempts to mimic its input as closely as possible to its output…

In this tutorial, we will learn about how to perform polyp segmentation using deep learning, UNet architecture, OpenCV, and other libraries. We will use a polyp segmentation dataset to understand how semantic segmentation is applied to real-world data.

In polyp segmentation, the images with polyp are given to a trained model and it will give us a binary image or mask. This binary image consists of black and white pixels, where white denotes the polyp in image and black denotes the background.

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store