Deep Learning

0

Vanilla GAN in TensorFlow

This tutorial will teach you how to implement basic Generative Adversarial Networks (GANs) in TensorFlow using Keras API. For this purpose, we will utilize the Anime Face Dataset and try to generate realistic anime faces. What is GAN GAN stands for Generative Adversarial Network, a framework in which two neural...

0

DeepLabV3+ ResNet50 Architecture in TensorFlow using Keras

In today’s tutorial, we will be looking at the DeepLabV3+ (ResNet50) architecture implementation in TensorFlow using Keras high-level API. Within this architecture, ResNet50 would be used as the encoder, which is pre-trained on the ImageNet classification dataset. We will begin with the overall architectural understanding of the DeepLabV3+ and ResNet50....

0

Image Segmentation-based Background Removal in TensorFlow

Image segmentation is an important area of computer vision that involves dividing an image into multiple segments, each of which corresponds to a different object. Background removal is one of the crucial applications of image segmentation that involves separating foreground objects from the background. This can be useful in various...

0

What is MultiResUNET?

MultiResUNET is an architecture developed by Nabil Ibtehaz et al. for the purpose of multimodal biomedical image segmentation at the Bangladesh University of Engineering and Technology. It is an improvement over the existing UNET architecture as it outperforms U-Net on the five biomedical datasets. The high performance of MultiResUNET is...

0

Human Face Detection using Multi-task Cascaded Convolutional Networks in TensorFlow

In recent years, advances in machine learning and deep learning techniques have revolutionized the field of computer vision. With the help of these techniques, we can now detect and identify objects in real time with remarkable accuracy. One of the most popular tasks in computer vision is human face detection,...

0

[Paper Summary] Class-Aware Adversarial Transformers for Medical Image Segmentation

Transformer-based models have shown remarkable progress in the field of medical image segmentation. However, the existing methods still suffer from limitations such as loss of information and inaccurate segmentation label maps. In this article, we will discuss a new type of adversarial transformer, the Class-Aware Adversarial Transformer (CASTformer), which overcomes...

0

What is U2-Net or U-square Net

U2-Net is a simple and powerful architecture designed for the purpose of salient object detection (SOD). It is a two-level nested U-shaped architecture built using the proposed ReSidual U-blocks (RSU). The U2-Net does not use any pre-trained architecture and is trained from scratch. The architecture comes with two variants: U2-Net...

0

TensorFlow vs PyTorch

TensorFlow and PyTorch are both popular open-source frameworks for building and training machine learning models. Both frameworks have their own strengths and weaknesses, and the choice between them depends on the specific needs of the project. Introduction to TensorFlow and PyTorch TensorFlow TensorFlow, which was developed by Google, is a...

0

Implementing Linear Regression in TensorFlow

TensorFlow is a powerful library for machine learning that allows for the easy implementation of various algorithms, including linear regression. In this tutorial, we will be using TensorFlow tape gradient to implement a linear regression model and plot the loss graph and x and y on matplotlib. First, we will...