deep learning Archives - Idiot Developer

Blog TensorFlow

GradCAM with TensorFlow: Interpreting Neural Networks with Class Activation Maps

Nikhil Tomar26th February 2025

Deep learning models, particularly convolutional neural networks (CNNs), are widely used for image classification, object detection, and various computer vision tasks. However, these models are often referred to as "black...

Computer Vision Deep Learning

[Paper Summary] EMCAD: Efficient Multi-scale Convolutional Attention Decoding for Medical Image Segmentation

Nikhil Tomar14th September 202414th September 2024

This post will analyze the research paper "EMCAD: Efficient Multi-scale Convolutional Attention Decoding for Medical Image Segmentation." We will discuss the problems with existing medical image segmentation methods and how...

Computer Vision Deep Learning

What is Image Captioning?

Nikhil Tomar29th August 2024

In recent years, the field of artificial intelligence (AI) has seen remarkable advancements, particularly in how machines can understand and describe visual content. One of the fascinating developments in this...

Deep Learning PyTorch TensorFlow

What is Dice Coefficient?

Nikhil Tomar28th August 202428th August 2024

This article will explore the Dice Coefficient (DSC), a metric commonly used to evaluate the similarity between two sets. We'll delve into its definition, provide implementations in NumPy, TensorFlow, and...

Deep Learning

Generative and Discriminative Models in Machine Learning

Nikhil Tomar17th August 202414th September 2024

Machine learning is a fascinating field that teaches computers to make decisions or predictions based on data. Two main types of models are commonly used: generative models and discriminative models....

Computer Vision Deep Learning TensorFlow

ResUNet++ Implementation in TensorFlow

Nikhil Tomar20th April 202420th April 2024

In this article, we will study the ResUNet++ architecture and implement it using the TensorFlow framework. ResUNet++ is a medical image segmentation architecture built upon the ResUNet architecture. It takes...

Computer Vision Deep Learning TensorFlow

UNet 3+ Implementation in TensorFlow

Nikhil Tomar11th April 202414th September 2024

In this article, we will implement the UNet 3+ architecture using TensorFlow. UNet 3+ extends the classic UNet and UNet++ architecture incorporating full skip connections. We will delve into each block...

Computer Vision Deep Learning

Skip Connection in Image Segmentation: UNet, UNet++ and UNet 3+

Nikhil Tomar7th February 2024

Image segmentation, a fundamental task in computer vision, involves partitioning an image into multiple segments to simplify its representation. One of the critical advancements in image segmentation architectures is the...

Computer Vision Deep Learning

[Paper Summary] UNet 3+: A Full-Scale Connected UNET For Medical Image Segmentation

Nikhil Tomar5th February 20245th February 2024

In medical image analysis, accurately identifying and outlining organs is vital for clinical applications such as diagnosis and treatment planning. The UNet architecture, a widely favoured choice for these tasks,...

Computer Vision Deep Learning TensorFlow

ResUNET: A TensorFlow Implementation for Semantic Segmentation

Nikhil Tomar1st February 20241st February 2024

In computer vision and medical image analysis, semantic segmentation plays a pivotal role in understanding and interpreting visual data. One of the prominent architectures in this domain is ResUNet, a...