Polyp Segmentation using UNet 3+ in TensorFlow Keras

📺 In this video, we'll use UNet 3+ for Polyp Segmentation in the TensorFlow framework using Keras API.

UNet 3+ is a U-shape encoder-decoder architecture built upon the foundation of its predecessors, i.e., UNet and UNet++. It aims to capture both fine-grained details and coarse-grained semantics from full scales. The paper highlights the re-design of inter and intra-connections between the encoder and the decoder, providing a more comprehensive understanding of organ structures.

Research Paper: https://arxiv.org/ftp/arxiv/papers/20...

🔧 Code: https://github.com/nikhilroxtomar/Pol...

🕒 Timeline:
00:00 - Introduction
00:10 - What is Polyp Segmentation
00:44 - What is UNet 3+
01:48 - Kvasir-SEG: Polyp Segmentation dataset
02:58 - Project Structure
03:31 - Import Libraries & Functions
04:40 - Defining the Height & Width for the dataset
05:01 - Function to create a folder
05:17 - Function to load and split the dataset
08:30 - Dataset Pipeline Functions
12:51 - The Main Function
13:39 - Hyperparameters
14:01 - Load the dataset
14:37 - Load the UNet 3+ Model
15:31 - Defining the Callbacks
17:03 - Training the Model
17:50 - Testing the Model

💡Support:
-    / @idiotdeveloper  
- https://www.buymeacoffee.com/nikhilro...

🌐 Connect with Me:
Blog: idiotdeveloper.com
Telegram: t.me/idiotdeveloper
Facebook: facebook.com/idiotdeveloper
Twitter: twitter.com/nikhilroxtomar
Instagram: instagram/nikhilroxtomar