UNET Transformers: UNETR Implementation for 2D Segmentation in TensorFlow

In this video, I will show you how to implement UNETR for a 2D segmentation model in TensorFlow.

By the end of this video, you will be able to:
1. Understand the architecture of UNETR
2. Implement UNETR in TensorFlow
3. Use UNETR to segment images
If you are interested in learning more about UNETR or 2D segmentation, then I encourage you to watch this video.

Code: https://github.com/nikhilroxtomar/Sem...

Timeline:
00:00 - Introduction
00:25 - What is UNETR?
01:46 - What is Vision Transformer (ViT)
03:04 - Image to Patches processing
05:55 - Importing TensorFlow
06:28 - Implementation of Multilayer Perception (MLP)
08:02 - Hyperparameter configuration for UNETR
09:33 - Implementation of Transformer Encoder
13:17 - Implementation of Convolutional Block
14:54 - Implementation of Deconvolutional Block
16:10 - Begin with the implementation of UNETR
16:20 - Input layer
18:05 - Patches
24:33 - Transformer Encoder
26:24 - CNN Decoder
41:17 - Output layer
41:41 - UNETR Model
43:02 - How to use it to a multiclass segmentation task
43:29 - Ending (Thank You)

Vision Transformer (ViT) Implementation in TensorFlow:    • Vision Transformer (ViT) Implementati...  

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

Follow Me:
BLOG: https://idiotdeveloper.com
TELEGRAM: https://t.me/idiotdeveloper
FACEBOOK:   / idiotdeveloper  
TWITTER:   / nikhilroxtomar  
INSTAGRAM: https://instagram/nikhilroxtomar