Object detection Using Detection Transformer (Detr) for Bone fraction dataset

Опубликовано: 27 Октябрь 2024
на канале: Eran Feit
408
10

In this comprehensive tutorial, we walk you through building an advanced Object Detection system using the DETR (DEtection TRansformer) model. We'll cover everything from data preparation to model training and inference.

Here's what you'll learn:

We use Python with libraries including PyTorch, Transformers, PyTorch Lightning, and Supervision.

The code includes:

Custom dataset handling with torchvision
DETR model implementation with PyTorch Lightning
Training pipeline setup
Inference on new images
Visualization of detection results

Code for the tutorial : https://ko-fi.com/s/f48f15ccd7

You can find more computer vision tutorials in my blog page : https://eranfeit.net/blog/

You can find more projects and tutorials in this playlist :    • Best Object Detection models  


~~~~~~~~~~~~~~~ recommended courses and books ~~~~~~~~~~~~~~~
A perfect course for learning modern Computer Vision with deep dive in TensorFlow , Keras and Pytorch . You can find it here : http://bit.ly/3HeDy1V
I also recommend this book, https://amzn.to/44GnlLW : "Make Your Own Neural Network - An In-depth Visual Introduction For Beginners ".
~~~~~~~~~~~~~~~ CONNECT ~~~~~~~~~~~~~~~
☕ Buy me a coffee - https://ko-fi.com/eranfeit
🖥️ Email : [email protected]
🌐 https://eranfeit.net
🤝 Fiverr : https://www.fiverr.com/s/mB3Pbb
🐦 Twitter -   / eran_feit  
📸 Instagram -   / eran_feit  
▶️ Subscribe -    / @eranfeit  
🐙 Facebook -   / 3080601358933585  
📝 Medium -   / feitgemel  
~~~~~~~~~~~~~~ SUPPORT ME 🙏~~~~~~~~~~~~~~
🅿 Patreon -   / eranfeit  
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#EranFeit #objectdetection #transformers
~~~~~~~~~~~~~~ Chapters ~~~~~~~~~~~~~
00:00 Introduction
00:21 Installation
02:43 Prepare the data
18:47 Build the model
36:12 Train the model
39:02 Test the model
~~~~~~~~~~~~~~ Credits ~~~~~~~~~~~~~
Music by Vincent Rubinetti
Download the music on Bandcamp: https://vincerubinetti.bandcamp.com/a...
Stream the music on Spotify: https://open.spotify.com/album/1dVyjw...