YOLOE: Next Gen Computer Vision - Zero Training Required!
Core Electronics 21:36
135,593 views · 5,234 likes Watch on YouTube ↗
🔗 *The full guide* : _https://core-electronics.com.au/guides/raspberry-pi/custom-object-detection-models-without-training-yoloe-and-raspberry-pi/_
In this guide, we will be looking at *YOLOE* on the *Pi 5* and how to use it to create *custom object detection* models without the need for *training.* YOLOE is a new and exciting vision model that runs off *visual concepts*, allowing it to take *text and image prompts* to detect objects it has never seen before.
🔧🔨🧰 Hardware featured in this guide:
*Raspberry Pi 5 4GB:*
_https://core-electronics.com.au/catalog/product/view/sku/CE09785_
*Camera Module V3:*
_https://core-electronics.com.au/catalog/product/view/sku/CE09425_
*Raspberry Pi:*
_https://core-electronics.com.au/raspberry-pi/boards.html#category_1392_
💡❓ If you have any questions about this content or want to share a project you're working on head over to our *maker forum:* _http://coreelec.io/forum_
0:00 Why YOLOE is so Special
1:30 How YOLOE Works
4:23 Running Prompt-Free Mode on the Pi
7:37 Converting to ONNX and Changing Resolution
11:01 Text-Prompt Mode
14:19 Changing Model Size
15:49 How to Choose the Right Model Size, Resolution and Format
16:35 Image-Prompt Mode
20:10 Demo Codes: Locating and Counting Objects
🌏🦘 *Core Electronics* is located in the heart of Newcastle, Australia. We're powered by makers, for makers. Drop by if you are looking for:
• *Raspberry Pi* _https://core-electronics.com.au/raspberry-pi.html_
• *Arduino* _https://core-electronics.com.au/arduino.html_
• *Sparkfun* _https://core-electronics.com.au/brands/sparkfun-australia_
• *Adafruit* _https://core-electronics.com.au/brands/adafruit-australia_
• *Pololu* _https://core-electronics.com.au/brands/pololu-australia_
• *DFRobot* _https://core-electronics.com.au/brands/dfrobot-australia_
The following trademarks are owned by *Core Electronics Pty Ltd:*
"Core Electronics" and the Core Electronics logo
"Makerverse" and the Makerverse logo
"PiicoDev" and the PiicoDev logo
"GlowBit" and the GlowBit logo
In this guide, we will be looking at *YOLOE* on the *Pi 5* and how to use it to create *custom object detection* models without the need for *training.* YOLOE is a new and exciting vision model that runs off *visual concepts*, allowing it to take *text and image prompts* to detect objects it has never seen before.
🔧🔨🧰 Hardware featured in this guide:
*Raspberry Pi 5 4GB:*
_https://core-electronics.com.au/catalog/product/view/sku/CE09785_
*Camera Module V3:*
_https://core-electronics.com.au/catalog/product/view/sku/CE09425_
*Raspberry Pi:*
_https://core-electronics.com.au/raspberry-pi/boards.html#category_1392_
💡❓ If you have any questions about this content or want to share a project you're working on head over to our *maker forum:* _http://coreelec.io/forum_
0:00 Why YOLOE is so Special
1:30 How YOLOE Works
4:23 Running Prompt-Free Mode on the Pi
7:37 Converting to ONNX and Changing Resolution
11:01 Text-Prompt Mode
14:19 Changing Model Size
15:49 How to Choose the Right Model Size, Resolution and Format
16:35 Image-Prompt Mode
20:10 Demo Codes: Locating and Counting Objects
🌏🦘 *Core Electronics* is located in the heart of Newcastle, Australia. We're powered by makers, for makers. Drop by if you are looking for:
• *Raspberry Pi* _https://core-electronics.com.au/raspberry-pi.html_
• *Arduino* _https://core-electronics.com.au/arduino.html_
• *Sparkfun* _https://core-electronics.com.au/brands/sparkfun-australia_
• *Adafruit* _https://core-electronics.com.au/brands/adafruit-australia_
• *Pololu* _https://core-electronics.com.au/brands/pololu-australia_
• *DFRobot* _https://core-electronics.com.au/brands/dfrobot-australia_
The following trademarks are owned by *Core Electronics Pty Ltd:*
"Core Electronics" and the Core Electronics logo
"Makerverse" and the Makerverse logo
"PiicoDev" and the PiicoDev logo
"GlowBit" and the GlowBit logo
Category (YouTube): Education
Playback is via YouTube's official embedded player. Data from YouTube; Exumo is not affiliated with YouTube.