Tensorflow 2 YOLOv3-Tiny object detection implementation

In this tutorial, you will learn how to utilize YOLOv3-Tiny the same as we did for YOLOv3 for near real-time object detection.

The YOLO object detector is often cited as being one of the fastest deep learning-based object detectors, achieving a higher FPS rate than computationally expensive two-stage detectors (ex. Faster R-CNN) and some single-stage detectors (ex. RetinaNet and some, but not all, variations of SSDs).

However, even with all that speed, YOLOv3 is still not fast enough to run on some specific tasks or embedded devices such as the Raspberry Pi.

To help make YOLOv3 even faster, Redmon et al. (the creators of YOLO), defined a variation of the YOLO architecture called YOLOv3-Tiny.

✅ Support My Channel Through Patreon:

✅ One-Time Contribution Through PayPal:

[barathm]

Good work.
how tune the hyper parameters for the tiny yolo.

[sehbinpapark]

Thanks for your informative tutorial of Yolo v3!! Do you have any plan to introduce the latest version of Yolo, version 4 ?

[mangaenfrancais]

Thanks, could you do please a video of Faster R CNN with Tensorflow 2

[rishi]

Hello Sir, when i am executing the python file "detection_custom.py", i am getting the following error: ERROR: Could not find a version that satisfies the requirement cv2-python (from versions: none)
ERROR: No matching distribution found for cv2-python

Can you please help me to rectify the error

[tommygun]

I subscribed because i am very excited to see your Aimbot using YOLO :P running on more frames :) thats a very cool project - something i "dream" of haha - if you would'nt make it - i probably would try - another option could be to buy a NVIDIA Xavier NX DevBoard - but i don't know if it can run CS:GO

[Ethan_here]

The accent is very irritating. Accent is so thick can't understand a single word.