Install YOLOv5 to Detect Objects on Windows & Google Colab with PyTorch GPU Support | Part 1

Hey everyone and welcome to the YOLOv5 series!

In this series we'll learn how to train a YOLOv5 object detection model on a custom dataset from scratch. In this video (part 1), we'll cover installing YOLOv5 on Windows with GPU support, as well as try out a quick Google Colab example. I'll also talk about what Mac users may do differently.

The goal of this video is learning how to run inference, aka detecting objects in our images or videos. In the next parts of the series, we'll cover data collection, and training/debugging models with Weights & Biases ML tools. Hope you enjoy!

--

Links:

---

You can watch the whole YOLOv5 Series here:

---

Follow Ivan:

---

⏳Timestamps⏳
0:00 Intro & overview of what's in the video/series
1:06 An overview about YOLOv5 and Weights & Biases integration
1:24 Setting up YOLOv5 on Google Colab
1:58 Installing YOLOv5 on Windows
2:42 Installing Python 3.8 or later
3:24 Environmental variables
4:01 Installing PyTorch
5:00 Installing CUDA
6:03 Installing dependencies
6:23 Fixing an error installing PyCOCOTools (installing Microsoft C++ build tools)
7:32 Detecting objects from webcam feed
8:29 Detecting objects in images
8:53 Detecting objects in YouTube videos
9:37 YOLOv5 models of different sizes
10:29 YOLOv5 and Python projects
11:02 Outro

---

---

[WeightsBiases]

Thank you for watching part 1 of the YOLOv5 Series!

You can watch the whole YOLOv5 Series here:

[drummdogs]

Thank you so much for this video. I've been battling with the windows install of yolov5 for a while and you got me over the line by walking through every step!

[farhadtorabi]

thank you for this great series. explanations were great and complete

[aryashinde]

Thank you very much for this tutorial. I was easily able to follow and implement all of the steps. I'm really grateful to you

[pycad]

Thank you very much man, the video was very helpful :)

[raisaalves]

Great material. Thank you and congratulations for the teaching.

[xodpjjt]

That's literally the best tutorial I've ever seen.

[kridsadahaengphit]

thank you so much, you are expaine very easy to understand

[alonsomoran]

Thanks, great tutorial. What part of the code do I have to modify to make it detect a specific object and ignore the rest of the objects?

[faezehghafouri]

thank you so much your video is the most completed video 😍🤟💥

[boquangdong]

thank you very much about your video. the best video i seen about yolov5

[adrianogoncalves]

Great tutorial. I have one question. If I have python+cuda+pytorch already working on a Linux machine, it will work immediately (after installing all the other dependencies) or would I need something else?

[asdfds]

Hi, a quick question: how do you extract the bounding boxes to be used in another program? Can you please show that? I guess that is the core issues that most people would love to have some input on! Thanks again for the amazing work!

[Traunsurf]

Thanks a lot for the video!!
for me the "pip install -r requirements.txt" command didn't work. instead i had to use "python -m pip install -r requirements.txt"

[kmhooibg]

Hi, this video is HELPFUL and RATED 5/5 by me. But I wonder can I use custom dataset instead of the pre-set dataset as shown?

[lightning_best]

Hello. I was inspired by your videos and decided to study yolov5. But I ran into one problem: there is a person box, 'person' is written above the box, but this word is filled with a red background . I want to make sure there is no red padding behind the text. Could you suggest what needs to be changed in the code to fix this problem. I will be very grateful to you
P.S. I opened the plots.py file, but there I could only adjust the text size and box

[ozcankosar]

Can I use models I trained on windows for ROS on ubuntu?

[OrionEx]

I tried the front face webcam streaming but it only open the main (back) camera from my laptop. Do you know where to change on the code? Thanks

[SouthSeaTrader]

I was able to get this running on my PC. now i would like to get this to deploy to my android phone. Is there a good tutorial for doing this? Thanks!

[haitammanar]

hi so i'm using my phone as the webcam camera, what source should I type for the python detect.py --source *