Interview Prep
Career
GenAI
Prompt Engg
ChatGPT
LLM
Langchain
RAG
AI Agents
Machine Learning
Deep Learning
GenAI Tools
LLMOps
Python
NLP
SQL
AIML Projects

Reading list

Deploy an Image Classification Model Using Flask
Introduction to Computer Vision
Reading and Stacking Images Understanding Colorspaces Image Processing Edge Detection Blur Detection Image Operations HOG features SIFT features Camera Calibration Interesting Applications of OpenCV
Why Do We Need CNN? How Does Filters Work in CNN? Parameter Sharing and Local Connectivity in CNN Understanding CNN Architecture What is Pooling in CNN? Math Behind Convolutional Neural Networks Image Classification Tutorial using CNN Introduction to Separable Convolutions
Introduction to Transfer Learning
CNN Visualization
LeNet AlexNet VGG16 Implement VGG Dataloaders using Pytorch Implementing VGG16 using Dataloaders
Understanding Inception Modules
Understanding Residual Blocks Building Your Own Residual Block from Scratch Understand ResNet 34 Build ResNet34 from Scratch With Python! Different Versions of ResNet
Understanding the Architecture of DenseNet
Implement Crowd Counting using CSRNet
Introduction to Object Detection Bounding Box Evaluation: (Intersection over union) IOU Calculating IOU
Why do we need Region Based Convolulional Neural Network? Fast R-CNN and Faster R-CNN Building Social Distancting Tool using Faster R-CNN
DETR
Introduction to Face Detection Why is Face Alignment Important for Face Recognition? Implementing Face Detection
Introduction to Object Tracking Object Tracking Applications
Comprehensive Guide on Pose Estimation Implement Human Pose Estimation
Introduction to Image Segmentation Different Types of Image Segmentation Implementing Background removal Image Segmentation Algorithms
Unet DeepLabv3 Mask R-CNN Architecture
Build Your Own Video Classification Model
Introduction to Image Generation What are Generative models? Understanding GANs Implementing Texture Generation using GANs Better GAN Architectures
Few Shot Learning

Playing with YOLO v1 on Google Colab

G
Guest Blog Last Updated : 04 Aug, 2020
6 min read

Object Detection is a computer vision task in which you build ML models to quickly detect various objects in images, and predict a class for them

For example, if I upload a picture of my pet dog to the model, it should output the probability that it detected a dog in the image, and a good model would show something along the lines of 99% Object Detection is a rapidly evolving field with research teams and scientists publishing thousands of interesting and intuitive research papers per year – each new paper improving upon its predecessor with increased accuracy and faster detection times.

YOLO v1

But hey, we gotta start somewhere, right? In this article, I’ll show you how you can quickly start detecting objects in images of your own, using the YOLO v1 architecture on the Google Colab platform, in no time.

Did I mention you have free access to fast GPU computing power? Okay so let’s talk about the YOLO v1 model.

Note: Here is the notebook used in this article.

In 2014, Joseph Redmon and his team brought out the YOLO model for object detection in front of the world. Moreover, YOLO was designed to be a unified architecture in that. Unlike its predecessors, it would perform all the operations required in object detection (extracting features using CNNs, predicting bounding boxes around objects, scoring those bounding boxes using SVMs, etc.) using a single CNN model.

In addition, it would do this in real-time too. Models before YOLO didn’t have a high real-time detection speed. For example, Fast R-CNN, which claimed to be an improvement over the famous R-CNN model, only had a meager speed of 0.5 FPS (frames per second)

YOLO v1 not only has a speed of 45 FPS (90x faster than Fast R-CNN), it improves upon Fast R-CNN by making much less background false positive errors

Comparison of YOLO v1 and Fast R-CNN on various error types (credits)

Comparison of YOLO v1 and Fast R-CNN on various error types (credits)

The following is the architecture of the YOLO v1 model-

YOLO v1 Architecture                                                                                                         (credits)

💡 The model has 24 convolutional layers followed by 2 fully connected layers.

It takes in an input image of dimensions 224 x 224 and resizes it to 448 x 448 for the detection task. The output is a 7 x 7 x 30 tensor containing predictions which the model makes on the input image

Also, introduced in the same paper, Fast YOLO boasts of a blazingly quick real-time performance of 155 FPS. Even faster and more accurate versions of YOLO exist — YOLO 9000, YOLO v3, and the very recent YOLO v4

We’ll talk about the performance statistics of YOLO and its variants in future posts, let’s now get our hands dirty with YOLO v1 using Colab!

 

Playing with YOLO on Colab

The following steps illustrate using if YOLO-

1. Installing Darknet

Firstly, let’s set our Colab runtime to use a GPU. You can do this by clicking on “Runtime”, then “Change Runtime type”, and choosing a GPU runtime

YOLO v1 Using a GPU runtime

Darknet is a library created by Joseph Redmon which eases the process of implementing YOLO and other object detection models online, or on a computer system.

Further, on Colab, we install Darknet by first cloning the Darknet repository on Git, and changing our working directory to ‘darknet’ as follows

!git clone https://github.com/pjreddie/darknet.gitimport os
os.chdir("/content/darknet")

If the above steps work perfectly, you can see the contents of the folder by typing…

!ls

afterward, you should see the following-

cfg	  include	LICENSE.gen   LICENSE.mit  python     src
data	  LICENSE	LICENSE.gpl   LICENSE.v1   README.md
examples  LICENSE.fuck	LICENSE.meta  Makefile	   scripts

To install Darknet for our session, we fetch the Makefile and run the following

!sed -i 's/GPU=0/GPU=1/g' Makefile
!make

If you followed correctly till here, you should see something like this

YOLO v1 - Installing Darknet

2. Downloading YOLOv1 model weights

Then, we’ll download the YOLO v1 pre-trained model weights. We do this as follows —

NOTE: Depending on your internet connection, this should take a while, as it’s a 753 MB file. It took me around 70 minutes :/

!wget http://pjreddie.com/media/files/yolov1/yolov1.weights

YOLO V1 - Installing YOLO weights

3. Playing with images

The /content/darknet/data directory will have lots of images for you to play with. Let’s try dog.jpg first, this is what it looks like

Yolo v1 - dog.jpg

Let’s try and detect the objects in this image, and see what probabilities our model outputs

!./darknet yolo test /content/darknet/cfg/yolov1.cfg /content/yolov1.weights /content/darknet/data/dog.jpg

Consequently, you’ll see an output like this

dog.jpg Prediction Probabilities

As you can see, our model detected a dog, a car, and a bicycle from the image with confidence scores of 26%, 74%, and 39% respectively.

The model saves the predictions to “predictions.jpg”, which you can view as follows

import cv2
import matplotlib.pyplot as plt
import os.pathfig,ax = plt.subplots()
ax.tick_params(labelbottom="off",bottom="off")
ax.tick_params(labelleft="off",left="off")
ax.set_xticklabels([])
ax.axis('off')file = '/content/darknet/predictions.jpg'if os.path.exists(file):
  img = cv2.imread(file)
  show_img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
  plt.imshow(show_img)

dog.jpg Detected Objects

Awesome! You just made your first image detection using the YOLO v1 model. Let’s play some more.

We’ll try kite.jpg next

kite.jpg

Let’s see what our model does on this one

!./darknet yolo test /content/darknet/cfg/yolov1.cfg /content/yolov1.weights /content/darknet/data/kite.jpgimport cv2
import matplotlib.pyplot as plt
import os.pathfig,ax = plt.subplots()ax.tick_params(labelbottom="off",bottom="off")
ax.tick_params(labelleft="off",left="off")
ax.set_xticklabels([])
ax.axis('off')file = '/content/darknet/predictions.jpg'if os.path.exists(file):
  img = cv2.imread(file)
  show_img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
  plt.imshow(show_img)

kite.jpg Detected Objects

While it correctly detected 2 persons enjoying themselves on the beach, it mistook a glider for a bird.

Then we have the following person.jpg-

Image for post

Abracadabra

!./darknet yolo test /content/darknet/cfg/yolov1-tiny.cfg /content/darknet/tiny-yolov1.weights /content/darknet/data/person.jpg

Image for post

Dog, correct.
Person, correct.
Horse…and sheep? No model, it’s just Horse

Fast YOLO

In addition, along with YOLO v1, the authors also built a Fast YOLO model, which is designed to run at 155 FPS (more than 3 times faster than YOLO).

It also weighs considerably less — just 103 MB, compared to the 753 MB YOLO used.

This is partly because Fast YOLO has just 9 convolutional layers, instead of the 24 in YOLO, and those 9 layers use a lesser number of features.

To make detections using Fast YOLO, let’s download its weights

!wget http://pjreddie.com/media/files/yolov1/tiny-yolov1.weights

Let’s see what it does on person.jpg, whose objects YOLO didn’t quite correctly detect.

!./darknet yolo test /content/darknet/cfg/yolov1-tiny.cfg /content/darknet/tiny-yolov1.weights /content/darknet/data/person.jpgimport cv2
import matplotlib.pyplot as plt
import os.pathfig,ax = plt.subplots()ax.tick_params(labelbottom="off",bottom="off")
ax.tick_params(labelleft="off",left="off")
ax.set_xticklabels([])
ax.axis('off')file = '/content/darknet/predictions.jpg'if os.path.exists(file):
  img = cv2.imread(file)
  show_img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
  plt.imshow(show_img)

person.jpg Detected Objects by Fast YOLO

Wow. Fast YOLO did what YOLO couldn’t, and correctly detected the 3 objects along with their classes in the image.

Additional Example – Upload any random image

Let’s upload a random image off the Internet and see what YOLO does on it. To upload any image to the Colab runtime, run the following code block

os.chdir("/content")from google.colab import files
uploaded = files.upload()

 We use the following famous Oscar selfie-

Image for post (credits)

And finally, when running on this image, we get the following output

os.chdir("/content/darknet/")!./darknet yolo test /content/darknet/cfg/yolov1-tiny.cfg /content/darknet/tiny-yolov1.weights /content/selfie.jpg

YOLO v1 - selfie.jpg Prediction Probabilities

So we see, our model has identified 9 people from this image. Let’s view the detections

YOLO v1 - selfie.jpg Detected Objects

Thank You for reading this article. As a bonus, you can try running the above codes on Colab yourself, using this notebook. Thus, we saw how we can detect objects in our images, using the state-of-the-art YOLO model, on the cloud using Google Colab.

In conclusion, I hope you learned useful stuff from this article. For more articles (coming soon), follow me on LinkedIn and Medium!

References

  1. YOLO v1 paper
  2. YOLO 9000 paper
  3. YOLO v3 paper
  4. YOLO v4 paper
  5. https://pjreddie.com/darknet/yolov1/
  6. Darknet

 

About the Author

Author

Anamitra Musib – CS engineer

Prospective MS Data Science student. Loves Deep Learning, Computer Vision, and all that jazz

G
Guest Blog

Free Courses

Generative AI 4.7

Generative AI - A Way of Life

Explore Generative AI for beginners: create text and images, use top AI tools, learn practical skills, and ethics.
Large Language Models 4.5

Getting Started with Large Language Models

Master Large Language Models (LLMs) with this course, offering clear guidance in NLP and model training made simple.
Prompt Engineering 4.6

Building LLM Applications using Prompt Engineering

This free course guides you on building LLM apps, mastering prompt engineering, and developing chatbots with enterprise data.
LlamaIndex 4.8

Improving Real World RAG Systems: Key Challenges & Practical Solutions

Explore practical solutions, advanced retrieval strategies, and agentic RAG systems to improve context, relevance, and accuracy in AI-driven applications.
RAG systems using LlamaIndex 4.7

Microsoft Excel: Formulas & Functions

Master MS Excel for data analysis with key formulas, functions, and LookUp tools in this comprehensive course.

Recommended Articles

Responses From Readers

Clear

Write for us

Write, captivate, and earn accolades and rewards for your work
  • Reach a Global Audience
  • Get Expert Feedback
  • Build Your Brand & Audience
  • Cash In on Your Knowledge
  • Join a Thriving Community
  • Level Up Your Data Science Game
imag

We use cookies essential for this site to function well. Please click to help us improve its usefulness with additional cookies. Learn about our use of cookies in our Privacy Policy & Cookies Policy.

Show details