Real-Time Object Detection Using YOLOv8: Step-by-Step Walkthrough

July 31, 2023

This article discusses the advancements in the field of object detection by explaining the latest breakthroughs that happened with the evolution of YOLO. The article covers YOLO architecture and the latest models such as YOLOv8 and YOLONAS, comparing and contrasting the advantages and improvements these techniques have over other approaches.

As AI takes over the software industry and many of its domains, one of the biggest advancements in the field of computer vision has been the advent of YOLO. It has made it possible for every image or video that ever existed to be processed by machines – by the power of machine learning – and offer valuable insights into what the content of the image is. Many softwares and organisations now use YOLO in their AI products.

In this article, we provide a step-by-step guide to understand the technology behind YOLO.

Object Detection in Computer Vision

In the field of computer vision where you can process any image, video – in the form of a live video or recordings, using AI to extract insights from this data – has become very crucial for a lot of applications. One such task defined to extract objects from a given image is called Object Detection. Given an input image, an object detection task will detect the area where an object lies in the image and classify it into a known label.

Traditional approaches used image segmentation and other techniques that often used the understanding of the pixel characteristics of an image. Modern techniques use the power of neural networks to understand the image and the subjects in it. CNNs (Convolutional Neural Networks) are a common neural network technique used in modern-day object detection systems.

Since a video can also be analysed with multiple frames that are images, Object Detection has  widespread application in image and video analysis for self-driving cars, traffic monitoring, surveillance, augmented reality, and much more. 

What Is YOLO? How Does It work?

YOLO is an algorithm and is an acronym for You Only Look Once. With one look into an image or a video, it can figure out the objects in the input. The foundational principles of YOLO rely on CNNs – by using an FCNN (Fully Convolutional Neural Network) and passing the image through it to perform the predictions.

YOLO outperformed many other algorithms for the object detection task. While other algorithms require multiple scanning procedures, the single scan by YOLO proves to be faster, which makes it highly efficient for real-time image processing. Hence it is popular among products that aim to have state-of-the-art image processing capabilities under their hood. 

The working of YOLO can be described with the following steps:

  • A neural network model divides the image into regions.
  • The model looks at each region and assigns scores (i.e., probabilities) and predict bounding boxes.
  • The regions with higher scores are considered to have a detection, and the rest are discarded.
  • The score and bounding box belongs to a class, which we now have as the detected object.

How to Use YOLOv8 on E2E Networks

In this section, we can test out how YOLO performs by using some pre-trained weights from the neural network. The cloud platform of our choice will be E2E Networks. The pre-trained weights capture the knowledge gained by the neural network during training and this can be reused in carrying out our detection tasks.

For implementing YOLO, we have to install Ultralytics. Ultralytics has an open-source framework which will help our object detection tasks with YOLO smoother. The Ultralytics project is continuously maintained, and includes releases that contain the latest versions of YOLO. 
Excited to test YOLO out? Here are the steps.

Step 1 - Launching E2E Node

  1. Create an Ubuntu 22.04 GPU node on E2E
  1. Select a 40GB Machine and hit Create.
  1. Check on Enable Backup and hit Create. 
  1. The node will now be created with the following specifications:
  1. Login to the E2E server using ssh via terminal:

ssh username@IP_address

Step 2 - Installing Ultralytics

Make sure your system has Python and Pip installed.

We can install Ultralytics via Pip.

pip install ultralytics

In case you want the most bleeding edge updates to Ultralytics, you can clone the repo using Git and install from source like this:

git clone
cd ultralytics
python install

Step 3 - Choosing the Pre-trained Models

You could explore any of the pre-trained models by exploring the models page and choosing the model you need for carrying out the experiments. For our experiments, we will be using one of the latest models, the YOLOv8x.

Here is a sample image I used. 

Source: Wikipedia

Step 4 - Testing the YOLO Algorithm with Custom Input

Now run the command like this:

yolo predict source='/path_to_image/image.jpg

Replace the /path_to_image/ directory path with your custom directory path. Note that you can mention the name pre-trained models – and the command will take care of downloading the models for you. In case you have a custom model that you would like to use for inference, mention the model path instead.

You will see an output like this:

Downloading to ''...
100% 131M/131M [00:02 00:00, 56.2MB/s]
Ultralytics YOLOv8.0.145 🚀 Python-3.10.6 torch-2.0.1+cu118 CPU (Intel Xeon 2.20GHz)
YOLOv8x summary (fused): 268 layers, 68200608 parameters, 0 gradients

image 1/1 /content/bear.jpg: 448x640 1 bear, 3318.5ms
Speed: 5.3ms preprocess, 3318.5ms inference, 2.1ms postprocess per image at shape (1, 3, 448, 640)
Results saved to runs/detect/predict4

The above inference has correctly detected the one bear in the image.

YOLO can predict multiple objects in an image. Let’s try another image like this:

Source: Author

Now we can see the output like this:

Ultralytics YOLOv8.0.145 🚀 Python-3.10.6 torch-2.0.1+cu118 CPU (Intel Xeon 2.20GHz)
YOLOv8x summary (fused): 268 layers, 68200608 parameters, 0 gradients

image 1/1 /content/image.jpg: 640x480 1 bench, 1 cat, 4 handbags, 3570.2ms
Speed: 5.9ms preprocess, 3570.2ms inference, 6.3ms postprocess per image at shape (1, 3, 640, 480)
Results saved to runs/detect/predict5

Training a YOLO Model with Your Custom Data

An Object Detection task can be done for any label that you want if you have the right kind of data. Once the images are collected, the data needs to be annotated with the bounding boxes and the preferred labels before training.

If you want to train your own model from scratch, there are popular datasets available for a wide variety of image datasets for object detection. One of the most used datasets for the task is the COCO (Common Objects in Context) dataset. Let’s take a look at how to train a COCO dataset with the YOLO architecture.

Coco Dataset

The coco dataset comprises hundreds of thousands of images containing information that could be helpful in training and validating many image recognition tasks like object detection, segmentation and captioning. There are around 80 categories and subcategories to perform object classification. This dataset is also used in evaluating YOLO algorithms and their accuracy.

Dataset Configuration

We will use a YAML (Yet Another Markup Language) file to configure details about the dataset. In the Coco.yaml file, we can configure details such as:

  1. Text files for training and validation and test files that contain information about the respective image paths.
  2. Image classes and their labels.
  3. Optional download script to fetch the dataset from the source.

# Ultralytics YOLO 🚀, AGPL-3.0 license
# COCO 2017 dataset by Microsoft
# Example usage: yolo train data=coco.yaml
# parent
# ├── ultralytics
# └── datasets
#     └── coco  ← downloads here (20.1 GB)

# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: ../datasets/coco  # dataset root dir
train: train2017.txt  # train images (relative to 'path') 118287 images
val: val2017.txt  # val images (relative to 'path') 5000 images
test: test-dev2017.txt  # 20288 of 40670 images, submit to

# Classes
  0: person
  1: bicycle
  2: car
  3: motorcycle
  4: airplane
  5: bus
  6: train
  7: truck
  8: boat
  9: traffic light
  10: fire hydrant
  11: stop sign
  12: parking meter
  13: bench
  14: bird
  15: cat
  16: dog
  17: horse
  18: sheep
  19: cow
  20: elephant
  21: bear
  22: zebra
  23: giraffe
  24: backpack
  25: umbrella
  26: handbag
  27: tie
  28: suitcase
  29: frisbee
  30: skis
  31: snowboard
  32: sports ball
  33: kite
  34: baseball bat
  35: baseball glove
  36: skateboard
  37: surfboard
  38: tennis racket
  39: bottle
  40: wine glass
  41: cup
  42: fork
  43: knife
  44: spoon
  45: bowl
  46: banana
  47: apple
  48: sandwich
  49: orange
  50: broccoli
  51: carrot
  52: hot dog
  53: pizza
  54: donut
  55: cake
  56: chair
  57: couch
  58: potted plant
  59: bed
  60: dining table
  61: toilet
  62: tv
  63: laptop
  64: mouse
  65: remote
  66: keyboard
  67: cell phone
  68: microwave
  69: oven
  70: toaster
  71: sink
  72: refrigerator
  73: book
  74: clock
  75: vase
  76: scissors
  77: teddy bear
  78: hair drier
  79: toothbrush

# Download script/URL (optional)
download: |
  from ultralytics.utils.downloads import download
  from pathlib import Path

  # Download labels
  segments = True  # segment or box labels
  dir = Path(yaml['path'])  # dataset root dir
  url = ''
  urls = [url + ('' if segments else '')]  # labels
  download(urls, dir=dir.parent)
  # Download data
  urls = ['',  # 19G, 118k images
          '',  # 1G, 5k images
          '']  # 7G, 41k images (optional)
  download(urls, dir=dir / 'images', threads=3)

Training the Model

After setting up the configuration files, you can train the model with the help of the command given below:

yolo train data=coco8.yaml epochs=3 imgsz=640

You can also specify the hyperparameters such as learning rate, epochs, image size, etc. from the Ultralytics CLI for YOLO. For more information, refer to the CLI docs. 

YOLO Nas: Latest Breakthrough in the Object Detection Industry

So far we have had several releases of YOLO, where each release has been outperforming the previous ones in the evaluation metrics. However, with YOLO Nas, there has been a leap in the speed and memory efficiency as well. This model is built from a neural architecture search engine called AutoNac. 

The major advantage that comes from using YOLO Nas is the ability to perform quantization with maximum precision, which was a challenge for much of the previous YOLO releases. Quantization is the process to reduce the precision of the weights and biases. This will make the model smaller in size, but also makes it faster and more power-efficient.

The Ultralytics framework introduced YOLO Nas in their releases. Here is an example of how to use YOLO Nas. Keep in mind that this model is still new and under lots of development and testing, so it might not be ideal to use it in production right away. 

First, download the pre-trained weights.

And run the below code.

from ultralytics import NAS

model = NAS('yolo_nas_s')
results = model.predict('path/to/image.jpg'')


YOLO achieves impressive accuracy and speed with its ability to scan an image just once and leveraging top deep learning methodologies. Using state-of-the-art frameworks like Ultralytics and Darknet that helps train YOLO using neural networks, the task of object detection is made easier. Numerous applications such as autonomous driving, surveillance, and so on have used YOLO for its popularity and ease of creating solutions based on it.

Latest Blogs
This is a decorative image for: A Complete Guide To Customer Acquisition For Startups
October 18, 2022

A Complete Guide To Customer Acquisition For Startups

Any business is enlivened by its customers. Therefore, a strategy to constantly bring in new clients is an ongoing requirement. In this regard, having a proper customer acquisition strategy can be of great importance.

So, if you are just starting your business, or planning to expand it, read on to learn more about this concept.

The problem with customer acquisition

As an organization, when working in a diverse and competitive market like India, you need to have a well-defined customer acquisition strategy to attain success. However, this is where most startups struggle. Now, you may have a great product or service, but if you are not in the right place targeting the right demographic, you are not likely to get the results you want.

To resolve this, typically, companies invest, but if that is not channelized properly, it will be futile.

So, the best way out of this dilemma is to have a clear customer acquisition strategy in place.

How can you create the ideal customer acquisition strategy for your business?

  • Define what your goals are

You need to define your goals so that you can meet the revenue expectations you have for the current fiscal year. You need to find a value for the metrics –

  • MRR – Monthly recurring revenue, which tells you all the income that can be generated from all your income channels.
  • CLV – Customer lifetime value tells you how much a customer is willing to spend on your business during your mutual relationship duration.  
  • CAC – Customer acquisition costs, which tells how much your organization needs to spend to acquire customers constantly.
  • Churn rate – It tells you the rate at which customers stop doing business.

All these metrics tell you how well you will be able to grow your business and revenue.

  • Identify your ideal customers

You need to understand who your current customers are and who your target customers are. Once you are aware of your customer base, you can focus your energies in that direction and get the maximum sale of your products or services. You can also understand what your customers require through various analytics and markers and address them to leverage your products/services towards them.

  • Choose your channels for customer acquisition

How will you acquire customers who will eventually tell at what scale and at what rate you need to expand your business? You could market and sell your products on social media channels like Instagram, Facebook and YouTube, or invest in paid marketing like Google Ads. You need to develop a unique strategy for each of these channels. 

  • Communicate with your customers

If you know exactly what your customers have in mind, then you will be able to develop your customer strategy with a clear perspective in mind. You can do it through surveys or customer opinion forms, email contact forms, blog posts and social media posts. After that, you just need to measure the analytics, clearly understand the insights, and improve your strategy accordingly.

Combining these strategies with your long-term business plan will bring results. However, there will be challenges on the way, where you need to adapt as per the requirements to make the most of it. At the same time, introducing new technologies like AI and ML can also solve such issues easily. To learn more about the use of AI and ML and how they are transforming businesses, keep referring to the blog section of E2E Networks.

Reference Links

This is a decorative image for: Constructing 3D objects through Deep Learning
October 18, 2022

Image-based 3D Object Reconstruction State-of-the-Art and trends in the Deep Learning Era

3D reconstruction is one of the most complex issues of deep learning systems. There have been multiple types of research in this field, and almost everything has been tried on it — computer vision, computer graphics and machine learning, but to no avail. However, that has resulted in CNN or convolutional neural networks foraying into this field, which has yielded some success.

The Main Objective of the 3D Object Reconstruction

Developing this deep learning technology aims to infer the shape of 3D objects from 2D images. So, to conduct the experiment, you need the following:

  • Highly calibrated cameras that take a photograph of the image from various angles.
  • Large training datasets can predict the geometry of the object whose 3D image reconstruction needs to be done. These datasets can be collected from a database of images, or they can be collected and sampled from a video.

By using the apparatus and datasets, you will be able to proceed with the 3D reconstruction from 2D datasets.

State-of-the-art Technology Used by the Datasets for the Reconstruction of 3D Objects

The technology used for this purpose needs to stick to the following parameters:

  • Input

Training with the help of one or multiple RGB images, where the segmentation of the 3D ground truth needs to be done. It could be one image, multiple images or even a video stream.

The testing will also be done on the same parameters, which will also help to create a uniform, cluttered background, or both.

  • Output

The volumetric output will be done in both high and low resolution, and the surface output will be generated through parameterisation, template deformation and point cloud. Moreover, the direct and intermediate outputs will be calculated this way.

  • Network architecture used

The architecture used in training is 3D-VAE-GAN, which has an encoder and a decoder, with TL-Net and conditional GAN. At the same time, the testing architecture is 3D-VAE, which has an encoder and a decoder.

  • Training used

The degree of supervision used in 2D vs 3D supervision, weak supervision along with loss functions have to be included in this system. The training procedure is adversarial training with joint 2D and 3D embeddings. Also, the network architecture is extremely important for the speed and processing quality of the output images.

  • Practical applications and use cases

Volumetric representations and surface representations can do the reconstruction. Powerful computer systems need to be used for reconstruction.

Given below are some of the places where 3D Object Reconstruction Deep Learning Systems are used:

  • 3D reconstruction technology can be used in the Police Department for drawing the faces of criminals whose images have been procured from a crime site where their faces are not completely revealed.
  • It can be used for re-modelling ruins at ancient architectural sites. The rubble or the debris stubs of structures can be used to recreate the entire building structure and get an idea of how it looked in the past.
  • They can be used in plastic surgery where the organs, face, limbs or any other portion of the body has been damaged and needs to be rebuilt.
  • It can be used in airport security, where concealed shapes can be used for guessing whether a person is armed or is carrying explosives or not.
  • It can also help in completing DNA sequences.

So, if you are planning to implement this technology, then you can rent the required infrastructure from E2E Networks and avoid investing in it. And if you plan to learn more about such topics, then keep a tab on the blog section of the website

Reference Links

This is a decorative image for: Comprehensive Guide to Deep Q-Learning for Data Science Enthusiasts
October 18, 2022

A Comprehensive Guide To Deep Q-Learning For Data Science Enthusiasts

For all data science enthusiasts who would love to dig deep, we have composed a write-up about Q-Learning specifically for you all. Deep Q-Learning and Reinforcement learning (RL) are extremely popular these days. These two data science methodologies use Python libraries like TensorFlow 2 and openAI’s Gym environment.

So, read on to know more.

What is Deep Q-Learning?

Deep Q-Learning utilizes the principles of Q-learning, but instead of using the Q-table, it uses the neural network. The algorithm of deep Q-Learning uses the states as input and the optimal Q-value of every action possible as the output. The agent gathers and stores all the previous experiences in the memory of the trained tuple in the following order:

State> Next state> Action> Reward

The neural network training stability increases using a random batch of previous data by using the experience replay. Experience replay also means the previous experiences stocking, and the target network uses it for training and calculation of the Q-network and the predicted Q-Value. This neural network uses openAI Gym, which is provided by taxi-v3 environments.

Now, any understanding of Deep Q-Learning   is incomplete without talking about Reinforcement Learning.

What is Reinforcement Learning?

Reinforcement is a subsection of ML. This part of ML is related to the action in which an environmental agent participates in a reward-based system and uses Reinforcement Learning to maximize the rewards. Reinforcement Learning is a different technique from unsupervised learning or supervised learning because it does not require a supervised input/output pair. The number of corrections is also less, so it is a highly efficient technique.

Now, the understanding of reinforcement learning is incomplete without knowing about Markov Decision Process (MDP). MDP is involved with each state that has been presented in the results of the environment, derived from the state previously there. The information which composes both states is gathered and transferred to the decision process. The task of the chosen agent is to maximize the awards. The MDP optimizes the actions and helps construct the optimal policy.

For developing the MDP, you need to follow the Q-Learning Algorithm, which is an extremely important part of data science and machine learning.

What is Q-Learning Algorithm?

The process of Q-Learning is important for understanding the data from scratch. It involves defining the parameters, choosing the actions from the current state and also choosing the actions from the previous state and then developing a Q-table for maximizing the results or output rewards.

The 4 steps that are involved in Q-Learning:

  1. Initializing parameters – The RL (reinforcement learning) model learns the set of actions that the agent requires in the state, environment and time.
  2. Identifying current state – The model stores the prior records for optimal action definition for maximizing the results. For acting in the present state, the state needs to be identified and perform an action combination for it.
  3. Choosing the optimal action set and gaining the relevant experience – A Q-table is generated from the data with a set of specific states and actions, and the weight of this data is calculated for updating the Q-Table to the following step.
  4. Updating Q-table rewards and next state determination – After the relevant experience is gained and agents start getting environmental records. The reward amplitude helps to present the subsequent step.  

In case the Q-table size is huge, then the generation of the model is a time-consuming process. This situation requires Deep Q-learning.

Hopefully, this write-up has provided an outline of Deep Q-Learning and its related concepts. If you wish to learn more about such topics, then keep a tab on the blog section of the E2E Networks website.

Reference Links

This is a decorative image for: GAUDI: A Neural Architect for Immersive 3D Scene Generation
October 13, 2022

GAUDI: A Neural Architect for Immersive 3D Scene Generation

The evolution of artificial intelligence in the past decade has been staggering, and now the focus is shifting towards AI and ML systems to understand and generate 3D spaces. As a result, there has been extensive research on manipulating 3D generative models. In this regard, Apple’s AI and ML scientists have developed GAUDI, a method specifically for this job.

An introduction to GAUDI

The GAUDI 3D immersive technique founders named it after the famous architect Antoni Gaudi. This AI model takes the help of a camera pose decoder, which enables it to guess the possible camera angles of a scene. Hence, the decoder then makes it possible to predict the 3D canvas from almost every angle.

What does GAUDI do?

GAUDI can perform multiple functions –

  • The extensions of these generative models have a tremendous effect on ML and computer vision. Pragmatically, such models are highly useful. They are applied in model-based reinforcement learning and planning world models, SLAM is s, or 3D content creation.
  • Generative modelling for 3D objects has been used for generating scenes using graf, pigan, and gsn, which incorporate a GAN (Generative Adversarial Network). The generator codes radiance fields exclusively. Using the 3D space in the scene along with the camera pose generates the 3D image from that point. This point has a density scalar and RGB value for that specific point in 3D space. This can be done from a 2D camera view. It does this by imposing 3D datasets on those 2D shots. It isolates various objects and scenes and combines them to render a new scene altogether.
  • GAUDI also removes GANs pathologies like mode collapse and improved GAN.
  • GAUDI also uses this to train data on a canonical coordinate system. You can compare it by looking at the trajectory of the scenes.

How is GAUDI applied to the content?

The steps of application for GAUDI have been given below:

  • Each trajectory is created, which consists of a sequence of posed images (These images are from a 3D scene) encoded into a latent representation. This representation which has a radiance field or what we refer to as the 3D scene and the camera path is created in a disentangled way. The results are interpreted as free parameters. The problem is optimized by and formulation of a reconstruction objective.
  • This simple training process is then scaled to trajectories, thousands of them creating a large number of views. The model samples the radiance fields totally from the previous distribution that the model has learned.
  • The scenes are thus synthesized by interpolation within the hidden space.
  • The scaling of 3D scenes generates many scenes that contain thousands of images. During training, there is no issue related to canonical orientation or mode collapse.
  • A novel de-noising optimization technique is used to find hidden representations that collaborate in modelling the camera poses and the radiance field to create multiple datasets with state-of-the-art performance in generating 3D scenes by building a setup that uses images and text.

To conclude, GAUDI has more capabilities and can also be used for sampling various images and video datasets. Furthermore, this will make a foray into AR (augmented reality) and VR (virtual reality). With GAUDI in hand, the sky is only the limit in the field of media creation. So, if you enjoy reading about the latest development in the field of AI and ML, then keep a tab on the blog section of the E2E Networks website.

Reference Links

Build on the most powerful infrastructure cloud

A vector illustration of a tech city using latest cloud technologies & infrastructure