Convolutional Neural Network – PyTorch Implementation

January 30, 2023

What are neural networks?

Neural networks are a type of artificial intelligence that is modeled after the human brain. They are composed of interconnected nodes, or neurons, which are connected to each other in various ways. Each neuron is responsible for a specific task, such as pattern recognition or memory recall. Neural networks can recognize patterns and make decisions based on those patterns, and are able to learn from experience. They are used in a wide range of applications, including image recognition, natural language processing, and robotics.

Being a subset of machine learning, they are at the heart of deep learning algorithms. They are composed of node layers, containing an input layer, one or more hidden layers, and an output layer. Each node connects to another and has an associated weight and threshold value, that node is activated, sending data to the next layer of the network. Otherwise, no data is passed along to the next layer of the network.

Different types of neural networks are used in several use cases. For example: recurrent neural networks are commonly used for natural language processing and speech recognition whereas convolutional neural networks are often utilized for classification and computer vision tasks. Prior to CNNs, manual, time-consuming feature extraction methods were used to identify objects in images. However, convolutional neural networks now provide a more scalable approach to image classification and object recognition tasks, leveraging principles from linear algebra, specifically matrix multiplication, to identify patterns within an image. That said, they can be computationally demanding, requiring GPUs to train models.

CNNs- History and Evolution

The concept of convolutional neural networks (CNNs) dates back to the late 1980s, when Yann LeCun and colleagues at AT&T Bell Labs developed the first convolutional neural network for recognizing handwritten digits. This concept was later refined by researchers who developed the Neocognitron in 1980 & the widely used backpropagation algorithm for training neural networks. 

In the late 1990s, CNNs began to be used more widely for tasks such as image recognition, object detection and natural language processing. The breakthrough came in 2012, when some of the prestigious researchers won the ImageNet Large-Scale Visual Recognition Challenge (ILSVRC) using a deep convolutional neural network. This success was followed by a number of similar breakthroughs in the field of computer vision, including the development of faster and more efficient CNNs, such as the ResNet architecture. In recent years, CNNs have been used for a wide range of tasks, including medical image analysis, natural language processing, autonomous vehicles, and robotics. 

Why Convolutional Neural Networks?

A ConvNet is able to successfully capture the spatial and temporal dependencies in an image through the application of relevant filters. The architecture performs a better fitting to the image dataset due to the reduction in the number of parameters involved and the reusability of weights. In other words, the network can be trained to understand the sophistication of the image better. It is a class of deep neural networks that is commonly applied for analyzing visual imagery. They can also be used for other data analysis or classification problems. Most generally, we can think of a CNN as an artificial neural network that has some type of specialization for being able to pick out or detect patterns and make sense of them. This pattern detection is what makes CNN so useful for image analysis so if a CNN is just some form of an artificial neural network what differentiates it from just a standard multi-layer perceptron or MLP.  

How do convolutional neural networks work?

Convolutional nets mainly work on image data and apply the so called convolutional filters so a typical confident architecture looks like the below.

We have our image and different convolutional layers, optional activation functions followed by so-called pooling layers and these layers are used to automatically run some features from the images and then at the end we have one or more fully connected layers for the actual classification tasks. 

These convolutional filters work by applying a filter kernel to our image so we put the filter at the first position as the input image and then we compute the output value by multiplying and summing up all the values and then we write the value into the output image. 

In other words, a convolutional layer combines two parts and generates a function that expresses how one alters the other. Recall, if you are familiar with neural networks, that they have inputs which are fed through a layer that has weights. If you take a look at this from a convolution perspective, such a layer will have weights - and it evaluates how many inputs "alter", or "trigger" these weights.

Then, by adapting the weights during optimization, we can teach the network to be "triggered" by certain patterns present in the input data. Indeed, such layers can be taught to be triggered by certain parts that are present in some input data, such as a nose, and relate it to e.g. output class "human" (when seen from the whole network).

Since Convnets work with a kernel that is slided over the input data, they are said to be translation invariant - meaning that a nose can be detected regardless of size and position within the image. It is why ConvNets are way more powerful for computer vision problems than classic MLPs.

Why is PyTorch implemented in CNN?

PyTorch is a powerful open-source deep learning framework that can be used to develop and deploy Convolutional Neural Networks (CNNs) in production. CNNs are a type of deep learning algorithm that can be used to analyze and classify images, videos, and other types of data. PyTorch CNNs can be used for image classification, object detection, and other computer vision tasks. They can also be used for natural language processing, speech recognition, and other tasks involving text or audio data. PyTorch CNNs are easy to use and have a high level of accuracy and performance. 

When deploying PyTorch CNNs in production, it is important to consider the hardware requirements. PyTorch typically requires a GPU with CUDA support and a minimum of 8GB of RAM. 

Additionally, developers must consider the software requirements, such as the version of Python and the appropriate PyTorch packages. 

It is also important to consider the deployment environment, such as the cloud platform or onsite hardware setup. 

Finally, developers should consider the security measures required to protect the data. When deploying PyTorch CNNs in production, it is important to perform testing and validation.

How is PyTorch implemented in neural networks?

PyTorch is used to implement Convolutional Neural Networks (CNNs) by defining the layers of the network, performing the convolution operations, and applying various activation functions. The core of the network is a convolutional layer, which takes an input image and applies a set of convolutional filters to it. These filters extract features from the input image, like edges and curves, and can be used to identify objects in the image. The output of the convolutional layer is then fed into a pooling layer, which reduces the size of the feature map by aggregating or combining the features. The result of the pooling layer is then passed through a fully-connected layer, which is a regular neural network that is used to make predictions based on the features extracted from the image. 

The output of the fully-connected layer is passed through an activation function, which determines the final output of the CNN.

Steps to implement PyTorch in CNN:

1. Install PyTorch: Install the latest version of PyTorch using pip or conda depending on your system. 

2. Load the Dataset: Load the dataset you wish to use for training your CNN. 

3. Preprocess the Data: Preprocess the data by performing transformations such as normalization, scaling, and augmentation. 

4. Define the Model: Define the CNN architecture you wish to use for your task. 

5. Train the Model: Train the model using an optimizer and a loss function. 

6. Evaluate the Model: Evaluate the model on the test set and measure its performance.

7. Fine-tune the Model: Fine-tune the model by adjusting its hyperparameters and tuning the architecture. 

8. Deploy the Model: Deploy the model in production and serve predictions.

PyTorch CNN in Production 

PyTorch offers a number of tools that can be used to evaluate, deploy, and maintain CNNs in production. These tools help to ensure that models are deployed quickly, accurately, and securely. The first step in deploying a PyTorch CNN in production is to create a model. This can be done in a variety of ways, including using pre-trained models, or training a model from scratch on a custom dataset. Once the model has been created, it can be evaluated for accuracy and performance. PyTorch provides a number of evaluation metrics, including accuracy and AUC, as well as tools for visualizing and debugging models. Once the model is evaluated, it can be deployed to production. 

PyTorch provides a number of ways to deploy models, including using cloud solutions such as frameworks such as TensorFlow Serving and OpenVINO. Once the model is deployed, PyTorch also provides tools for monitoring and maintaining the model, such as performance metrics and automated alerts. Finally, the deployed model can be monitored for performance in production. PyTorch provides a number of tools for monitoring performance, including metrics such as accuracy, AUC, precision and recall. Additionally, PyTorch provides tools for debugging, such as visualizing models, weights and activations, and examining feature maps.

Deploying a PyTorch CNN in production requires a few steps: 

1. Preparing your data: Depending on the size of your dataset, it may need to be split into smaller batches. Additionally, you will need to scale and normalize your data. 

2. Training your model: PyTorch provides a number of built-in optimizers and loss functions. You can also use data augmentation to increase the accuracy of your model. 

3. Evaluating your model: Once your model is trained, you can evaluate its performance on a test set. This will give you an indication of how well the model will perform on unseen data. 

4. Deploying your model: PyTorch provides several deployment options, including direct deployment to the cloud or a local machine. You can also use a containerization solution such as Docker to deploy your model. 

5. Monitoring and updating your model: You should monitor your model's performance in production, and update your model as needed. PyTorch provides tools for monitoring metrics such as accuracy and recall.

How can you deploy PyTorch/CNNs on E2E Cloud?

Using E2E Cloud Myaccount portal -

  • First login into the myaccount portal of E2E Networks with your respective credentials. 
  • Now, Navigate to the GPU Wizard from your dashboard.
  • Under the “Compute” menu extreme left click on “GPU” 
  • Then click on “GPU Cloud Wizard”

  • For NGC Container Pytorch click on “Next” under the “Actions” column.
  • Choose the card according to requirement,  A100 is recommended.

Now, Choose your plan amongst the given options. 

  • Optionally you can add SSH key (recommended) or subscribe to CDP backup.
  • Click on “Create my node”
  • Wait for few minutes and and confirm that node is in running state

  • Now, Open terminal on your local PC and type the following command

ssh -NL localhost:1234:localhost:8888 root@<your_node_ip>

  • The command usually will not show any output which represents the command has run without any error.

  • Congratulations! Now you can run your python code inside this jupyter notebook which has Pytorch and all the libraries frequently used in machine learning preconfigured.
  • To get the most out of GPU acceleration use RAPIDS and DALI  which are already installed inside this container.
  • RAPIDS and DALI accelerate the tasks in machine learning apart from the learning also like data loading and preprocessing.

This article covered the PyTorch implementation of a simple CNN. The reader is encouraged to play around with the network architecture and model hyperparameters to increase the model accuracy even more. 

We hope we were able to guide you through the implementation of PyTorch on E2E Cloud. As you know, E2E Cloud is an accelerated cloud computing platform for training your ML models. 

You can contact us for your free trial:

Reference Links:

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