Step By Step Guide to Image Classification Using MobileNetV2

August 22, 2023


Image classification represents a fundamental task within the realm of computer vision, involving the assignment of labels or categories to images. This tutorial guides the reader through the process of developing an image classification model using a deep learning approach. The tutorial employs Python as well as popular libraries like TensorFlow and Keras for the model creation process using MobileNetV2 [1]. The reader must have a basic understanding of Python programming, and familiarity with the concepts of machine learning and deep learning.

1: Data Collection and Preparation

Dataset Selection

The process begins with the critical task of selecting a suitable dataset for the image classification process - our focus narrows on to the esteemed Fruits and Vegetables Image Recognition Dataset [2]

Data Preprocessing

Upon dataset selection, the next step involves preparing the data to facilitate model training. This encompasses several essential preprocessing steps:

  • Data Loading: The Fruits and Vegetable dataset is loaded using relevant Python libraries such as TensorFlow or PyTorch.
  • Image Resizing: The images are resized to a standardized dimension, often set to 64x64 pixels. This resizing ensures uniformity across the dataset and aids in computational efficiency.
  • Normalization: Pixel values of the images are normalized to a range between 0 and 1. This normalization process enhances the model's convergence during training.
  • Data Partitioning: The dataset is divided into distinct training and validation subsets. A typical split ratio is 80% for training and 20% for validation. This partitioning enables the assessment of the model's performance on previously unseen data.

Consider an application seeking to categorize products based on images to optimize inventory management. In this context, the fruits and vegetables dataset could serve as a foundational resource to construct a classification model capable of distinguishing various fruits and vegetables.

Step 2: Building the Model

Library Import

In this phase, the process commences by importing essential libraries to facilitate the construction of the image classification model. TensorFlow, Keras, and any other pertinent libraries are imported to establish a strong foundation for the model development process.

Model Architecture

Upon library import, the model's architecture is established. This stage presents two pivotal choices:

  • Pre-Built Architecture: Opt for a pre-existing architecture, such as VGG or ResNet. These architectures are renowned for their efficacy in image classification tasks, with well-defined structures designed to capture intricate features.
  • Custom Architecture: Alternatively, craft a novel architecture using Keras' versatile layers. This tailored approach enables the creation of a model precisely attuned to the specific classification requirements, offering flexibility in design. However, for this tutorial, we will focus on the power of transfer learning with MobileNetV2.

Transfer Learning Technique

Transfer learning takes the spotlight as a potent technique to harness the capabilities of pre-trained models. In our case, we will leverage the remarkable MobileNetV2 as the base model and fine-tune it for our specific task of fruit and vegetable image recognition.


Following the architecture establishment, the model is compiled. This involves defining crucial components that profoundly impact its learning process and subsequent performance:

  • Loss Function: Choose an appropriate loss function that guides the model towards convergence during training. The choice of loss function aligns with the nature of the classification task.
  • Optimizer: Select an optimizer responsible for refining the model's learning process. Popular choices include Adam and SGD, each influencing how the model updates its parameters.
  • Evaluation Metrics: Specify evaluation metrics that provide insights into the model's performance. Metrics like accuracy, precision, and recall gauge the model's effectiveness in differentiating classes.

This code exemplifies the creation of a robust image classification model using the 'Fruits and Vegetables Image Recognition Dataset' and the power of 'MobileNetV2 with Deep Transfer Learning Technique.' The model architecture, intricately woven with the elegance of MobileNetV2, is primed for classification excellence. Compiled with a choice optimizer an

d tailored loss function, this symphony of code converges toward the harmonious goal of recognizing the diverse array of fruits and vegetables present within the dataset..

Step 3: Training the Model

Data Augmentation

The training phase is initiated by applying data augmentation techniques to augment the training dataset. These techniques introduce controlled variations to the images, enriching the dataset's diversity. This is a crucial step to combat overfitting tendencies and enhance the model's robustness.

Model Training

With augmented data in place, the model is ready for training. The curated training dataset is utilized to train the model iteratively. During training, it's essential to closely monitor two key indicators:

  • Validation Loss: This metric gauges how well the model is generalizing to unseen data. A decreasing validation loss suggests effective learning.
  • Validation Accuracy: Monitoring validation accuracy provides insights into the model's performance. An increasing accuracy indicates that the model is becoming proficient at correctly classifying images.

This training phase is pivotal in enabling the model to recognize patterns and accurately classify diverse instances across the image dataset.

4: Model Evaluation

Validation Set Evaluation

To gauge the model's proficiency, it undergoes rigorous evaluation on the validation set. This section introduces a case study to exemplify the evaluation process. In our ongoing scenario of image classification for product categorization, the trained model is evaluated on the validation set composed of images from diverse product categories. The following code snippet demonstrates how to evaluate the model using TensorFlow and Keras:

In the case study, the validation loss and accuracy metrics provide critical insights into the model's performance in accurately categorizing various products within the validation set.


Should the model's performance fall short of desired standards, fine-tuning strategies come into play to enhance its capabilities further.

Hyperparameter Tuning

Hyperparameters significantly influence a model's learning process. Fine-tuning hyperparameters like learning rate and optimizer can enhance the model's effectiveness:

Model Architecture Refinement

Adjusting the model's architecture can yield performance improvements. For instance, consider adding an additional convolutional layer to the architecture:

Extended Training

Extending training duration enables the model to grasp intricate features. Increase the number of training epochs:

Fine-tuning strategies are pivotal in refining the model's accuracy and reliability for diverse image classification tasks.The model evaluation phase, illuminated through the case study, meticulously examines the model's proficiency with various metrics. Fine-tuning strategies provide avenues for ameliorating performance and adapting the model to specific image classification challenges.

5. Predictions

Transitioning to the prediction phase, the trained model is loaded using Keras. This preparatory step is crucial for leveraging the model's learned knowledge in making predictions. In our retail product categorization scenario, after fine-tuning and evaluation, the trained model is ready for deployment. The following code snippet demonstrates how to load the trained model using Keras:

Here, the 'trained_model.h5' file contains the model's architecture, weights, and other necessary information. To ensure accurate interpretation of new input data by the model, it's imperative to apply the same preprocessing steps as during training.

It is vital to preprocess the new images consistently. This code snippet showcases how to preprocess a single image using TensorFlow and Keras:

Prediction Generation

Finally, the model's essence shines as it generates predictions for the categories of new images, showcasing its generalization capabilities. This code snippet demonstrates how to obtain predictions:

Here, predicted_category corresponds to the predicted class label of the new image.


Throughout this tutorial, a comprehensive exploration of the complete image classification workflow has been meticulously undertaken. Commencing with the foundational phases of data collection and preparation, progressing through the intricate steps of model construction, training, evaluation, and prediction, each aspect of this multifaceted process has been thoughtfully addressed.

The relevance of image classification is illuminated as a versatile technique with applications ranging from medical diagnostics to object recognition. The mastery of this skill empowers individuals to extract nuanced insights from visual data, driving innovation across a myriad of domains.

With our spotlight cast upon the 'Fruits and Vegetables Image Recognition Dataset' and our sails propelled by the winds of the 'MobileNetV2 with Deep Transfer Learning Technique,' we've unearthed practical wisdom. This tutorial has unraveled the mechanics of this dynamic duo, accentuating the prowess of deep transfer learning through MobileNetV2. As we ventured into the realms of fruits and vegetables, the algorithmic symphony orchestrated by MobileNetV2 echoed through our model, shaping it to discern the intricacies of nature's bounty.

On E2E Cloud, you can deploy MobileNetV2 and train it efficiently in a scalable manner on advanced GPU nodes, ranging from H100, A100, L4, V100, L4S and more. Get started today by creating an account on MyAccount.


[1] Gulzar, Y. (2023, January 19). Fruit Image Classification Model Based on MobileNetV2 with Deep Transfer Learning Technique. Sustainability, 15(3), 1906.

[2] Seth. (2022). Fruits and Vegetables Image Recognition Dataset. Kaggle. Retrieved August 8, 2023, from

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