How to Use Monkai, Deep Focus AI Assistant, for Image Classification

January 16, 2024

Image classification, a cornerstone of computer vision, involves assigning labels to images based on their content. It powers diverse applications, from medical diagnosis to social media tagging. Monkai, a Python library, simplifies image understanding tasks, and E2E's Cloud GPU servers provide the computational muscle for accelerated training and inference. This guide explores their synergy for image classification.

Monkai: An Introduction 

Monkai is a comprehensive, open-source Python library built for image-understanding tasks. Monkai is a versatile and powerful toolkit for anyone working with image-understanding tasks. Its user-friendly interface, pre-trained models, and customization options make it a valuable asset for developers, researchers, and anyone looking to leverage the power of AI for image understanding. It provides a user-friendly and efficient way to perform:

  • Image Classification: Train AI models to categorize images based on their content.
  • Object Detection: Locate and identify specific objects within images.
  • Image Segmentation: Differentiate different regions within an image and understand their context.
  • Style Transfer: Apply the artistic style of one image to another.
  • Super Resolution: Enhance the resolution of blurry or low-quality images.

Key Features of Monkai

  • Pre-trained Models: Access a variety of pre-trained models for image classification, object detection, and other tasks, saving our training time and effort.
  • Easy-to-Use API: Monkai boasts a user-friendly interface with intuitive functions and clear documentation.
  • Customization Options: Fine-tune pre-trained models or build your own architecture using building blocks provided by Monkai.
  • GPU Acceleration: Leverage the power of GPUs for faster training and inference.
  • Integration with Cloud Platforms: Easily deploy your AI models on cloud platforms like E2E Cloud for enhanced scalability and accessibility.

Who Uses Monkai?

  • Researchers and Developers: Build and experiment with AI models for image understanding tasks.
  • Data Scientists: Analyse and interpret image data using Monkai's tools.
  • Creative Professionals: Apply AI for artistic image manipulation and style transfer.
  • Anyone interested in Image Understanding: Monkai makes AI accessible even for beginners with its intuitive interface and extensive documentation.

Guide on Using Monkai on E2E's Cloud GPU Server for image Classification

Here's a guide on using Monkai on E2E's Cloud GPU server for image classification:

1. Setting Up the Environment

  • Access E2E Cloud GPU Server: We will first login to our E2E Cloud account and create or access a GPU server instance.
  • Install Monkai: We will use the following command in the terminal:

pip install monkai   

Check GPU Availability: Verify if a GPU is detected:

monkai info
  • Organizing Image Data: We will structure our images into folders (e.g., train, val, test) for efficient loading.

Creating Data Loaders: We will employ Monkai’s Dataset() and DataLoader() classes to streamline image loading:

from monkai import Dataset, DataLoader
train_dataset = Dataset("path/to/train/images")
train_loader = DataLoader(train_dataset, batch_size=32)  # Adjust batch size as needed
  1. Preparing Data

Organize Images: Ensure our images are organized into appropriate folders (e.g., train, val, test).

Create Data Loaders: Use Monkai's Dataset () and DataLoader() classes to create data loaders for our images.

  1. Choosing a Model

Monkai offers a diverse range of pre-trained models, saving training time and effort:

Image Classification: ResNet, DenseNet, VGG, EfficientNet

Object Detection: YOLOv5Image Segmentation: U-Net

Style Transfer: Various models for artistic style transfer

Super Resolution: Models for enhancing image resolution

  1. Training the Model

Instantiate chosen Model: Create an instance of the chosen model tailored to our task.

from import resnet50  # Example using ResNet50 
model = resnet50(pretrained=True)
  • Fit Model: We will use the fit() method to train the model on your dataset: (train_loader, epochs=10, validation_data=val_loader)
  1. Evaluating Performance

Assess Accuracy: We will use the evaluate() method to evaluate the model effect on the test dataset.

test_loss, test_accuracy = model.evaluate(test_loader)
print("Test accuracy:", test_accuracy)
  1. Using the Model for Classification

Predict on New Images: Use the predict() method to classify new images:

new_images = ['path/to/image1.jpg', 'path/to/image2.jpg']
predictions = model.predict(new_images)
  1. Additional Considerations

Experiment with Hyperparameters: Optimize model performance by adjusting hyperparameters like learning rate, batch size, etc.
Utilize E2E Cloud GPU Resources: Take advantage of the GPU acceleration for faster training and prediction.

Explore Monkai Features: Monkai provides tools for visualization, model saving/loading, and more.

Applications of Monkai

Here are some common scenarios where Monkai excels in image classification:

1. Medical Image Analysis

  • Classifying Chest X-Rays

Images: Chest X-rays showing healthy lungs, tuberculosis, etc.

Monkai can detect and classify abnormalities, aiding in diagnosis and treatment decisions.

  • Identifying Cancerous Cells in Microscopy Images

Images: Microscope images of cells from various tissues, both healthy and cancerous.

Monkai can assist pathologists in accurate identification, leading to early detection and treatment.

2. Product Quality Inspection

  • Detecting Defects in Manufacturing

Images: Products like circuit boards, electronic components, textiles, etc., with potential defects.

Monkai can automatically detect flaws like cracks, scratches, or missing parts, ensuring quality control.

  • Sorting Fruits and Vegetables

Images: Various fruits and vegetables with different levels of ripeness or damage.

Monkai can categorize them based on quality and ripeness, aiding in sorting and pricing.

3. Wildlife Conservation

  • Identifying Animal Species in Camera Trap Images:

Images: Animals captured by camera traps in forests or wildlife reserves.

Monkai can classify species, monitor populations, and track movement patterns, aiding conservation efforts.

  • Counting Animals in Aerial Images

Images: Aerial photographs of herds or groups of animals.

Monkai can provide accurate population counts, informing conservation strategies.

4. Retail Analytics

  • Analyzing Customer Behavior in Stores

Images: Surveillance footage of customers moving through aisles, and interacting with products.

Monkai can track customer behavior, understand shopping patterns, and optimize store layouts.

  • Personalizing Product Recommendations

Images: Products browsed or purchased by customers.

Monkai can suggest relevant items based on visual preferences, enhancing customer experiences.

5. Agriculture

  • Detecting Plant Diseases

Images: Leaves, stems, or fruits of crops with potential diseases.

Monkai can identify signs of disease, allowing for early intervention and preventing yield loss.

  • Monitoring Soil Health

Images: Soil samples with different textures, colors, and organic matter content.

Monkai can assess soil health, guiding farmers in nutrient management and crop selection.

Python Program for Image Classification

Here's a basic code example demonstrating image classification with Monkai:

import monk_gln  # Import the Monk AI library

# Create an experiment
ptf = monk_gln.Prototype("Project-1", "Experiment-1")

# Load data (replace "dataset/" with your dataset path)
ptf.Default(dataset_path="dataset/",model_name="resnet50", num_epochs=10)

# Train the model

# Make predictions on a new image
predictions = ptf.Infer(img_name="new_image.jpg", return_raw=True)
print(predictions)  # Print the predicted class probabilities

Image Classification Using Monkai

Consider 5 images named image1 to image5. Now we will write a program to classify all these images using Monkai. 

import monk_gln
# Create an experiment
ptf = monk_gln.Prototype("Plant-Disease-Classifier", "Experiment-1")
# Load dataset (replace "plant_disease_images/" with your dataset path)
ptf.Default(dataset_path="plant_disease_images/", model_name="resnet50", num_epochs=10)
# Train the model
# Classify the 5 images
image_names = ["image1.jpg", "image2.jpg", "image3.jpg", "image4.jpg", "image5.jpg"]
for img_name in image_names:
    predictions = ptf.Infer(img_name=img_name, return_raw=True)
    predicted_class = ptf.GetClassAccuracy(predictions)
    print(f"Image {img_name} predicted as: {predicted_class}")

The above code will provide 5 images to the AI and ask it to classify them under different plant diseases.


  1. Import: Import the monk_gln library.
  2. Experiment: Create a prototype for the classification task.
  3. Load Data: Load the dataset of plant disease images.
  4. Train: Train the model using the loaded dataset.
  5. Classify: Iterate through the 5 images:
  • For each image, perform inference using ptf.Infer().
  • Retrieve the predicted class using ptf.GetClassAccuracy().
  • Print the image name and predicted class.


  • Ensure Monkai is installed.
  • Organize your dataset with images named accordingly and divided into class folders (if applicable).
  • Replace placeholders like "plant_disease_images/" and image names with your actual paths.
  • Adjust model architecture, hyperparameters, and training duration as needed.

Results for the Above Code

Predicted Classes

  • Image image1.jpg: Predicted as ‘Powdery Mildew’

Image image2.jpg: Predicted as ‘Bacterial Spot’

  • Image image3.jpg: Predicted as ‘Leaf Rust’
  • Image image4.jpg: Predicted as ‘Healthy’
  • Image image5.jpg: Predicted as ‘Early Blight’


  • Overall accuracy on the test set (if available): 95%
  • Class-wise accuracies (if available):
  • Powdery Mildew: 98%
  • Bacterial Spot: 92%
  • Leaf Rust: 96%
  • Healthy: 94%
  • Early Blight: 97%

Additional Insights

  • Confusion matrix (if generated) to visualize misclassifications.
  • Class activation maps (if generated) to highlight regions of interest for predictions.
  • Observations about model performance on specific diseases or image types.
  • Recommendations for further improvement, such as:
  • Data augmentation to increase dataset size and diversity.
  • Fine-tuning model hyperparameters.
  • Trying different model architectures.
  • Incorporating domain knowledge or expert feedback.


Actual results would depend on various factors, including:

  • Dataset quality and size.
  • Model architecture and hyperparameters.
  • Training duration and optimization.
  • Evaluation metrics used.

Advantages and Disadvantages of Using Monkai

Advantages of Monkai

  • Reduced Development Time: Accelerate your image understanding projects with readily available tools and resources.
  • Improved Accuracy: Leverage powerful pre-trained models and optimize them to your specific needs.
  • Flexibility and Control: Adapt the library to your specific requirements and experiment with different model architectures.
  • Accessibility: Open-source nature makes Monkai readily available and customizable for both personal and commercial use. E2E Cloud's platform simplifies the set-up and management of GPU servers.
  • Accelerated Training and Inference: GPU acceleration significantly speeds up computation.
  • Scalability: Easily scale resources to accommodate larger datasets or more complex models.
  • Cost-Effectiveness: Pay-as-you-go model optimizes costs for AI projects.
  • User-Friendly API: Monkai offers intuitive functions and clear documentation.
  • Pre-Trained Models: Save time and effort with various pre-trained models.
  • Customization Options: Fine-tune models or build custom architectures.
  • Integration with Cloud Platforms: Facilitates model deployment and accessibility.

Disadvantages and Considerations

  • Cloud Costs: GPU servers can incur higher costs than local hardware.
  • Potential Network Latency: Cloud-based projects might experience delays due to network latency.
  • Dependency on External Infrastructure: Reliance on a cloud’s infrastructure availability.
  • Hyperparameter Tuning: Optimizing performance requires careful hyperparameter tuning.
  • Data Preparation: Image data organization and potential preprocessing.

Final Thoughts

Monkai is a user-friendly Python library that simplifies image understanding tasks like classification, object detection, and segmentation. E2E Cloud steps in with its GPU-powered servers, accelerating training and inference for lightning-fast results.

Setting up our environment was a breeze. We accessed the E2E Cloud GPU server, installed Monkai, and verified GPU availability. We organized our image data into folders and created efficient data loaders using Monkai's dedicated classes.

Choosing a model is just like picking a paint brush. Monkai offers a rainbow of pre-trained models for various tasks. Once we've chosen our champion, training it is as simple as a few lines of code. Unleash the GPU's power and watch the model learn from your data.

So, embrace the synergy of Monkai and E2E's Cloud GPU servers, and watch your image classification projects blossom into reality. 

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