Artificial Intelligence @ Nagarro

Focused AI group in Nagarro (AI-COE) with a strong skilled workforce in AI
Data Sciences
Machine Learning
Deep Learning
Latest AI Technologies and Best practices in AI workflow
Cloud and Custom Solutions to fit Customer Concerns/Costs
Latest GPUs
Using Cloud Solutions
Custom on Premise Solution
Complete Workflow from modelling to Business Integration
Data Analysis
Model Building
Business Integration

Artificial Intelligence Services

Encourage your organization to make Data driven decisions
Incorporate Predictive Intelligence into your processes, products and services
Drive Automation into your processes and workflow

Data Services

Predictive Services

Cognitive Services

AI Services

Deep Learning Demonstrations @ Nagarro

In nagarro we are working on different types AI problems in multiple domains. We have built some demonstrations

Computer Vision

Railcar - Image classification using transfer learning

image-classification transfer-learning

A Deep Learning Model has been fine tuned through the techniques of Transfer Learning to recognize different rail car types.

Image classification - over 1000 types of general objects

image-classification fine-tuning

A Deep Learning Model that has been trained to recognize 1000 different objects.

Image Segmentation - over 20 types of general objects

image-segmentation deeplab

A Deep Learning Model that has been trained to detect 20 different objects and then mask them over original image.

Image Search

feature-extraction nearest-neighbour

A Deep Learning Model has been trained to search images which are most similar to the query image.

Object Detection - over 5 types of general objects

object-detection single-shot-detection

A Deep Learning Model has been trained to detect objects and draw bounding box at their location.

Recommendation Engine

Banking - Product Recommendation System

recommendation banking

A Machine learning model that recommends banking customers to buy next products.

Optical Character Recognition

OCR - Handwriting recognition

ocr handwriting-recognition

A Deep Learning Model has been trained to recognise handwritten text from an image

Anomaly Detection

Anomaly Detection - Finding anomaly in IoT Senor data

anomaly time-series

A Deep learning model continuously separating normal IOT operation from anomalous IOT operation

Natural Language Processing

Sentiment Analysis

sentiment-analysis nlp

A Deep Learning Model has been trained to predict sentiment from a sentence.

Video Intelligence

Configuration Validation

video-classification lstm

A Deep Learning Model has been trained to validate the configuration of video.

Nagarro Deep Learning Toolkit

Some of the popular tools we use are:


  • Python

    A simple, elegant, consistent, and math-like language popularly used in the area of Deep Learning and machine learning

Data Science & visualization

  • Pandas

    A great library for data manipulation and analysis. It offers data structures and operations for manipulating numerical tables and time series.
  • NumPy

    NumPy provides fast precompiled functions for numerical routines. It adds support to Python for large, multi-dimensional arrays and matrices. and a large library of high-level mathematical functions to operate on these arrays
  • Matplotlib

    Matplotlib is a plotting library for the Python programming language and its numerical mathematics extension NumPy
  • Seaborn

    Seaborn is a Python visualization library based on matplotlib. It provides a high-level interface for drawing attractive statistical graphics.

Deep Learning

  • TensorFlow

    Open source library for numerical computation using data flow graphs for Deep Learning
  • Theano

    Theano is a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently
  • Tefla

    Tefla is a deep learning mini-framework that sits on top of Tensorflow. Tefla's primary goal is to enable simple, stable, end-to-end deep learning.
  • Keras

    Keras is a high-level neural networks API, written in Python and capable of running on top of either TensorFlow or Theano.

Machine Learning

  • scikit-learn

    scikit-learn features various classification, regression and clustering algorithms and is designed to interoperate with the Python numerical and scientific libraries NumPy and SciPy


  • Flask

    Flask is a micro web framework written in Python and based on the Werkzeug toolkit and Jinja2 template engine
  • Celery

    Celery is an asynchronous task queue/job queue based on distributed message passing. It is focused on real-time operation, but supports scheduling as well.

Natural Language Processing

  • NLTK

    A suite of libraries and programs statistical natural language processing (NLP) for the Python. NLTK includes graphical demonstrations and sample data. and building research systems
  • TextBlob

    TextBlob is a Python library for processing textual data. It provides a simple API for diving into common natural language processing (NLP) tasks such as part-of-speech tagging, noun phrase extraction, sentiment analysis, classification, translation, and more

Image Processing

  • OpenCV

    OpenCV is a library of Image Processing bindings designed to solve computer vision problems. OpenCV-Python makes use of Numpy, which is a highly optimized library for numerical operations with a MATLAB-style syntax
  • Python Imaging Library (PIL)

    The Python Imaging Library (PIL) adds image processing capabilities to your Python interpreter. This library supports many file formats, and provides powerful image processing and graphics capabilities.

Hardware and infrastructure


    NVIDIA GPUs power millions of desktops, notebooks, workstations and supercomputers around the world, accelerating computationally-intensive tasks for consumers, professionals, scientists, and researchers
  • CUDA

    CUDA is a parallel computing platform and application programming interface (API) model created by Nvidia. It allows software developers and software engineers to use a CUDA-enabled graphics processing unit (GPU) for general purpose processing.
  • cuDNN

    The NVIDIA CUDA® Deep Neural Network library (cuDNN) is a GPU-accelerated library of primitives for deep neural networks. cuDNN provides highly tuned implementations for standard routines such as forward and backward convolution, pooling, normalization, and activation layers.
  • Virtualenv

    A great tool to create isolated Python environments. It keeps the dependencies required by different projects in separate places, by creating virtual Python environments for them.
  • redis

    Redis is an open source, in-memory data structure store, used as a database, cache and message broker. It supports data structures such as strings, hashes, lists, sets, sorted sets with range queries, bitmaps, hyperloglogs and geospatial indexes with radius queries.