Vishal T. Profile

EXPLORE

0.0

(0 reviews)

You're now following

Error following user.

This user does not allow users to follow them.

You are already following this user.

Your membership plan only allows 0 follows. Upgrade here.

Successfully unfollowed

Error unfollowing user.

You have successfully recommended

Error recommending user.

Something went wrong. Please refresh the page and try again.

Email successfully verified.

$10 USD / hour

pune,

india

$10 USD / hour

It's currently 4:42 AM here

Joined March 14, 2020

0 Recommendations

Vishal T.

@VishalThengane

0.0

(0 reviews)

0.0

$10 USD / hour

pune,

india

$10 USD / hour

N/A

Jobs Completed

N/A

On Budget

N/A

On Time

N/A

Repeat Hire Rate

Machine Learning and Computer Vision Engineer

I have a good grasp on programming languages like python, C++, and Java. I have done work in applying machine learning and NLP algorithms for handwritten text recognition, Image denoising, image generation, text completion, object detection and localization, image segmentation, Q&A prediction using frameworks like PyTorch, TensorFlow, Keras, Caffe and put into production using Flask, Docker and AWS.

See all Python Developers in India

Contact Vishal T. about your job

Portfolio

I implemented the LSTM and attention-based time series forecasting model for multivariate data, using TensorFlow and Keras.

LSTM and attention based time series datat prediction

Implemented transformer-based time-series prediction model.

Time series data prediction using transformer

LSTM and attention based time series datat prediction

Time series data prediction using transformer

Reviews

Changes saved

No reviews to see here!

Experience

Smartail Pvt. Ltd

Jul 2020 - Present

- Working on DeepGrade app which uses AI to grade handwritten papers. - Working on a Transformer based handwritten text recognition model. - The denoising of handwritten paper done by using CycleGAN. - For the Quiz correction, we are using BERT language model.

Nanyang Technological University Singapore

Sep 2019 - Jun 2020 (9 months, 1 day)

Worked on the context based human action prediction using generative adversarial network.

Nanyang Technological University Singapore

Feb 2019 - Aug 2019 (6 months, 4 days)

Worked on domain adaptation for nighttime vehicle classification. The classification in the night-time is done by adapting model trained on day-time scenes in a unsupervised domain for large scale unlabeled dataset. We used SqueezeNet model, it produces 50 times fewer parameter and it has less than 0.5MB model size which is easy to deploy on limited memory hardware. We used PyTorch framework for our project.

Education

Bachelor of Technology

Swami Ramanand Teerth Marathwada University,

India

2015 - 2019

(4 years)

Publications

Document Segmentation and Language Translation Using Tesseract-OCR

IEEE

Document segmentation and Translation are one of the key areas in pattern recognition and natural language processing. This paper presents details about translation in terms of a web application that accepts image document as an input, where input document is a user define image file containing text in any language available in the Python-tesseract library and does its exact translation in any supported languages using Google Translator (i.e Googletrans).

Cycle Face Aging Generative Adversarial Networks

Institute of Electrical and Electronics Engineers (IEEE)

We introduce a Cycle Face Aging Generative Adversarial Network (CFA-GANs) framework which preserves original face identity in the aged version of his/her face. Due to the shortage of paired data of human faces, we used CycleConsistent Generative Adversarial Network (CycleGANs) which transform an image from source domain X to target domain Y in absence of paired example.