Vishal T. Profile

EXPLORAR

0,0

(0 comentarios)

Ahora estás siguiendo a

Error al seguir a usuario.

Este usuario no permite que los usuarios lo sigan.

Ya estás siguiendo a este usuario.

Tu plan de membresía solo permite 0 seguimientos. Mejora tu membresía aquí.

Dejaste de seguir correctamente a

Error al dejar de seguir al usuario.

Has recomendado exitosamente a

Error al recomendar al usuario.

Algo salió mal. Por favor, actualiza la página e intenta de nuevo.

Email verificado correctamente.

$10 USD / hora

pune,

india

$10 USD / hora

Aquí son las 4:22 a. m.

Se unió el marzo 14, 2020

0 Recomendaciones

Vishal T.

@VishalThengane

0,0

(0 comentarios)

0,0

$10 USD / hora

pune,

india

$10 USD / hora

N/A

Trabajos finalizados

N/A

Dentro del presupuesto

N/A

A tiempo

N/A

Tasa de recontratación

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.

Ver todo Python Developers en India

Contacta Vishal T. sobre tu trabajo

Inicia sesión para comentar cualquier detalle por chat.

Portafolio

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

Comentarios

Cambios guardados

¡No hay comentarios para ver aquí!

Experiencia

Smartail Pvt. Ltd

jul 2020 - Presente

- 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

sept 2019 - jun 2020 (9 meses, 1 día)

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

Nanyang Technological University Singapore

feb 2019 - ago 2019 (6 meses, 4 días)

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.

Educación

Bachelor of Technology

Swami Ramanand Teerth Marathwada University,

India

2015 - 2019

(4 años)

Publicaciones

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.