Sai Ram K. Profile

5.0

(1 review)

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.

$25 USD / hour

kharagpur,

india

$25 USD / hour

It's currently 7:28 AM here

Joined August 3, 2015

0 Recommendations

Sai Ram K.

@supersai007

5.0

(1 review)

0.0

100%

$25 USD / hour

kharagpur,

india

$25 USD / hour

100%

Jobs Completed

100%

On Budget

100%

On Time

N/A

Repeat Hire Rate

Deep learning Expert

Hey, If you are looking for deep learning experts for image object classification and recognition tasks, here I am. I have worked on varied CV tasks on deep neural nets on Pytorch library and published papers too.

See all Python Developers in India

Contact Sai Ram K. about your job

Reviews

Changes saved

Showing 1 - 1 out of 1 reviews

Filter reviews by:

5.0

€8.00 EUR

Data science/ML tutoring

Sai is reliable and knowledgeable in his domain. He has expertise on deep learning/convolutional neural networks and also gives good advice on how to approach a machine learning problem, will definitely work with him again. Thanks!

Python

Machine Learning (ML)

Data Science

Wenting J.

@avocano2019

•

5 years ago

Education

MS by Research

Indian Institute of Technology, Kharagpur,

India

2015 - 2018

(3 years)

B.Tech

Indian Institute of Technology, Kharagpur,

India

2010 - 2014

(4 years)

Publications

HSD-CNN: Hierarchically self decomposing CNN using class specific filter sensitivity analysis

ACM ICVGIP

An efficient way to convert large many-class pre-trained networks into small few-class networks is through a hierarchical decomposition of its feature maps. To alleviate this issue, an automated framework for such decomposition in Hierarchically Self Decomposing CNN (HSD-CNN), is proposed in four steps.

Video Based Person Reid by Re-Ranking Attentive Temporal Information in Deep Recurrent CNNs

IEEE International Conference on Image Processing (ICIP)

Person Re-identification is a crucial task in visual surveillance and human-computer interaction. Deep learning approach for video based person re-id is presented. We use ResNet along with LSTM for feature extraction. The extracted feature is passed through an attentive temporal pooling layer, which enables the feature extractor to be aware of the current input video sequences. we re-rank the result using k-reciprocal encodin to mitigate the effect of false matching