Abhijith Nair (@abhijith97)
github

abhijith97

Twitter logo Share LinkedIn logo Share Facebook logo Share
  • Stars
    star
    10
  • Global Rank 972,962 (Top 34 %)
  • Followers 27
  • Following 29
  • Registered about 9 years ago
  • Most used languages
    Python
         50.0 %
    C
         16.7 %
    Fortran
         16.7 %
    Java
         16.7 %
  • Location 🇮🇳 India
  • Country Total Rank 41,342
  • Country Ranking
    Fortran
         48
    C
         4,895

Top repositories

1

Universal-Style-Transfer

A Keras implementation of Universal Style Transfer via Feature Transforms by Li et al. The core architecture is an auto-encoder trained to reconstruct from intermediate layers of a pre-trained VGG19 image classification net. Stylization is accomplished by matching the statistics of content/style image features through the Whiten-Color Transform (WCT), which is implemented here using NumPy library. No style images are used for training, and the WCT allows for 'universal' style transfer for arbitrary content/style image pairs.
Python
4
star
2

MNET-Cerebellum

MNET Cerebellum
Python
2
star
3

Shell

A C - implementation of a basic bash-like Linux Shell
C
1
star
4

Distributed-Banking-System

A cloud infrastructure for banking with a command-line interface. It is a client-server setup developed using Java’s RMI protocol. Optimized data structures like hash tables were used to optimise the data enquiry. The system is scalable to multiple clients at different geographical locations and the communication is encrypted using Diffie Hellman key exchange protocol.
Java
1
star
5

Reflection-Removal

This project was done as the course project for the Digital Image Processing course and was mentored by Prof. Avinash Sharma. I developed a matlab implementation of the paper “Reflection removal using ghosting cues” by YiChang et al. It includes Reflection Removal using Ghosting Cues and Patch Priors which is modeled as a half Quadratic Optimization Problem.
Fortran
1
star
6

Automatic-Directory-Syncer

A python application level program to keep two separate directories synced, similar to Dropbox using low-level socket programming. The program follows a client-server architecture, actively listening to the communication channel for file transfer requests. Files and directories are transferred automatically when updated preserving the file permissions at the source directory. The file transfer incorporates checksum to handle file transfer errors. Occurrences of race conditions are prevented by cross-process file locks. Additionally, a simple, intuitive, and composable command-line interface was developed.
Python
1
star