Name: Snehashis Chatterjee
Type: User
Company: University of Calcutta
Bio: I have completed my undergrad at the University of Calcutta in ECE. I have a strong interest in Deep learning, Computer vision.
Twitter: SnehashisChatt6
Location: Barasat
Snehashis Chatterjee's Projects
Python in High Performance Computing
An improved contrast enhancement method for image. :camera:
In my internship at âRAD365 Technologies Incâ, I was design various classiīŦcation and segmentation CNN models using Python Keras, Opencv, Sklearn etc. libraries. Here I implement CNN models for CT, MRI, X-RAY images.
Indicators of Attack Failure: Debugging and Improving Optimization of Adversarial Examples
Image registration is one of the prior steps for building computational model and Computer added diagnosis (CAD) which is the processes of transferring images into a common coordinate system, so that corresponding pixels represents homologous biological points. In this lab, we have familiarized with the concepts and framework of image registration based on two different transformation techniques namely ârigid transformationâ and âaffine transformationâ for brain MRI. Comparisons also have been accomplished for single-resolution and multi-resolution registration for the same images in both rigid transformation and affine transformation. Different quantitative and qualitative metric performance are also been observed for all the experiments.
normalize the intensity of several MR image contrasts with various routines
Intro to Reinforcement Learning (åŧēååĻäš įē˛čĻīŧ
C++/CUDA solutions, slides, and resources for Udacity's Intro to Computer Vision (UD810) course.
test/report the size of an IPC kernel buffer
This is the personal profile readme for....well, me!
The official repository of the ISBI 2022 KNIGHT Challenge
Code shown in the lectures
An open source library for face detection in images. The face detection speed can reach 1000FPS.
How to be low-level programmer
All course assignments/code of Machine Learning A-Z: Hands-on Python and R in Data Science.
Design a CNN based Binary classification model which classifies between normal and parasitized malaria cells. Add Class activation mapping (GRAD CAM) for better explainability of the model. Add parasitized cell detection using Tensorflow object detection API using the SSD model.
Code for "Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks"
Medical image registration related books, tutorials, papers, datasets, toolboxes and deep learning open source codes
FPGA on-device training and inference of a MLP neural network
Distributed learning with mpi4py
medical image visualization library and development toolkit