amzadhossainrafis Goto Github PK

amzadhossainrafis

Amzad's portfolio

amzadhossainrafis.github.io

conway-s_game_of_life_simulation-

data_visualization

deep-learning-coursera

Deep Learning Specialization by Andrew Ng on Coursera.

denoiser_encoder-with-dncnn

this project is created based on state of the art model Dncnn . This is a simple implementation of image denoising

diffusion__

dncnnv

This is a PyTorch implementation of DNCnn(modified) for image denoising and deblurring. Dncnn is a deep convolutional neural network for image denoising. It is a fully convolutional network with residual learning and batch normalization.

droneimage-segmentation

This is a PyTorch-based project for drone image segmentation. The goal of this project is to segment objects and regions of interest within aerial images captured by drones. Image segmentation is a crucial task in computer vision and has various applications, including agriculture, urban planning, and environmental monitoring.

emailo-email

flask-web-templates

fuel-economy-data-analysis

fun_3d_scanner-

This is an university fun project . :P main perpose of this project is to create and prototype that only try to scan any object(not so big ) by using ir distance sensor any try to plot it in 3d dimension space

gan_s

git_profile

idc-classification

image-segmentation

Semantic segmentation is a type of computer vision technique that assigns a label to every pixel in an image. The label indicates the class of object that the pixel represents. Semantic segmentation is used in tasks such as self-driving cars, where it is important to know not only the boundaries of objects, but also what those objects are.

image_classification_pipeline

The main goal of this project is to create an image classification pipeline in Keras using several models and to walk you through all of the necessary steps in Keras to create a good and accurate model. This model can be utilized for both binary and multi-class classification. This project explains how to use Keras to train a model, including how to design different types of models, how to integrate transfer learning, how to prepare a data set for training, data augmentation, a data loader/data generetor, and how to visualize the results.how to handel and use build in callback fucntions, Compare the outcomes, learn how to use custom metric, how to reduce the traing time with keras mixed precision and more. In a simple word this pipeline contain all the importent aspet of keras for imagae clssification

insar-coding

practice code with project file

my_portfolio

news_classification

The main goal of this project is to make a simple news keyword classifier. The classifier will be trained on a dataset of news articles and their respective keywords. The classifier will then be able to classify a news article into one or more keywords.

ocr-ssl

performer

personal-protective-gear-surveillance-system

In this present world where a great pandemic is going on which is spreading rapidly from one man to another man at present more than 88,668,711 people are currently infected and including 1,884,341 deaths the of the infection is increasing day by day the infected rate is increasing .In average .. people are effected by this virous and many well developed countries like USA, England are facing huge problems to maintain the infected rete in control. But matter to be noted that developing countries like Bangladesh ,India, Pakistan where the population is far more than the developed country where people live by day to day earning, It is not quaite possible to keep people inside their house. Keeping those thing in our mind we tried to developed a surveillance system that are trained in image using effective algorithm like YOLOv4 ,mobilenetV2,YOLO-tiny(ligh weight also mobile detection supported) with mask , with out mask ,gloves on face shield and PPE(personal protective equivalents ) monitor general people in public places also notify not only that also count the actual detection and take picture of those people who is not wearing mask properly or on mask at all we also use deepsort method to count the the actual number of the detection and store it in for farther statistical analysis

predictoo

Predictoo is a python package which allows to predict the future of a time series.Predictoo contain 10 deep learning model .It is a tool for producing high quality forecasts for time series data that has multiple seasonality with linear or non-linear growth. It is based on an additive model where non-linear trends are fit with yearly and weekly .

project2

pygame

This is a straightforward university assignment based on undergraduate courses. The primary goal of this project is to depict the fundamental concepts of Python programming while also being acquainted with some Python modules (pygame).

pythorch.lightning-

pl.lightning

resume-classifier

semantic-segmentation-of-aerial-satellite-imagery-using-u-net