ShahariarRabby
One of my greatest strengths is my ability to make the conceptual practical to computer program. My goal is to make a computer that will able to see and talk.
The University of Alabama at Birmingham & Apurba TechnologiesAL, USA
Pinned Repositories
Archer-c5-v4-Firmware
This repo was created specifically for the Archer C5 v4 which uses a MediaTek SoC. This is a Dual band router with 5 Gigabit (1000Mbps) ethernet ports and a single USB2 port. It is advertised as AC1200 for its 867Mbps (2×2) 5GHz band and 300 Mbps (2×2) 2.4GHz band. There is also a 'C5 W v4' offered in some countries such as Brazil.
Bangla_Digit_Recognition_CNN
Bangla Handwritten Digit Recognition using Convolutional Neural Network
Blynk-Home-Automation
Controlling the lights in your house using your voice is a great way to dip your toes into the smart homeworld. And if you already have a smartphone you can build your own smart switch using a few bucks.
CarND_Capstone
A team project to build a self-driving car with the ROS framework. Capstone Project of Udacity's Self-Driving Car Engineer Nanodegree Program.
deeplearning.ai
deeplearning.ai , By Andrew Ng, All video link
Ekush
EkushNet
EkushNet is the first research which can recognize Bangla handwritten basic characters, digits, modifiers, and compound characters. Handwritten recognition is one of the most interesting issue in present time due to its variant applications and help to make the old form and information digitization and reliable.
GYMX
The use of online gymnasium management system is little bit difficult to handle. With GYMX it can be digitized and overcome challenges. http://gymx.ga
Mnist_cnn_Swish
I have a Keras ReLU model that score 0.99457 on kaggle submission. I choose that model and Change all the ReLU activation to Swish. That model achieve 0.99671 .
shahariarrabby.github.io
My portfolio website. https://shahariarrabby.github.io
ShahariarRabby's Repositories
ShahariarRabby/shahariarrabby.github.io
My portfolio website. https://shahariarrabby.github.io
ShahariarRabby/BreastUltrasoundImageClassificationDocker
A web-based application for classifying breast ultrasound images into benign, malignant, or normal categories. Built with Flask for the web interface and TensorFlow for image classification. Dockerized for easy deployment and consistent environments. Includes comprehensive documentation, sample images, and a demonstration video
ShahariarRabby/adv_web
ShahariarRabby/AW-Net
[ICCVw 2023] "AW-Net: A Novel Fully Connected Attention-based Medical Image Segmentation Model" by Debojyoti Pal, Tanushree Meena, Dwarikanath Mahapatra, and Sudipta Roy.
ShahariarRabby/awesome-NeRF
A curated list of awesome neural radiance fields papers
ShahariarRabby/cat-sam
[ECCV 2024 Oral] The official implementation of "CAT-SAM: Conditional Tuning for Few-Shot Adaptation of Segment Anything Model".
ShahariarRabby/chatgpt-web
ChatGPT web interface using the OpenAI API
ShahariarRabby/CLIP
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
ShahariarRabby/CS_621Q_assignments
ShahariarRabby/CSBSR
Official PyTorch implementation of the paper "Joint Learning of Blind Super-Resolution and Crack Segmentation for Realistic Degraded Images", IEEE Transactions on Instrumentation and Measurement (TIM) 2024. CSBSR is an advanced version of our previous work CSSR [MVA'21].
ShahariarRabby/csc-app-lung-lobe
App for segmentation of Lung Lobes and Lesions for severity classification of COVID-19 CT Scans
ShahariarRabby/data.csv
ShahariarRabby/Enhancing-Segment-Anything-using-Few-Shot-Learning
Presenting a novel yet simple system that extends SAM’s segmentation capabilities by automatically picking the correct segmentation mask. The approach leverages the power of few-shot learning (FSL) methods coupled with an Out-of-Distribution (OOD) threshold strategy.
ShahariarRabby/Fetch-Rewards-ARIMA-model-API
ShahariarRabby/fissure-segmentation
Keypoint-based lung fissure segmentation with Geometric Convolutional Networks (Master's Thesis)
ShahariarRabby/Grounded-SAM-2
Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2
ShahariarRabby/InternVL
[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的可商用开源多模态对话模型
ShahariarRabby/lang-segment-anything
SAM with text prompt
ShahariarRabby/local-rag-example
Build your own ChatPDF and run them locally
ShahariarRabby/MaxViT-UNet
Official implementation of "MaxViT-UNet: Multi-Axis Attention for Medical Image Segmentation" in MMSegmentation Framework.
ShahariarRabby/netron
Visualizer for neural network, deep learning and machine learning models
ShahariarRabby/NextDNS-Config
Setup guide for NextDNS, a DoH proxy with advanced capabilities
ShahariarRabby/photography-portfolio
📷 A Website created using Tailwind CSS, HTML, CSS and JavaScript that can be used as a Photographer Portfolio.
ShahariarRabby/resume-chatbot-local-llm
Playing with RAG using Ollama, Langchain, and Streamlit. This project aims to demonstrate how a recruiter or HR personnel can benefit from a chatbot that answers questions regarding candidates.
ShahariarRabby/SAM-finetune
Finetune SegmentAnything for Road Segmentation
ShahariarRabby/sam-unet
sam-unet
ShahariarRabby/transparency-data
U.S. Healthcare Transparency Data. Supplemental data for the CMS/HHS price transparency rules.
ShahariarRabby/unet
U-Net Biomedical Image Segmentation
ShahariarRabby/vnet-tensorflow
Implementation of vnet in tensorflow for medical image segmentation
ShahariarRabby/Window-Constraint-for-Broken-Mac-Screen
A Hammerspoon configuration script that helps users confine application windows to a usable portion of an iMac’s screen. This is especially useful for those with partially broken or damaged iMac displays who need to restrict window placement to the functional area of their screen.