Discover @MZayed47 Open Source projects

Mashrukh Zayed (@MZayed47)

MZayed47

Stars
19
Global Rank 661,842 (Top 23 %)
Followers 6
Following 1
Registered over 7 years ago
Most used languages

Python
60.0 %

Jupyter Notebook
30.0 %

C++
10.0 %
Location 🇧🇩 Bangladesh
Country Total Rank 3,385
Country Ranking

Jupyter Notebook
289

Python
377

C++
1,462

Bangla-License-Plate-Recognition

This repository contains my ongoing project on "Bangla License Plate Recognition using YOLOv4 & PyTesseract". YOLOv4 algorithm is used for the Detection part, then PyTesseract is used for the recognition part. Further work is in progress.

DDPG_Agent

Deep Deterministic Policy Gradient (DDPG) is a model-free off-policy algorithm for learning continuous actions. It is a reinforcement learning technique that combines ideas from DPG (Deterministic Policy Gradient) and DQN (Deep Q-Network). From DQN, it uses Experience Replay and Slow-learning target networks. From DPG, it incorporates Operating over continuous action spaces.

Jupyter Notebook

Real_time_OD_webcam_dashcam

This project is a part of my ongoing research work on “Real-Time On-Road Vehicle Detection and Distance Estimation”. For this project, I have used the YOLOv4 algorithm (published in April 2020) which is considered the fastest and most accurate version of YOLO.

Object_Detection_using_YOLOv3

This project is a part of my second research work on “Real-Time Detection and Recognition of traffic signs in Bangladesh using YOLOv3 Detector”. I used Keras library to build the YOLOv3 model from scratch and loaded it with a pre-trained weight file. Then I used both Keras and TensorFlow to load the model and detect several classified objects in images.

A3C_Agent

The Asynchronous Advantage Actor Critic (A3C) algorithm is one of the newest algorithms to be developed under the field of Deep Reinforcement Learning Algorithms. This algorithm was developed by Google’s DeepMind which is the Artificial Intelligence division of Google. In this repository, I have my implementations of A3C on Cartpole game, Robot arm, etc.

Multi-Agent-BC-Study

This repository holds my study and understanding on the applications of Multi Agent Behavior Cloning in real world problems.

Handwritten_Bangla_Character_Recognition

This research work aimed to develop a handwritten character recognition model using a deep convolutional neural network and analyze the three complete datasets: BanglaLekha Isolated, CMATERdb, and Ekush and get significant accuracies for all the character classes, considering the maximum number of samples they have. The aim was to improve the basic structure of OCR based identification of documents and exam papers for the educational institutes with Bangla medium.

Jupyter Notebook

SQIL_Immitation_Learning

In this piece of work, I have implemented Soft Quality Imitation Learning (SQIL) on Cartpole game environment. Now I'm trying to implement the algorithm on VizDoom Game Environment. It's still in progess.

Signature_Validator_GABOR

This repository contains my project on "Handwritten Signature Validation using GABOR Transform method". Few versions of a signature is first registered and stored in database. Then any signature is matched with a signature registered in the database.

CS-GO_KD-Classifier

This classification task is specifically dependent on a video dataset that includes video clips of kill and death scenes from the first-person shooting game “CS Go”. I have used the ResNet-50 model for image classification and then turn it into a more accurate video classifier by employing the rolling averaging method.

Jupyter Notebook