cyatreya Goto Github PK

dehaze

Matlab implementation of "Single Image Haze Removal Using Dark Channel Prior"

driver-behaviour-analysis

Driver behaviour analysis using OBD data and Adaboost algorithms

driver_safety_analysis

Estimating driver safety for connected cars

ecu_datalog_analysis

Jupyter notebook containing script to read ECU data log for analysis

examples

TensorFlow examples

finbert

Financial Sentiment Analysis with BERT

generating-blog-posts-with-gpt-2-large

A walkthrough of how to generate blog posts with GPT-2 Large using Hugging Face

handson-ml2

A series of Jupyter notebooks that walk you through the fundamentals of Machine Learning and Deep Learning in Python using Scikit-Learn, Keras and TensorFlow 2.

handwritten-prescription-recognition

The Optical Character Recognition (OCR) system consists of a comprehensive neural network built using Python and TensorFlow that was trained on over 115,000 wordimages from the IAM On-Line Handwriting Database (IAM-OnDB). The neural network consists of 5 Convolutional Neural Network (CNN) layers, 2 Recurrent Neural Network (RNN) Layers, and a final Connectionist Temporal Classification (CTC) layer. As the input image is fed into the CNN layers, a non-linear ReLU function is applied to extract relevant features from the image. The ReLU function is preferred due to the lower likelihood of a vanishing gradient (which arises when network parameters and hyperparameters are not properly set) relative to a sigmoid function. In the case of the RNN layers, the Long Short-Term Memory (LSTM) implementation is used due to its ability to propagate information through long distances. The CTC is given the RNN output matrix and the ground truth text to compute the loss value and the mean of the loss values of the batch elements is used to train the OCR system. This means is fed into an RMSProp optimizer which is focused on minimizing the loss, and it does so in a very robust manner. For inference, the CTC layer decodes the RNN output matrix into the final text. The OCR system reports an accuracy rate of 95.7% for the IAM Test Dataset, but this accuracy falls to 89.4% for unseen handwritten doctors’ prescriptions.

hough_transform

A case study: line and circle detection technique using hough transform

human_activity_recognition_lrcn

image_dehaze

Single Image Haze Removal Using Dark Channel Prior

information-extraction-using-python

A notebook to understand the concept of Information Extraction using NLP techniques in Python.

kitchendashconfig

For those of you who want to see how I configured my Kitchen Dashboard.

kounya

lane-detection-hough-transform

Practical application of image processing and recognition techniques with matlab.

lane-detection-using-edge-detection

Self-driving or Autonomous driving, Advanced Driving Assistance System (ADAS) is one of the most popular topics in research related to vehicle safety. One of the most useful technologies in autonomous driving is lane detection that uses longitudinal marks (e.g. straight and dashed lines) as a reference to keep the vehicle running on lane. Various operators on edge detection are proposed to obtain the best accuracy of lane detection. However, the movement of the line marks between frames will vary depending on the speed of the vehicle. If the system fails to detect the line marker at high speed, will cause the autonomous driving system make a wrong decision. In this final task, we will perform a comparison analysis of Canny, Laplacian of Gaussian (Marr-Hildreth) and Kirsch's ability on edge detection methods to detect dashed line marks at varying speeds. The results showed that all operators succeeded in achieving the minimum detection target of 80% and obtained the best operators for line marker detection is Kirsch with the highest percentage at all speeds 30, 50 and 80 km / h.

learning-based-attack-detection-and-classification-for-controller-area-network

learning-based Attack Detection and Classification for Controller Area Network

linkedin-skill-assessments-quizzes

Full reference of LinkedIn answers 2021 for skill assessments, LinkedIn test, questions and answers (aws-lambda, rest-api, javascript, react, git, html, jquery, mongodb, java, css, python, machine-learning, power-point) linkedin excel test lösungen, linkedin machine learning test

longform-summarization-with-hugging-face

A walkthrough of how to use Hugging Face summarization pipelines for long post summarization.

models

Models and examples built with TensorFlow

natural-language-processing-python-and-nltk

Natural Language Processing Python and NLTK by Packt

neural-network-homework

Logistic regression, perception, multi-layer perception(BP), CNN filter, RNN, DBN

neural-networks

Implemented Convolutional Neural Network, LSTM Neural Network, and Neural Network From Scratch in Python Language.

nltk-trainer

Train NLTK objects with zero code

notebooks

Notebooks using the Hugging Face libraries 🤗

object-detection-and-tracking

Object Detection and Multi-Object Tracking

opencv-3.2.0-compiling-on-raspberry-pi

Download, Compile, Build, and Install OpenCV 3.2.0 with Extra Modules on RPI running Raspberry Pi OS

parrot_paraphraser

A practical and feature-rich paraphrasing framework to augment human intents in text form to build robust NLU models for conversational engines. Created by Prithiviraj Damodaran. Open to pull requests and other forms of collaboration.

practical-nlp

Official Repository for 'Practical Natural Language Processing' by O'Reilly Media