Posts

Subject Sentiment Analysis CODE for Twitter

Image
Why Sentiment Analysis ? Millions of messages are appearing daily in popular web-sites that provide services for microblogging such as Twitter , Tumblr , Facebook . Authors of those messages write about their life, share opinions on variety of topics and discuss current issues. Because of a free format of messages and an easy accessibility of microblogging platforms, Internet users tend to shift from traditional communication tools (such as traditional blogs or mails) to microblogging services. As more and more users post about products and services they use, or express their political and religious views, microblogging web-sites become valuable sources of people’s opinions and sentiments. Such data can be efficiently used for marketing or social studies. Source : you can follow this project on my GIthub . -->Click Here<-- "This is sample project to analyze sentiments based on particular subject" We would like to add Facebook Sentiment Analysis based
5 comments
Read more

Making Of A Virtual Self Driving Car

Image
Making of A Virtual Self-Driving Car As many companies are spending millions of dollars for testing their algorithm for self driving car. It would be cost efficient if we used virtual environment for testing of self driving car . I am machine learning  enthusiast, so self driving car problem is heart of it right now. Took many references from NVIDA's self driving , mudassir repository on self driving and Udacity's nano degree program. Made this project for my college as minor project in 6th semester. Got O grade and 10 GPA for the subject. Virtual Environment: The first requirement for making a Virtual Self-Driving Car is a simulator. I used  Udacity’s simulator  in my project. It is a great tool, it has multiple tracks and an easy API to send throttle, brake and steering controls to the car. Udacity Simulator (credits: Udacity) The Brains: In order to teach a virtual car how to drive, I took the  deep learning  approach. Specifically, I trained a  convolut
2 comments
Read more

virtual mouse and keyboard

virtual mouse and keyboard Won second prize for this project at hackthon event conducted by SRM texus which included cash prize .Thanks to dibakar saha for inspiration.To check repository for this project CLICK HERE Virtual Keyboard A simple virtual keyboard created using OpenCV and Python which has 26 alphabets and a space bar. What have I done The secret here is the area of the yellow paper I am wearing on my fingers. When I bring the paper near to the camera, the area of the paper as seen by the camera increases. When it is moved back the, the area of the paper as seen by the camera decreases. This is the simple idea that I have used to detect the click. The position of the click determines the key press that is to be simulated. The keyboard creation is a bit complicated process. I hope that the code will be able to explain it. Requirements PyAutoGui OpenCV 3 Usage First run the range-detector.py to set the range for the mask for colour segmentation. The easies
Post a Comment
Read more

Getting Started with YOLO object detection with sample code and detection

Image
Intro You only look once (YOLO) is a system for detecting objects on the  Pascal VOC  2012 dataset. It can detect the 20 Pascal object classes: person bird, cat, cow, dog, horse, sheep aeroplane, bicycle, boat, bus, car, motorbike, train bottle, chair, dining table, potted plant, sofa, tv/monitor YOLO is joint work with  Santosh ,  Ross , and  Ali , and is described in detail in our  paper . How it works All prior detection systems repurpose classifiers or localizers to perform detection. They apply the model to an image at multiple locations and scales. High scoring regions of the image are considered detections. We use a totally different approach. We apply a single neural network to the full image. This network divides the image into regions and predicts bounding boxes and probabilities for each region. These bounding boxes are weighted by the predicted probabilities. Finally, we can threshold the detections by some value to only see high scoring detections:
1 comment
Read more