4 days agoMember-onlyExploring Paddle-OCR: Performance on Diverse Data Formats and Multilingual TextThis blog stems from my curiosity to research the performance of Paddle-OCR, a robust and versatile optical character recognition (OCR) toolkit. Paddle-OCR offers an array of features and capabilities for extracting text from images and documents, and I was eager to explore its capabilities and limitations.Ocr4 min readOcr4 min read
Apr 27Yoga pose estimation using Openpose on Mac OSX with CPUYoga is a highly individualized practice and can be tailored to suit your specific needs and goals. …Openpose4 min readOpenpose4 min read
Published inMachine Learning & AI in Automated Map Making·Apr 18A quick and step-by-step guide to run Segment Anything Research by Meta AI on a GPU-Linux machineSegment Anything model (SAM) Keypoints: The largest segmentation dataset to date (by far), with over 1 billion masks on 11M licensed and privacy-respecting images. Promptable segmentation SAM to return a valid segmentation mask for any prompt, where a prompt can be foreground/background points, a rough box or mask, freeform text, or, in general, any…7 min read7 min read
Published inMachine Learning & AI in Automated Map Making·Mar 21Advancement of Paddle-OCR over time-An excellent AblationMy thoughts on building an OCR system — In the past 6 years, I have got opportunities to work on more than 4 OCR projects. I have been constantly working on the OCR modules when it all began first in the industry and now when OCR systems are so much more advanced and capable. The data formats I…Ocr12 min readOcr12 min read
Feb 14, 2022Detectron2 evaluation COCO Evaluator Test AP of your detectron2 Mask-RCNN models in a minuteSharing the code and line by line explanation of what you can do to evaluate your detectron2 model using coco evaluation metrics. Create your detectron2 instance segmentation custom configuration using the below code: Save the model when the training begins with this code: Run COCO Evaluator after training on your custom test dataset:Coco Dataset1 min readCoco Dataset1 min read
Jan 11, 2022GitLab commands for beginners and everyday usersSay Yes to simplifying education You have been given a new project and here are a few tasks which you are expected to do: Download the production repository on your machine Make code changes in the code present in the repository Push your code changes to the cloud in the same repository Create a code…Gitlab6 min readGitlab6 min read
Aug 31, 2021How to run Spyder with anaconda on macOSIntroduction The scope of this blog is to help the reader run Spyder with an anaconda environment on macOS in 5 minutes. Please follow the below steps sequentially and you will be ready to code and debug your project in Spyder. What is Spyder? Spyder is a free and open-source scientific environment written in…Spyder5 min readSpyder5 min read
Aug 27, 2021What is Geospatial data and basics about getting started with geospatial data analysisWhat is Geospatial data? Geospatial data is data about objects, events, or phenomena that has a location on the earth's surface. It is data that has a geographic aspect to it. Geospatial data combines location information (usually coordinates on the earth), attribute information (the characteristics of the object, event, or phenomena concerned), and often…Geospatial17 min readGeospatial17 min read
Aug 10, 2021Step by step guide to training Detectron2 detection models on GPU -Part 1Introduction This blog series is divided into four parts, Part 1- The first part is about setting up the docker container for detectron2. Part 2- Part two is about an open-source tool called labelme to label training images for detection Part 3- Part three is about creating a dataset as per…Detectron215 min readDetectron215 min read
Sep 5, 2020Step by step -Understand the architecture of Region proposal network (R-CNN)Introduction This blog is written to explain the evolution of object detection models in simple words and self-explanatory diagrams. …R Cnn9 min readR Cnn9 min read
