Author: Deep Learner

Machine Learning

Exploring Hybrid CNN-transformers with Block-wisely Self-supervised Neural Architecture Search

BossNAS This repository contains PyTorch code and pretrained models of our paper: BossNAS: Exploring Hybrid CNN-transformers with Block-wisely Self-supervised Neural Architecture Search. Illustration of the fabric-like Hybrid CNN-transformer Search Space with flexible down-sampling positions. Our Results and Trained Models Here is a summary of our searched models: Model MAdds Steptime Top-1 (%) Top-5 (%) Url BossNet-T0 w/o SE 3.4B 101ms 80.5 95.0 checkpoint BossNet-T0 3.4B 115ms 80.8 95.2 checkpoint BossNet-T0^ 5.7B 147ms 81.6 95.6 same as above BossNet-T1 7.9B 156ms […]

Read more
Machine Learning

Jetson Nano-based smart camera system that measures crowd face mask usage in real-time

MaskCam MaskCam is a prototype reference design for a Jetson Nano-based smart camera system that measures crowd face mask usage in real-time, with all AI computation performed at the edge. MaskCam detects and tracks people in its field of view and determines whether they are wearing a mask via an object detection, tracking, and voting algorithm. It uploads statistics (not videos) to the cloud, where a web GUI can be used to monitor face mask compliance in the field of […]

Read more
Command-line Tools

Run context-aware commands from your source code comments

codeline Codeline allows you to run custom commands directly from source-code comments, combining the power of IDE extensions with the expressiveness of the command-line. Installation git clone https://github.com/synek/codeline.git poetry install Development Codeline can monitor the current directory for file-changes, and then run any commands it finds:poetry run codeline –watch . Alternatively you can run Codeline on a single file, executing any commands the file and then exiting.poetry run codeline –run path/to/python/file.py To build a command, copy the plugins/test_plugin as a […]

Read more
Command-line Tools

Transforming the classic Command-Line Interface

Magic Carpet Magic Carpet is an infrastructure as code and network automation tool that transforms CLI command and REST API data, using the Cisco Genie parsers, the Cisco pyATS Python library, and Python to automatically generate, at scale, better documentation from the output; send #chatbots; #voicebots; even #phonebots! Getting Started Requirements (instructions below) Virtual Environment We recommend running Magic Carpet in a Python virtual environment while testing or developing. This will help keep your host system clean and allow you […]

Read more
GUI

A graphical user interface built using Dear PyGui Python GUI Framework

MultiPy MultiPy is a graphical user interface built using Dear PyGui Python GUI Framework that lets you conveniently keep track of your python scripts for personal use or showcase by loading and grouping them into categories. It allows you to either run each script individually or together with just one click. You can choose a name for your categories and scripts, indicate whether your script requires a virtual environment to run and select the virtual environment you need, choose whether […]

Read more
Data Visualization

Resources for teaching & learning practical data visualization with python

Practical Data Visualization with Python This repository contains all materials related to a lecture / seminar I teach on practical data visualization with python. What I mean by “practical” is that the materials herein do not focus on one particular library or data visualization method; rather, my goal is to empower the consumer of this content with the tools, heuristics, and methods needed to handle a wide variety of data visualization problems. If you have questions, comments, or suggested alterations […]

Read more
Machine Learning

MLOps tool for deploying machine learning projects to Kubernetes

bodywork-core Bodywork deploys machine learning projects developed in Python, to Kubernetes. It helps you: serve models as microservices execute batch jobs run reproducible pipelines On demand, or on a schedule. It automates repetitive DevOps tasks and frees machine learning engineers to focus on what they do best – solving data problems with machine learning. Where does Bodywork Fit? Bodywork is aimed at teams who want to deploy machine learning projects in containers. It will deliver your project’s Python modules directly […]

Read more
Beginner, NLP, Python, Technique, Text, Unsupervised

A Simple Guide to Metrics for Calculating String Similarity

Introduction One of the applications of Natural Language Processing is auto-correction and spellings checks. All of us have encountered this that if we type an incorrect or typo in the Google search engine, then the engine automatically corrects it and suggests the right word in its place. How does the engine do that? How does it know what word we wanted to write or ask? That is what we will be covering in this article. The methods available to check […]

Read more
Beginner, Deep Learning, NLP

Role of Machine Learning in Natural Language Processing

Introduction Machine Learning and Natural Language Processing are important subfields of Artificial Intelligence that have gained prominence in recent times. Machine Learning and Natural Language Processing play a very important part in making an artificial agent into an artificial ‘intelligent’ agent. An Artificially Intelligent system can accept better information from the environment and can act on the environment in a user-friendly manner because of the advancement in Natural Language Processing. Similarly, an Artificially Intelligent System can process the received information […]

Read more
1 … 700 701 702 703 704 … 973