Command-line Tools

CommonMark compliant Markdown formatter with python

Mdformat Mdformat is an opinionated Markdown formatter that can be used to enforce a consistent style in Markdown files. Mdformat is a Unix-style command-line tool as well as a Python library. Installing Install with CommonMark support: pip install mdformat Alternatively install with GitHub Flavored Markdown (GFM) support: pip install mdformat-gfm Or with Markedly Structured Text (MyST) support: pip install mdformat-myst Command line usage Format files Format files README.md and CHANGELOG.md in place mdformat README.md CHANGELOG.md Format .md files in current […]

Read more
Python

Python Basics: Paperback Now Available!

After years of writing, reviewing, and testing, we’re delighted to announce that Python Basics: A Practical Introduction to Python 3 is now available in paperback! It’s been rewarding to hear how readers have been using this book to supercharge their learning. After receiving so much community feedback, we’re confident that you’ll build a strong foundation for your Python journey with this book: You’ll not only cover the core concepts you really need to know, but you’ll also learn them in […]

Read more
NLP

MLOps Primer – 2021

Machine learning operations (MLOps) is becoming an exciting space as we figure out the best practices and technologies to deploy machine learning models in the real world. MLOps enable ML teams to build responsible and scalable machine learning systems and infrastructure. This facilitates tasks that range from risk assessment to building and testing to monitoring. While still in its infancy, MLOps has attracted machine learning engineers and software engineers in general. With every new paradigm comes new challenges and opportunities […]

Read more
Neural Machine Translation (NMT), NMT Leave a comment

Machine Translation Weekly 76: Zero-shot MT with pre-trained encoder

Using pre-trained multilingual representation as a universal encoder for machine translation might seem like an obvious thing to try: train a decoder into one target language using one or several source languages and you get a translation from 100 languages into the target language. This sounds great, but this is not how it works. (Or it works somehow, but not really well, I tried it myself.) Recently, I came across a pre-print where the authors figured out how to do […]

Read more
Natural Language Processing

A software toolkit for weak supervision applied to NLP tasks

skweak Labelled data remains a scarce resource in many practical NLP scenarios. This is especially the case when working with resource-poor languages (or text domains), or when using task-specific labels without pre-existing datasets. The only available option is often to collect and annotate texts by hand, which is expensive and time-consuming. skweak (pronounced /skwi:k/) is a Python-based software toolkit that provides a concrete solution to this problem using weak supervision. skweak is built around a very simple idea: Instead of […]

Read more
Machine Learning

Learning Calibrated-Guidance for Object Detection in Aerial Images

CG-Net This codebase is created to build benchmarks for object detection in aerial images. It is modified from mmdetection. The master branch works with PyTorch 1.1 or higher. If you would like to use PyTorch 0.4.1, please checkout to the pytorch-0.4.1 branch. Results Visualization results for oriented object detection on the test set of DOTA. Comparison to the baseline on DOTA for oriented object detection with ResNet-101. The figures with blue boxes are the results of the baseline and pink […]

Read more
Command-line Tools

A scriptable stream downloader for Qobuz, Tidal, Deezer and SoundCloud

streamrip A scriptable stream downloader for Qobuz, Tidal, Deezer and SoundCloud. Features Super fast, as it utilizes concurrent downloads and conversion Downloads tracks, albums, playlists, discographies, and labels from Qobuz, Tidal, Deezer, and SoundCloud Supports downloads of Spotify and Apple Music playlists through last.fm Automatically converts files to a preferred format Has a database that stores the downloaded tracks’ IDs so that repeats are avoided Easy to customize with the config file Installation First, ensure pip is installed. Then run […]

Read more
Framework

A fast and robust LiDAR point cloud panoptic segmentation framework

Panoptic-PolarNet This is the official implementation of Panoptic-PolarNet. Panoptic-PolarNet is a fast and robust LiDAR point cloud panoptic segmentation framework. We learn both semantic segmentation and class-agnostic instance clustering in a single inference network using a polar Bird’s Eye View (BEV) representation. Predictions from the semantic and instance head are then fused through a majority voting to create the final panopticsegmentation. We test Panoptic-PolarNet on SemanticKITTI and nuScenes datasets. Experiment shows that Panoptic-PolarNet reaches state-of-the-art performances with a real-time inference […]

Read more
Machine Learning

Simple Contrastive Learning of Sentence Embeddings

SimCSE We propose a simple contrastive learning framework that works with both unlabeled and labeled data. Unsupervised SimCSE simply takes an input sentence and predicts itself in a contrastive learning framework, with only standard dropout used as noise. Our supervised SimCSE incorporates annotated pairs from NLI datasets into contrastive learning by using entailment pairs as positives and contradiction pairs as hard negatives. The following figure is an illustration of our models. Use our models out of the box Our pre-trained […]

Read more
1 … 652 653 654 655 656 … 919