- On-Device Deep Learning: PyTorch Mobile and TensorFlow Lite - Nov 22, 2021.
PyTorch and TensorFlow are the two leading AI/ML Frameworks. In this article, we take a look at their on-device counterparts PyTorch Mobile and TensorFlow Lite and examine them more deeply from the perspective of someone who wishes to develop and deploy models for use on mobile platforms.
- Deep Learning on your phone: PyTorch C++ API for use on Mobile Platforms - Nov 12, 2021.
The PyTorch Deep Learning framework has a C++ API for use on mobile platforms. This article shows an end-to-end demo of how to write a simple C++ application with Deep Learning capabilities using the PyTorch C++ API such that the same code can be built for use on mobile platforms (both Android and iOS).
- Advanced PyTorch Lightning with TorchMetrics and Lightning Flash - Nov 1, 2021.
In this tutorial we will be diving deeper into two additional tools you should be using: TorchMetrics and Lightning Flash. TorchMetrics unsurprisingly provides a modular approach to define and track useful metrics across batches and devices, while Lightning Flash offers a suite of functionality facilitating more efficient transfer learning and data handling, and a recipe book of state-of-the-art approaches to typical deep learning problems.
- Getting Started with PyTorch Lightning - Oct 26, 2021.
As a library designed for production research, PyTorch Lightning streamlines hardware support and distributed training as well, and we’ll show how easy it is to move training to a GPU toward the end.
- The 20 Python Packages You Need For Machine Learning and Data Science - Oct 14, 2021.
Do you do Python? Do you do data science and machine learning? Then, you need to do these crucial Python libraries that enable nearly all you will want to do.
- Building Multimodal Models: Using the widedeep Pytorch package - Oct 13, 2021.
This article gets you started on the open-source widedeep PyTorch framework developed by Javier Rodriguez Zaurin.
- AutoML: An Introduction Using Auto-Sklearn and Auto-PyTorch - Oct 11, 2021.
AutoML is a broad category of techniques and tools for applying automated search to your automated search and learning to your learning. In addition to Auto-Sklearn, the Freiburg-Hannover AutoML group has also developed an Auto-PyTorch library. We’ll use both of these as our entry point into AutoML in the following simple tutorial.
- Introduction to PyTorch Lightning - Oct 4, 2021.
PyTorch Lightning is a high-level programming layer built on top of PyTorch. It makes building and training models faster, easier, and more reliable.
- A Breakdown of Deep Learning Frameworks - Sep 23, 2021.
Deep Learning continues to evolve as one of the most powerful techniques in the AI toolbox. Many software packages exist today to support the development of models, and we highlight important options available with key qualities and differentiators to help you select the most appropriate for your needs.
- Overview of Albumentations: Open-source library for advanced image augmentations - Jul 22, 2021.
With code snippets on augmentations and integrations with PyTorch and Tensorflow pipelines.
- High-Performance Deep Learning: How to train smaller, faster, and better models – Part 5 - Jul 16, 2021.
Training efficient deep learning models with any software tool is nothing without an infrastructure of robust and performant compute power. Here, current software and hardware ecosystems are reviewed that you might consider in your development when the highest performance possible is needed.
- What makes a winning entry in a Machine Learning competition? - May 5, 2021.
So you want to show your grit in a Kaggle-style competition? Many, many others have the same idea, including domain experts and non-experts, and academic and corporate teams. What does it take for your bright ideas and skills to come out on top of thousands of competitors?
- The Most In-Demand Skills for Data Scientists in 2021 - Apr 15, 2021.
If you are preparing to make a career as a Data Scientist or are looking for opportunities to skill-up in your current role, this analysis of in-demand skills for 2021, based on over 15,000 Data Scientist job postings, should offer you a good idea as to which programming languages and software tools are increasing and decreasing in importance.
- Multilingual CLIP with Huggingface + PyTorch Lightning - Mar 26, 2021.
An overview of training OpenAI's CLIP on Google Colab.
- Getting Started with Distributed Machine Learning with PyTorch and Ray - Mar 3, 2021.
Ray is a popular framework for distributed Python that can be paired with PyTorch to rapidly scale machine learning applications.
- Speech to Text with Wav2Vec 2.0 - Mar 2, 2021.
Facebook recently introduced and open-sourced their new framework for self-supervised learning of representations from raw audio data called Wav2Vec 2.0. Learn more about it and how to use it here.
- Hugging Face Transformers Package – What Is It and How To Use It - Feb 16, 2021.
The rapid development of Transformers have brought a new wave of powerful tools to natural language processing. These models are large and very expensive to train, so pre-trained versions are shared and leveraged by researchers and practitioners. Hugging Face offers a wide variety of pre-trained transformers as open-source libraries, and you can incorporate these with only one line of code.
- Build Your First Data Science Application - Feb 4, 2021.
Check out these seven Python libraries to make your first data science MVP application.
- Computer Vision at Scale With Dask And PyTorch - Nov 23, 2020.
A tutorial on conducting image classification inference using the Resnet50 deep learning model at scale with using GPU clusters on Saturn Cloud. The results were: 40x faster computer vision that made a 3+ hour PyTorch model run in just 5 minutes.
- 5 Most Useful Machine Learning Tools every lazy full-stack data scientist should use - Nov 18, 2020.
If you consider yourself a Data Scientist who can take any project from data curation to solution deployment, then you know there are many tools available today to help you get the job done. The trouble is that there are too many choices. Here is a review of five sets of tools that should turn you into the most efficient full-stack data scientist possible.
- Facebook Open Sourced New Frameworks to Advance Deep Learning Research - Nov 17, 2020.
Polygames, PyTorch3D and HiPlot are the new additions to Facebook’s open source deep learning stack.
- How to Acquire the Most Wanted Data Science Skills - Nov 13, 2020.
We recently surveyed KDnuggets readers to determine the "most wanted" data science skills. Since they seem to be those most in demand from practitioners, here is a collection of resources for getting started with this learning.
- How to deploy PyTorch Lightning models to production - Nov 5, 2020.
A complete guide to serving PyTorch Lightning models at scale.
- Building Neural Networks with PyTorch in Google Colab - Oct 30, 2020.
Combining PyTorch and Google's cloud-based Colab notebook environment can be a good solution for building neural networks with free access to GPUs. This article demonstrates how to do just that.
- Getting Started with PyTorch - Oct 14, 2020.
A practical walkthrough on how to use PyTorch for data analysis and inference.
- Top KDnuggets tweets, Sep 23-29: An Introduction to #AI – updated for 2020; Master using Pandas for time series analysis - Sep 30, 2020.
An Introduction to #AI - updated for 2020; Free From MIT: Intro to Computer Science and Programming in Python; The Most Complete Guide to #PyTorch for Data Scientists; (Good) Data Cleaning is just reusable Data Transformations
- KDnuggets™ News 20:n37, Sep 30: Introduction to Time Series Analysis in Python; How To Improve Machine Learning Model Accuracy - Sep 30, 2020.
Learn how to work with time series in Python; Tips for improving Machine Learning model accuracy from 80% to over 90%; Geographical Plots with Python; Best methods for making Python programs blazingly fast; Read a complete guide to PyTorch; KDD Best Paper Awards and more.
- Looking Inside The Blackbox: How To Trick A Neural Network - Sep 28, 2020.
In this tutorial, I’ll show you how to use gradient ascent to figure out how to misclassify an input.
- The Most Complete Guide to PyTorch for Data Scientists - Sep 24, 2020.
All the PyTorch functionality you will ever need while doing Deep Learning. From an Experimentation/Research Perspective.
- Autograd: The Best Machine Learning Library You’re Not Using? - Sep 16, 2020.
If there is a Python library that is emblematic of the simplicity, flexibility, and utility of differentiable programming it has to be Autograd.
- Math and Architectures of Deep Learning! - Jul 15, 2020.
This hands-on book bridges the gap between theory and practice, showing you the math of deep learning algorithms side by side with an implementation in PyTorch. Save 50% with code kdarch50.
- PyTorch LSTM: Text Generation Tutorial - Jul 13, 2020.
Key element of LSTM is the ability to work with sequences and its gating mechanism.
- PyTorch for Deep Learning: The Free eBook - Jul 7, 2020.
For this week's free eBook, check out the newly released Deep Learning with PyTorch from Manning, made freely available via PyTorch's website for a limited time. Grab it now!
- PyTorch Multi-GPU Metrics Library and More in New PyTorch Lightning Release - Jul 2, 2020.
PyTorch Lightning, a very light-weight structure for PyTorch, recently released version 0.8.1, a major milestone. With incredible user adoption and growth, they are continuing to build tools to easily do AI research.
- KDnuggets™ News 20:n25, Jun 24: PyTorch Fundamentals You Should Know; Free Math Courses to Boost Your Data Science Skills - Jun 24, 2020.
A Classification Project in Machine Learning: a gentle step-by-step guide; Crop Disease Detection Using Machine Learning and Computer Vision; Bias in AI: A Primer; Machine Learning in Dask; How to Deal with Missing Values in Your Dataset
- The Most Important Fundamentals of PyTorch you Should Know - Jun 18, 2020.
PyTorch is a constantly developing deep learning framework with many exciting additions and features. We review its basic elements and show an example of building a simple Deep Neural Network (DNN) step-by-step.
- KDnuggets™ News 20:n22, Jun 3: How to Think Like a Data Scientist; Six Ways For Data Scientists to Succeed at a Startup - Jun 3, 2020.
Learn how to think like a Data Scientist; Read about 6 ways for a data scientist to succeed at a startup; Get a great and free new book on Deep Learning for Coders with fast.ai and PyTorch; check best GIS Courses in 2020; and more.
- Deep Learning for Coders with fastai and PyTorch: The Free eBook - Jun 1, 2020.
If you are interested in a top-down, example-driven book on deep learning, check out the draft of the upcoming Deep Learning for Coders with fastai & PyTorch from fast.ai team.
- Build PyTorch Models Easily Using torchlayers - Apr 9, 2020.
torchlayers aims to do what Keras did for TensorFlow, providing a higher-level model-building API and some handy defaults and add-ons useful for crafting PyTorch neural networks.
- Francois Chollet on the Future of Keras and Reinforce Conference - Feb 25, 2020.
Ahead of Reinforce Conference in Budapest, we asked Francois Chollet, the creator of Keras, about Keras future, proposed developments, PyTorch, energy efficiency, and more. Listen to him in person in Budapest, April 6-7, and use code KDNuggets to save 15% on conference tickets.
- KDnuggets™ News 20:n05, Feb 5: How to land a Data Scientist job at your dream company; 12-Hour Machine Learning Challenge - Feb 5, 2020.
Read how one very persistent data scientist got a job at her dream company; Learn how to complete a 12 hour ML challenge; Top 10 AI, Machine Learning research papers; How to optimize your Jupyter notebook; and PyTorch FTW.
- OpenAI is Adopting PyTorch… They Aren’t Alone - Jan 31, 2020.
OpenAI is moving to PyTorch for the bulk of their research work. This might be a high-profile adoption, but it is far from the only such example.
- Xavier Amatriain’s Machine Learning and Artificial Intelligence 2019 Year-end Roundup - Dec 16, 2019.
It is an annual tradition for Xavier Amatriain to write a year-end retrospective of advances in AI/ML, and this year is no different. Gain an understanding of the important developments of the past year, as well as insights into what expect in 2020.
- PyTorch in 2019 and where in Europe you can learn about PyTorch in 2020 - Dec 4, 2019.
The Reinforce AI Conference is coming to Budapest again. Join us Apr 6-7 for the conference days, and optionally Apr 8 for workshops. Stefan Otte returns as a speaker, while Francois Chollet joins this time as well.
- Facebook Has Been Quietly Open Sourcing Some Amazing Deep Learning Capabilities for PyTorch - Nov 4, 2019.
The new release of PyTorch includes some impressive open source projects for deep learning researchers and developers.
- Contributing to PyTorch: By someone who doesn’t know a ton about PyTorch - Oct 9, 2019.
By the end of my week with the team, I managed to proudly cut two PRs on GitHub. I decided that I would write a blog post to knowledge share, not just to show that YES, you can too.
- A Gentle Introduction to PyTorch 1.2 - Sep 20, 2019.
This comprehensive tutorial aims to introduce the fundamentals of PyTorch building blocks for training neural networks.
- Which Data Science Skills are core and which are hot/emerging ones? - Sep 17, 2019.
We identify two main groups of Data Science skills: A: 13 core, stable skills that most respondents have and B: a group of hot, emerging skills that most do not have (yet) but want to add. See our detailed analysis.
- 5 Step Guide to Scalable Deep Learning Pipelines with d6tflow - Sep 16, 2019.
How to turn a typical pytorch script into a scalable d6tflow DAG for faster research & development.
- TensorFlow vs PyTorch vs Keras for NLP - Sep 3, 2019.
These three deep learning frameworks are your go-to tools for NLP, so which is the best? Check out this comparative analysis based on the needs of NLP, and find out where things are headed in the future.
- Pytorch Lightning vs PyTorch Ignite vs Fast.ai - Aug 16, 2019.
Here, I will attempt an objective comparison between all three frameworks. This comparison comes from laying out similarities and differences objectively found in tutorials and documentation of all three frameworks.
- 9 Tips For Training Lightning-Fast Neural Networks In Pytorch - Aug 9, 2019.
Who is this guide for? Anyone working on non-trivial deep learning models in Pytorch such as industrial researchers, Ph.D. students, academics, etc. The models we're talking about here might be taking you multiple days to train or even weeks or months.
- KDnuggets™ News 19:n29, Aug 7: What 70% of Data Science Learners Do Wrong; Pytorch Cheat Sheet for Beginners - Aug 7, 2019.
This week on KDnuggets: What 70% of Data Science Learners Do Wrong; Pytorch Cheat Sheet for Beginners and Udacity Deep Learning Nanodegree; How a simple mix of object-oriented programming can sharpen your deep learning prototype; Can we trust AutoML to go on full autopilot?; Ten more random useful things in R you may not know about; 25 Tricks for Pandas; and much more!
- Pytorch Cheat Sheet for Beginners and Udacity Deep Learning Nanodegree - Aug 2, 2019.
This cheatsheet should be easier to digest than the official documentation and should be a transitional tool to get students and beginners to get started reading documentations soon.
- Build your own AutoML computer vision pipeline, July 16 webinar - Jul 2, 2019.
This webinar will present a step-by-step use case so you can build your own AutoML computer vision pipelines, and will go through the essentials for research, deployment and training using Keras, PyTorch and TensorFlow.
- Extracting Knowledge from Knowledge Graphs Using Facebook’s Pytorch-BigGraph - May 22, 2019.
We are using the state-of-the-art Deep Learning tools to build a model for predict a word using the surrounding words as labels.
Pages: 1 2
- Which Deep Learning Framework is Growing Fastest? - May 1, 2019.
In September 2018, I compared all the major deep learning frameworks in terms of demand, usage, and popularity. TensorFlow was the champion of deep learning frameworks and PyTorch was the youngest framework. How has the landscape changed?
- KDnuggets™ News 19:n14, Apr 10: Which Data Science/ML methods and algorithms you used? Predict Age and Gender Using Neural Nets - Apr 10, 2019.
Getting started with NLP using the PyTorch framework; Building a Recommender System; Advice for New Data Scientists; All you need to know about text preprocessing for NLP and Machine Learning; Advanced Keras - Constructing Complex Custom Losses and Metrics; Top 8 Data Science Use Cases in Gaming
- Getting started with NLP using the PyTorch framework - Apr 3, 2019.
We discuss the classes that PyTorch provides for helping with Natural Language Processing (NLP) and how they can be used for related tasks using recurrent layers.
- Deploy your PyTorch model to Production - Mar 20, 2019.
This tutorial aims to teach you how to deploy your recently trained model in PyTorch as an API using Python.
- Beating the Bookies with Machine Learning - Mar 8, 2019.
We investigate how to use a custom loss function to identify fair odds, including a detailed example using machine learning to bet on the results of a darts match and how this can assist you in beating the bookmaker.
- 5 things that happened in Data Science in 2018 - Jan 8, 2019.
We review 5 things that happened in Data Science in 2018 and offer 20% discount on Reinforce AI Conference, Mar 20-22 in Budapest.
- Top Python Libraries in 2018 in Data Science, Deep Learning, Machine Learning - Dec 19, 2018.
Here are the top 15 Python libraries across Data Science, Data Visualization. Deep Learning, and Machine Learning.
- State of Deep Learning and Major Advances: H2 2018 Review - Dec 13, 2018.
In this post we summarise some of the key developments in deep learning in the second half of 2018, before briefly discussing the road ahead for the deep learning community.
- Introduction to PyTorch for Deep Learning - Nov 7, 2018.
In this tutorial, you’ll get an introduction to deep learning using the PyTorch framework, and by its conclusion, you’ll be comfortable applying it to your deep learning models.
- Top 13 Python Deep Learning Libraries - Nov 2, 2018.
Part 2 of a new series investigating the top Python Libraries across Machine Learning, AI, Deep Learning and Data Science.
- Deep Learning Framework Power Scores 2018 - Sep 24, 2018.
Who’s on top in usage, interest, and popularity?
- [ebook] Apache Spark™ Under the Hood - Jun 27, 2018.
Learn how to install and run Spark yourself; A summary of Spark core architecture and concepts; Spark powerful language APIs and how you can use them.
- Top 20 Python Libraries for Data Science in 2018 - Jun 27, 2018.
Our selection actually contains more than 20 libraries, as some of them are alternatives to each other and solve the same problem. Therefore we have grouped them as it's difficult to distinguish one particular leader at the moment.
Pages: 1 2
- Taming LSTMs: Variable-sized mini-batches and why PyTorch is good for your health - Jun 14, 2018.
After reading this, you’ll be back to fantasies of you + PyTorch eloping into the sunset while your Recurrent Networks achieve new accuracies you’ve only read about on Arxiv.
- KDnuggets™ News 18:n21, May 23: Python eats away at R; Top 2018 Analytics, Data Science, Machine Learning tools; 9 Must-have skills for a Data Scientist - May 23, 2018.
Also How to Implement a YOLO (v3) Object Detector from Scratch in PyTorch; Frameworks for Approaching the Machine Learning Process.
- Top Stories, May 14-20: Data Science vs Machine Learning vs Data Analytics vs Business Analytics; Implement a YOLO Object Detector from Scratch in PyTorch - May 21, 2018.
Also: An Introduction to Deep Learning for Tabular Data; 9 Must-have skills you need to become a Data Scientist, updated; GANs in TensorFlow from the Command Line: Creating Your First GitHub Project; Complete Guide to Build ConvNet HTTP-Based Application
- How to Implement a YOLO (v3) Object Detector from Scratch in PyTorch: Part 1 - May 17, 2018.
The best way to go about learning object detection is to implement the algorithms by yourself, from scratch. This is exactly what we'll do in this tutorial.
- KDnuggets™ News 18:n20, May 16: PyTorch Tensor Basics; Data Science in Finance; Executive Guide to Data Science - May 16, 2018.
PyTorch Tensor Basics; Top 7 Data Science Use Cases in Finance; The Executive Guide to Data Science and Machine Learning; Data Augmentation: How to use Deep Learning when you have Limited Data
- Simple Derivatives with PyTorch - May 14, 2018.
PyTorch includes an automatic differentiation package, autograd, which does the heavy lifting for finding derivatives. This post explores simple derivatives using autograd, outside of neural networks.
- PyTorch Tensor Basics - May 11, 2018.
This is an introduction to PyTorch's Tensor class, which is reasonably analogous to Numpy's ndarray, and which forms the basis for building neural networks in PyTorch.
- Ultra-compact workstation for top deep learning frameworks - Apr 27, 2018.
For workstation development platforms purpose-built for Tensorflow, PyTorch, Caffe2, MXNet, and other DL frameworks, the solution is BOXX. We're bringing deep learning to your deskside with the all-new APEXX W3!
- KDnuggets™ News 18:n16, Apr 18: Key Algorithms and Statistical Models; Don’t learn Machine Learning in 24 hours; Data Scientist among the best US Jobs in 2018 - Apr 18, 2018.
Also: Top 10 Technology Trends of 2018; 12 Useful Things to Know About Machine Learning; Robust Word2Vec Models with Gensim & Applying Word2Vec Features for Machine Learning Tasks; Understanding What is Behind Sentiment Analysis - Part 1; Getting Started with PyTorch
- Getting Started with PyTorch Part 1: Understanding How Automatic Differentiation Works - Apr 11, 2018.
PyTorch has emerged as a major contender in the race to be the king of deep learning frameworks. What makes it really luring is it’s dynamic computation graph paradigm.
Pages: 1 2
- Comparing Deep Learning Frameworks: A Rosetta Stone Approach - Mar 26, 2018.
A Rosetta Stone of deep-learning frameworks has been created to allow data-scientists to easily leverage their expertise from one framework to another.
- Deep Learning Development with Google Colab, TensorFlow, Keras & PyTorch - Feb 20, 2018.
Now you can develop deep learning applications with Google Colaboratory - on the free Tesla K80 GPU - using Keras, Tensorflow and PyTorch.
Pages: 1 2
- A Simple Starter Guide to Build a Neural Network - Feb 5, 2018.
This guide serves as a basic hands-on work to lead you through building a neural network from scratch. Most of the mathematical concepts and scientific decisions are left out.
- Top 10 Videos on Deep Learning in Python - Nov 17, 2017.
Playlists, individual tutorials (not part of a playlist) and online courses on Deep Learning (DL) in Python using the Keras, Theano, TensorFlow and PyTorch libraries. Assumes no prior knowledge. These videos cover all skill levels and time constraints!
- Ranking Popular Deep Learning Libraries for Data Science - Oct 23, 2017.
We rank 23 open-source deep learning libraries that are useful for Data Science. The ranking is based on equally weighing its three components: Github and Stack Overflow activity, as well as Google search results.
- Top KDnuggets tweets, Oct 04-10: Using #MachineLearning to Predict, Explain Attrition; Tidyverse, an opinionated #DataScience Toolbox in R - Oct 11, 2017.
Also #MachineLearning: Understanding Decision Tree Learning; #PyTorch tutorial distilled - Moving from #TensorFlow to PyTorch.
- PyTorch or TensorFlow? - Aug 29, 2017.
PyTorch is better for rapid prototyping in research, for hobbyists and for small scale projects. TensorFlow is better for large-scale deployments, especially when cross-platform and embedded deployment is a consideration.
- Top KDnuggets tweets, Aug 2-8: PyTorch: concise overview of the framework and its tensor implementation - Aug 9, 2017.
Also: What is the most important step in a #MachineLearning project? #MachineLearning Algorithms: a concise technical overview; McKinsey state of #MachineLearning and #AI.
- Design by Evolution: How to evolve your neural network with AutoML - Jul 20, 2017.
The gist ( tl;dr): Time to evolve! I’m gonna give a basic example (in PyTorch) of using evolutionary algorithms to tune the hyper-parameters of a DNN.
Pages: 1 2 3