How to Develop Optimization Models in Python

From: https://towardsdatascience.com/how-to-develop-optimization-models-in-python-1a03ef72f5b4 Determining how to design and operate a system in the best way, under the given circumstances such as allocation of scarce resources, usually requires leveraging on quantitative methods in decision making. Mathematical optimization is one of the main approaches for deciding the best action for a given situation. It consists of maximizing or minimizing the … Continue reading How to Develop Optimization Models in Python

Dockerize Jupyter with the Visual Debugger

From: https://towardsdatascience.com/dockerize-jupyter-with-official-visual-debugger-enabled-cbce1840b7f Jupyter recently announced its first-ever public release of the much-awaited visual debugger. Though it is the first release it supports all the basic debugging requirements needed to debug and inspect variables, etc. The Data Science community is relied heavily on Jupyter Notebooks due to its ability to easily communicate and share the outcomes … Continue reading Dockerize Jupyter with the Visual Debugger

Using Optuna to Optimize PyTorch Lightning Hyperparameters

From: https://medium.com/optuna/using-optuna-to-optimize-pytorch-lightning-hyperparameters-d9e04a481585 This post uses pytorch-lightning v0.6.0 (PyTorch v1.3.1)and optuna v1.1.0. PyTorch Lightning + Optuna! Optuna is a hyperparameter optimization framework applicable to machine learning frameworks and black-box optimization solvers. PyTorch Lightning provides a lightweight PyTorch wrapper for better scaling with less code. Combining the two of them allows for automatic tuning of hyperparameters to find the … Continue reading Using Optuna to Optimize PyTorch Lightning Hyperparameters

Faster Video Processing in Python using Parallel Computing

From: https://towardsdatascience.com/faster-video-processing-in-python-using-parallel-computing-25da1ad4a01 If you want to process a number of video files, it might take a from minutes to hours, depending on the size of the video, frame count, and frame dimensions. How can we speed up video processing? Parallel processing is the answer! If you are processing images in batches, you can utilize the … Continue reading Faster Video Processing in Python using Parallel Computing

PyTorch layer dimensions: what size and why?

From: https://towardsdatascience.com/pytorch-layer-dimensions-what-sizes-should-they-be-and-why-4265a41e01fd Preface This article covers defining tensors, and properly initializing neural network layers in PyTorch, and more! Introduction You might be asking: “How do I initialize my layer dimensions in PyTorch without getting yelled at?” Is it all just trial and error? No, really… What are they supposed to be? For starters, did you … Continue reading PyTorch layer dimensions: what size and why?

Noise: It’s not always annoying

From: https://towardsdatascience.com/noise-its-not-always-annoying-1bd5f0f240f One of the first concepts you learn when you begin to study neural networks is the meaning of overfitting and underfitting. Sometimes, it is a challenge to train a model that generalizes your data perfectly, especially when you have a small dataset because: When you train a neural network with small datasets, the network generally memorizes … Continue reading Noise: It’s not always annoying

Deploying your first Deep Learning Model: MNIST in production environment

From: https://towardsdatascience.com/deploying-your-first-deep-learning-model-mnist-in-production-environment-510bfdc4808d How you can deploy your MNIST model in production environment MNIST Dataset is a hello world dataset for most of the ML Enthusiast likes us. At some point everyone who has started their journey in this field or willing to start will come across this dataset and get their hands on for sure. It … Continue reading Deploying your first Deep Learning Model: MNIST in production environment

A Collection of 10 Data Visualizations You Must See

From: https://www.analyticsvidhya.com/blog/2018/01/collection-data-visualizations-you-must-see/ Introduction Writing codes is fun. Creating models with them is even more intriguing. But things start getting tricky when it comes to presenting our work to a non-technical person. This is where visualizations comes in. They are one of the best ways of telling a story with data. In this article, we look … Continue reading A Collection of 10 Data Visualizations You Must See

Object-oriented programming for data scientists: Build your ML estimator

From: https://towardsdatascience.com/object-oriented-programming-for-data-scientists-build-your-ml-estimator-7da416751f64 Implement some of the core OOP principles in a machine learning context by building your own Scikit-learn-like estimator, and making it better. What is the problem? Data scientists often come from a background which is quite far removed from traditional computer science/software engineering — physics, biology, statistics, economics, electrical engineering, etc. Source: “Where do … Continue reading Object-oriented programming for data scientists: Build your ML estimator

Modeling “Unknown Unknowns” with TensorFlow Probability — Industrial AI, Part 3

From: https://medium.com/tensorflow/modeling-unknown-unknowns-with-tensorflow-probability-industrial-ai-part-3-52146cd0201a Posted by Venkatesh Rajagopalan, Director Data Science & Analytics; Mahadevan Balasubramaniam, Principal Data Scientist; and Arun Subramaniyan, VP Data Science & Analytics at BHGE Digital We believe in a slightly modified version of George Box’s famous comment: “All models are wrong, some are useful” for a short period of time. Irrespective of how sophisticated a model … Continue reading Modeling “Unknown Unknowns” with TensorFlow Probability — Industrial AI, Part 3