If I had to pick only one tool that makes machine learning easier for everyone...

If you read my posts or take a look at my projects, it comes as no surprise that I use Google Colab a lot in my machine learning projects. Each time I start a new project, I create a Colab notebook in the first place. Recently I was wondering why I keep doing that and what’s so special about it.

in Tools, Nov 04, 2020

Conference talks from the top-class ML creators and experts to watch online

Conference talks or video tutorials are a great resource to learn programming, data science or anything else. These talks are even more precious if given by true experts and creators.

Read More

All Stories

If I had to pick only one tool that makes machine learning easier for everyone...

If you read my posts or take a look at my projects, it comes as no surprise that I use Google Colab a lot in my machine learning projects. Each time I start a new project, I create a ...

in Tools, Nov 04, 2020

Conference talks from the top-class ML creators and experts to watch online

Conference talks or video tutorials are a great resource to learn programming, data science or anything else. These talks are even more precious if given by true experts and creators.

in Education, Resources, Oct 29, 2020

Deploying machine learning models as a web application is quite a no-brainer now

A vast majority of machine learning projects won’t make it into production. It’s accurate for commercial projects within companies but also for personal projects developed by hobbyist...

in Production, Tools, Oct 20, 2020

Organizing work with Neptune tool for experiment tracking and visualizations

Whenever I start a new project that will require running a hundreds of experiments, integration with experiment tracking tools is the very first thing I add to my code. Such tools can...

in Project Tracking, Visualization, Oct 13, 2020

Finding good learning rate for your neural nets using PyTorch Lightning

Among of all hyperparameters used in machine learning, learning rate is probably the very first one you hear about. It may also the one that you start tuning in the first place. You c...

in Neural Networks, Tools, Sep 24, 2020

How to use data from Google Drive in Colab and what can possibly go wrong

Google Colab is extremely useful if you want to train your machine learning models in cloud for free. It allows you to use free GPU and a decent amount of disk space for your training...

in Tools, Tutorial, Sep 05, 2020

Hyperparameter tuning with Keras and Keras Tuner for images classification

In this post I describe and review Keras Tuner which can help you pick the optimal set of hyperparameters for your model. I used a small dataset for garbage classification and two dif...

in Neural Networks, Tutorial, Aug 16, 2020

Don't give up on machine learning because of your low-end hardware

Year by year machine learning models are getting more advanced, more accurate and break performance records. We collect more data and we use more complex models. Although it’s a good ...

in Education, Tools, Aug 10, 2020

Using H2O AutoML to simplify training process (and also predict wine quality)

Training a machine learning model can take a lot of your time and effort. If you have already prepared your data and set up the whole environment - finding the best model for your pro...

in AutoML, Tools, Aug 04, 2020

PyTorch Lightning for surface crack classification. Less boilerplate code?

First version has been relased in March 2019. At the time of writing we have version 0.9 pre-release available. It means that PyTorch Lightning is a new player in town. But what it is...

in Tools, Jul 24, 2020