Theodoros Ntakouris

Published in Towards Data Science

·Pinned

The Time Series Transformer

All you need to know about the state of the art Transformer Neural Network Architecture, adapted to Time Series Tasks. Keras code included. — Table of Contents Introduction Preprocessing Learnable Time Representation (Time 2 Vec) Architecture Bag Of Tricks (things to consider when training Transformers) Introduction Attention Is All You Need they said. Is it a more robust convolution? Is it just a hack to squeeze more learning capacity out of fewer parameters? Is it supposed to be…

Deep Learning

6 min read

Deep Learning

6 min read

Published in Towards Data Science

·Pinned

Structuring ML Pipeline Projects

An organised codebase enables you to implement changes faster and make less mistakes, ultimately leading to higher code and model quality. Read more to learn how to structure your ML projects with Tensorflow Extended (TFX), the easy and straightforward way. — Project Structure: Requirements Enable experimentation with multiple pipelines Support both alocal execution mode and a deployment execution mode. This ensures the creation of 2 separate running configurations, with the first being used for local development and end-to-end testing and the second one used for running in the cloud.

Machine Learning

4 min read

Machine Learning

4 min read

Published in Towards Data Science

·Pinned

Tensorflow Best Practises: Named Inputs and Outputs

Quit depending on positional indices and input value ordering. Start relying on named inputs and outputs. Avoiding data wiring errors — Named inputs and outputs are essentially dictionaries with string keys and tensor values. Benefits Defence Against Feature Reordering Self — Sufficient Model Serving Signatures and Metadata Renaming and Absent Feature Protection Most machine learning pipelines read data from a structured source ( database, CSV files/ Pandas Dataframes , TF Records), perform…

Tensorflo

2 min read

Tensorflo

2 min read

Pinned

A quick overview of compression methods for Convolutional Neural Networks

Namely: Hyperparameter Search, Convolution Variants, Network-in-Network, Weight Sharing, Pruning, Quantization — The following is a very, very brief and non-technical summary of a chapter in the author’s dissertation. Motives A very deep neural network that is designed to solve hard problems might take a few seconds to run on modern computers with hardware accelerators for linear algebra operations. Similarly, smaller neural networks…

Deep Learning

6 min read

A quick overview of compression methods for Convolutional Neural Networks

Deep Learning

6 min read

Apr 19, 2022

Python & Maintainability: Keeping track of constants

Hard-coded string values that linger around your project impact your ability to change negatively, but there’s an easy way around that. But first, what’s wrong with magic strings? We’re going to demonstrate the usage of using static classes to keep track of constants, in 2 scenarios: Declaring routes in a FastAPI app Keeping track of metrics and…

Machine Learning

3 min read

Python & Maintainability: Keeping track of constants

Machine Learning

3 min read

Oct 1, 2021

Functional and Type-Safe Heterogeneous Data Handling in Rust

Safely store and handle incoming heterogeneous data in a functional, type-safe, rusty way. — Problem Statement You’ve got to make a web API that accepts JSON objects (or anything that serde supports, actually). You need some code — first way of declaring the structure of those incoming entities, so that they can be processed accordingly and deserialized into easy-to-use structs and traits. Consider the following example:

Web Development

4 min read

Functional and Type-Safe Heterogeneous Data Handling in Rust

Web Development

4 min read

Published in Towards Data Science

·Sep 25, 2020

Advanced Tensorflow Data Input Pipelines: Handling Time Series

Extracting labels, windowing multivariate series, multiple TF Record file shards and other useful tips for dealing with sequential data — The tf.data.Dataset API is a very efficient pipeline builder. Time Series Tasks can be a bit tricky to implement properly. In this article, we are going to dive deep into common tasks: Windowing Labelled Data Windowing Unlabelled Data by Looking Ahead Sharding TF Record Files Tips for Efficiency and No…

Time Series Forecasting

4 min read

Advanced Tensorflow Data Input Pipelines: Handling Time Series

Time Series Forecasting

4 min read

Published in Towards Data Science

·Sep 23, 2020

Playing chrome’s dino game by physically jumping and crouching

A creative PoseNet application that runs on your browser and tries to predict if you’re jumping, crouching, or staying still — You all know what this game is about. This is the best service-offline-sorry page in the world. People have made simple bots that time the dino’s jump to beat the game to reinforcement learning agents with CNN state encoders. It’s a game and we’re supposed to have fun. Today, I’ll…

Deep Learning

3 min read

Playing chrome’s dino game by physically jumping and crouching

Deep Learning

3 min read

Published in Towards Data Science

·Jul 31, 2020

Deep Learning End to End Pipelines made easy with Fluent Tensorflow Extended

A quick api overview and a self-contained example of fluent-tfx — If this production e2e ML pipelines thing seems new to you, please read the TFX guide first. On the other hand, if you’ve used TFX before, or planning to deploy a machine learning model, you’re in the right place. But Tensorflow Extended is already fully capable to construct e2e pipelines by itself, why bother to use another API ? Verbose and long code definitions. Actual preprocessing and training code can…

Deep Learning

4 min read

Deep Learning

4 min read

Published in Towards Data Science

·Jul 16, 2020

A comprehensive ML Metadata walkthrough for Tensorflow Extended

Why it exists and how it’s used in Beam Pipeline Components — ML Metadata (MLMD) is a library for recording and retrieving metadata associated with ML developer and data scientist workflows. TensorFlow Extended (TFX) is an end-to-end platform for deploying production ML pipelines The current version of ML Metadata by the time this article is being published is v0.22 (tfx is also…

Metadata

5 min read

Metadata

5 min read