PinnedPublished inTowards Data ScienceStructuring ML Pipeline ProjectsAn organised codebase enables you to implement changes faster and make less mistakes, ultimately leading to higher code and model quality…Sep 19, 2020Sep 19, 2020
PinnedPublished inTowards Data ScienceTensorflow Best Practises: Named Inputs and OutputsQuit depending on positional indices and input value ordering. Start relying on named inputs and outputs. Avoiding data wiring errors.Sep 25, 2020Sep 25, 2020
PinnedA quick overview of compression methods for Convolutional Neural NetworksNamely: Hyperparameter Search, Convolution Variants, Network-in-Network, Weight Sharing, Pruning, QuantizationDec 10, 2020Dec 10, 2020
Image deduplication using OpenAI’s CLIP and Community DetectionA short guide on how to use image embeddings from OpenAI’s CLIP and clustering techniques in order to group near-duplicate images together.Apr 9, 2023Apr 9, 2023
Python & Maintainability: Keeping track of constantsHard-coded string values that linger around your project impact your ability to change negatively, but there’s an easy way around that.Apr 19, 2022Apr 19, 2022
Functional and Type-Safe Heterogeneous Data Handling in RustSafely store and handle incoming heterogeneous data in a functional, type-safe, rusty way.Oct 1, 2021Oct 1, 2021
Published inTowards Data ScienceAdvanced Tensorflow Data Input Pipelines: Handling Time SeriesExtracting labels, windowing multivariate series, multiple TF Record file shards and other useful tips for dealing with sequential data.Sep 25, 2020Sep 25, 2020
Published inTowards Data SciencePlaying chrome’s dino game by physically jumping and crouchingA creative PoseNet application that runs on your browser and tries to predict if you’re jumping, crouching or staying still.Sep 23, 20201Sep 23, 20201
Published inTowards Data ScienceDeep Learning End to End Pipelines made easy with Fluent Tensorflow ExtendedA quick api overview and a self-contained example of fluent-fJul 31, 2020Jul 31, 2020