Podium

Getting Started

Installation
Quickstart
Walkthrough

In Depth Overview

Podium data flow
How to interact with Fields
Special tokens
Custom numericalization functions
Fields with multiple outputs
- The Multioutput Field
Dataset manipulation
- Dataset splitting
- Dataset concatenation
Bucketing instances when iterating
Saving and loading Podium components
Documentation chapters in progress
- Handling datasets with missing data
- Creating your own Dataset subclass

Examples

TFIDF + scikit-learn SVM
- Using ngram features
Pytorch RNN classifier

Preprocessing Tools

Hooks
Utilities
- SpaCy sentencizer
- Hook conversion

Package Reference

Fields and Vocab
Built-in preprocessing tools
Dataset classes
Iterators
Data vectorizers

Modules Under Development

Abstractions for model training with Podium
Concrete implementations of models

Podium

»
Documentation chapters in progress
View page source

Documentation chapters in progress¶

Handling datasets with missing data¶

Creating your own Dataset subclass¶

Next Previous

© Copyright 2020, TakeLab, FER, Zagreb

Built with Sphinx using a theme provided by Read the Docs.