Metadata-Version: 2.2
Name: multimodal_feature_builder
Version: 0.1.0
Summary: Build multi-modal feature matrices from text, images, categorical and numeric data.
Home-page: https://github.com/shivambhujbal/multimodal-feature-builder
Author: Shivam Bhujbal
License: MIT
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.7
Description-Content-Type: text/markdown
Requires-Dist: numpy
Requires-Dist: pandas
Requires-Dist: torch
Requires-Dist: torchvision
Requires-Dist: transformers
Requires-Dist: tqdm
Requires-Dist: scikit-learn
Requires-Dist: Pillow
Dynamic: author
Dynamic: classifier
Dynamic: description
Dynamic: description-content-type
Dynamic: home-page
Dynamic: license
Dynamic: requires-dist
Dynamic: requires-python
Dynamic: summary

# multimodal-feature-builder


Easily build multi-modal feature matrices from text, images, categorical, and numeric data.

- Uses BERT or any HuggingFace model for text.
- Uses ResNet/EfficientNet for images.
- Uses Scikit-Learn pipeline for tabular data.

## Installation

From GitHub (latest):

```bash
pip install git+https://github.com/shivambhujbal/multimodal-feature-builder.git
