# naiveHobo/InvoiceNet

Deep neural network to extract intelligent information from invoice documents.

Repository: https://github.com/naiveHobo/InvoiceNet
Canonical: https://ross.abutalabs.com/products/invoicenet
Language: Python
License: MIT
License Family: permissive
Topics: invoice, invoice-management, invoices, invoice-insight, classification, deep-learning, deep-neural-networks, deeplearning, keras, keras-tensorflow, keras-neural-networks, invoice-pdf, invoice-parser, invoice-software, information-retrieval, information-extraction, billing
Last push: 2024-05-03T20:12:57+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2985, "days_push": 852, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2694, forks 411 (observed 2026-08-28T04:07:11.125882+00:00)

## What it is
InvoiceNet is a deep neural network application with a GUI for extracting structured information from invoice documents in PDF, JPG, and PNG formats. It includes a Trainer UI for building custom models on your own labeled invoice datasets and supports customizable extraction fields.

## Use cases
- extract fields like vendor and total from invoice pdfs
- train a custom model on my own invoice dataset
- parse invoice documents into structured data
- automate invoice data entry
- view and extract information from scanned invoices

## When to choose
- you have a labeled dataset of invoices and want to train a custom extraction model
- you need a GUI tool to annotate, train, and extract invoice fields
- you want an open-source alternative to commercial invoice OCR services

## When to avoid
- you need ready-to-use pre-trained models for general invoices - none are available yet
- you lack GPU/training setup or labeled training data
- you need production-grade document extraction across many document types beyond invoices

## Facets
- artifact type: application
- maturity: active
- function: machine-learning, deep-learning, ocr, pdf, nlp, gui
- domain: machine-learning, pdf, developer-tools
- platform: windows, python
- tags: invoice-processing, information-extraction, document-ai, keras, tensorflow, training-ui, automation, linux, desktop

## Member repositories
- naiveHobo/InvoiceNet (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:11.125882+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:16:20.875825+00:00, confidence not recorded.
  - readme: https://github.com/naiveHobo/InvoiceNet (fetched 2026-08-28T04:07:11.125882+00:00, sha 6d830d8c6248)
- Data as of 2026-08-30T08:39:29.467469+00:00.