https://github.com/ljvmiranda921/prodigy-pdf-custom-recipe

Custom recipe and utilities for document processing
https://github.com/ljvmiranda921/prodigy-pdf-custom-recipe

Last synced: 7 days ago
JSON representation

Custom recipe and utilities for document processing

• Host: GitHub
• URL: https://github.com/ljvmiranda921/prodigy-pdf-custom-recipe
• Owner: ljvmiranda921
• Created: 2022-05-02T02:16:37.000Z (over 2 years ago)
• Default Branch: master
• Last Pushed: 2022-06-19T03:55:37.000Z (over 2 years ago)
• Last Synced: 2024-11-26T05:52:09.568Z (18 days ago)
• Language: Python
• Homepage:
• Size: 722 KB
• Stars: 198
• Watchers: 5
• Forks: 20
• Open Issues: 2
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        


# 🪐 spaCy Project: Prodigy recipes for document processing and layout understanding

This repository contains recipes on how to use [Prodigy](https://prodi.gy) and

[Hugging Face](https://huggingface.co) for annotating, training, and reviewing

document layout datasets.  We'll be finetuning a

[LayoutLMv3](https://arxiv.org/abs/2204.08387) model using

[FUNSD](https://guillaumejaume.github.io/FUNSD/), a dataset of noisy scanned

documents.

![](docs/prodigy_annotation.gif)

This also serves as an illustration of how to design document processing

solutions. I attempted to generalize this approach into a framework, which you

can read more [from my

blog.](https://ljvmiranda921.github.io/notebook/2022/06/19/document-processing-framework/)

![](docs/design_principles.png)

## 📋 project.yml

The [`project.yml`](project.yml) defines the data assets required by the

project, as well as the available commands and workflows. For details, see the

[spaCy projects documentation](https://spacy.io/usage/projects).

### ⏯ Commands

The following commands are defined by the project. They

can be executed using [`spacy project run [name]`](https://spacy.io/api/cli#project-run).

Commands are only re-run if their inputs have changed.

| Command | Description |

| --- | --- |

| `install` | Install dependencies |

| `hydrate-db` | Hydrate the Prodigy database with annotated data from FUNSD |

| `review` | Review hydrated annotations |

| `train` | Train FUNSD model |

| `qa` | Perform QA for the test dataset using a trained model |

| `clean-db` | Drop all generated Prodigy datasets |

| `clean-files` | Clean all intermediary files |

### ⏭ Workflows

The following workflows are defined by the project. They

can be executed using [`spacy project run [name]`](https://spacy.io/api/cli#project-run)

and will run the specified commands in order. Commands are only re-run if their

inputs have changed.

| Workflow | Steps |

| --- | --- |

| `all` | `install` → `hydrate-db` → `train` |

| `clean-all` | `clean-db` → `clean-files` |

### 🗂 Assets

The following assets are defined by the project. They can

be fetched by running [`spacy project assets`](https://spacy.io/api/cli#project-assets)

in the project directory.

| File | Source | Description |

| --- | --- | --- |

| `assets/funsd.zip` | URL | FUNSD dataset - noisy scanned documents for layout understanding |