|
|
| --- |
| language: en |
| --- |
| |
| <p align="center"> |
| <img src="https://doctr-static.mindee.com/models?id=v0.3.1/Logo_doctr.gif&src=0" width="60%"> |
| </p> |
|
|
| **Optical Character Recognition made seamless & accessible to anyone, powered by TensorFlow 2 & PyTorch** |
|
|
| ## Task: recognition |
|
|
| https://github.com/mindee/doctr |
|
|
| ### Example usage: |
|
|
| ```python |
| >>> from doctr.io import DocumentFile |
| >>> from doctr.models import ocr_predictor, from_hub |
| |
| >>> img = DocumentFile.from_images(['<image_path>']) |
| >>> # Load your model from the hub |
| >>> model = from_hub('mindee/my-model') |
| |
| >>> # Pass it to the predictor |
| >>> # If your model is a recognition model: |
| >>> predictor = ocr_predictor(det_arch='db_mobilenet_v3_large', |
| >>> reco_arch=model, |
| >>> pretrained=True) |
| |
| >>> # If your model is a detection model: |
| >>> predictor = ocr_predictor(det_arch=model, |
| >>> reco_arch='crnn_mobilenet_v3_small', |
| >>> pretrained=True) |
| |
| >>> # Get your predictions |
| >>> res = predictor(img) |
| ``` |
| ### Run Configuration |
|
|
| { |
| "arch": "vitstr_small", |
| "train_path": "C:\\Users\\smartmind\\Desktop\\workspace\\test\\train_ocr\\train", |
| "val_path": "C:\\Users\\smartmind\\Desktop\\workspace\\test\\train_ocr\\validation", |
| "train_samples": 1000, |
| "val_samples": 20, |
| "font": "FreeMono.ttf,FreeSans.ttf,FreeSerif.ttf", |
| "min_chars": 1, |
| "max_chars": 12, |
| "name": "vitstr_small-korean", |
| "epochs": 15, |
| "batch_size": 64, |
| "device": 0, |
| "input_size": 32, |
| "lr": 0.001, |
| "weight_decay": 0.01, |
| "workers": 8, |
| "resume": null, |
| "vocab": "korean", |
| "test_only": false, |
| "show_samples": false, |
| "wb": true, |
| "push_to_hub": true, |
| "pretrained": true, |
| "sched": "onecycle", |
| "amp": true, |
| "find_lr": false |
| } |
