|
|
|
|
|
--- |
|
|
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: detection |
|
|
|
|
|
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 |
|
|
|
|
|
{ |
|
|
"train_path": "/workspace/donut_train/doctr/train/", |
|
|
"val_path": "/workspace/donut_train/doctr/val/", |
|
|
"arch": "db_resnet50", |
|
|
"name": "detection_test", |
|
|
"epochs": 15, |
|
|
"batch_size": 2, |
|
|
"device": 0, |
|
|
"save_interval_epoch": false, |
|
|
"input_size": 1024, |
|
|
"lr": 0.001, |
|
|
"weight_decay": 0, |
|
|
"workers": 16, |
|
|
"resume": null, |
|
|
"test_only": false, |
|
|
"freeze_backbone": false, |
|
|
"show_samples": false, |
|
|
"wb": true, |
|
|
"push_to_hub": true, |
|
|
"pretrained": false, |
|
|
"rotation": false, |
|
|
"eval_straight": false, |
|
|
"sched": "poly", |
|
|
"amp": false, |
|
|
"find_lr": false, |
|
|
"early_stop": false, |
|
|
"early_stop_epochs": 5, |
|
|
"early_stop_delta": 0.01 |
|
|
} |
