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": "master",
  "train_path": "C:/Users/Admin/Documents/AI/git_repos/doctr/data/pn/train",
  "val_path": "C:/Users/Admin/Documents/AI/git_repos/doctr/data/pn/val",
  "train_samples": 1000,
  "val_samples": 20,
  "font": "FreeMono.ttf,FreeSans.ttf,FreeSerif.ttf,NotoSeridGurmukhi.ttf",
  "min_chars": 1,
  "max_chars": 12,
  "name": null,
  "epochs": 100,
  "batch_size": 64,
  "device": 0,
  "input_size": 32,
  "lr": 0.001,
  "weight_decay": 0.001,
  "workers": 16,
  "resume": null,
  "vocab": "panjabi",
  "test_only": false,
  "freeze_backbone": false,
  "show_samples": false,
  "wb": false,
  "push_to_hub": true,
  "pretrained": false,
  "sched": "cosine",
  "amp": false,
  "find_lr": false,
  "early_stop": true,
  "early_stop_epochs": 5,
  "early_stop_delta": 0.01
}