language: en
Optical Character Recognition made seamless & accessible to anyone, powered by TensorFlow 2 & PyTorch
Task: recognition
https://github.com/mindee/doctr
Example usage:
>>> 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": "crnn_vgg16_bn", "train_path": "train-data", "val_path": "validation-data", "train_samples": 1000, "val_samples": 20, "font": "FreeMono.ttf,FreeSans.ttf,FreeSerif.ttf", "min_chars": 1, "max_chars": 32, "name": "doctr-torch-crnn_vgg16_bn-danish-v1", "epochs": 1, "batch_size": 64, "device": 0, "input_size": 32, "lr": 0.001, "weight_decay": 0, "workers": 16, "resume": "crnn_vgg16_bn_20240317-095746.pt", "vocab": "danish", "test_only": false, "freeze_backbone": false, "show_samples": false, "wb": false, "push_to_hub": true, "pretrained": true, "sched": "cosine", "amp": false, "find_lr": false, "early_stop": false, "early_stop_epochs": 5, "early_stop_delta": 0.01 }