Crnn Mobilenet V3 Large Gen Hw

🚀 Doctr - 光學字符識別工具

Doctr 藉助 TensorFlow 2 和 PyTorch 技術，讓光學字符識別變得無縫且人人可用。

🚀 快速開始

Doctr 項目的 GitHub 倉庫鏈接：https://github.com/mindee/doctr

💻 使用示例

基礎用法

>>> from doctr.io import DocumentFile
>>> from doctr.models import ocr_predictor, from_hub

>>> img = DocumentFile.from_images(['<image_path>'])
>>> # 從模型中心加載模型
>>> model = from_hub('mindee/my-model')

>>> # 將模型傳入預測器
>>> # 如果你的模型是識別模型：
>>> predictor = ocr_predictor(det_arch='db_mobilenet_v3_large',
>>>                           reco_arch=model,
>>>                           pretrained=True)

>>> # 如果你的模型是檢測模型：
>>> predictor = ocr_predictor(det_arch=model,
>>>                           reco_arch='crnn_mobilenet_v3_small',
>>>                           pretrained=True)

>>> # 獲取預測結果
>>> res = predictor(img)

🔧 運行配置

以下是運行該項目的配置信息：

{
  "arch": "crnn_mobilenet_v3_large",
  "train_path": "train",
  "val_path": "val",
  "train_samples": 1000,
  "val_samples": 20,
  "font": "FreeMono.ttf,FreeSans.ttf,FreeSerif.ttf",
  "min_chars": 1,
  "max_chars": 12,
  "name": "crnn_mobilenet_v3_large_gen_hw",
  "epochs": 3,
  "batch_size": 64,
  "device": null,
  "input_size": 32,
  "lr": 0.001,
  "weight_decay": 0,
  "workers": 2,
  "resume": "crnn_mobilenet_v3_large_printed.pt",
  "vocab": "tamazight",
  "test_only": false,
  "show_samples": false,
  "wb": true,
  "push_to_hub": true,
  "pretrained": false,
  "sched": "cosine",
  "amp": false,
  "find_lr": false
}