captcha_detection icon indicating copy to clipboard operation
captcha_detection copied to clipboard

点选式验证码识别方案

Results 3 captcha_detection issues
Sort by recently updated
recently updated
newest added

Collecting xyolo Using cached xyolo-0.1.6-py3-none-any.whl (118 kB) Collecting tensorflow>=2.2 (from xyolo) Obtaining dependency information for tensorflow>=2.2 from https://files.pythonhosted.org/packages/93/21/9b035a4f823d6aee2917c75415be9a95861ff3d73a0a65e48edbf210cec1/tensorflow-2.15.0-cp311-cp311-win_amd64.whl.metadata Using cached tensorflow-2.15.0-cp311-cp311-win_amd64.whl.metadata (3.6 kB) Collecting numpy=1.18.1 (from xyolo) Using cached numpy-1.18.5.zip...

目测比项目自带的字体干扰差不多,val_loss越来越大,是网络不合适吗

我在跑目标检测时发现GPU 共享内存使用率几乎没有,CPU 使用率也不高,可以通过参数启用共享内存吗? ![image](https://github.com/AaronJny/captcha_detection/assets/43197840/c9633e6d-2ed3-421d-b8b6-47b25496625c) 这是我的参数配置: ``` # 创建一个DefaultYolo3Config的子类,在子类里覆盖默认的配置 class MyXYoloConfig(DefaultYolo3Config): def __init__(self): super(MyXYoloConfig, self).__init__() # 数据集路径,推荐使用绝对路径 self._dataset_path = './xyolo_label.txt' # 类别名称文件路径,推荐使用绝对路径 self._classes_path = './classes.txt' # 模型保存路径,默认是保存在当前路径下的xyolo_data下的,也可以进行更改 # 推荐使用绝对路径 self._output_model_path =...