This metaclass is assigned by default to all pybind11 types and is required in order for static properties to function correctly. Users may overri

Instance creation function for all pybind11 types. It only allocates space for the C++ object (or multiple objects, for Python-side inheritance from m

Create a brand new Python type according to the `type_record` specification. Return value: New reference. */

Create the type which can be used as a common base for all classes. This is needed in order to satisfy Python's requirements for multiple inherit

A `static_property` is the same as a `property` but the `__get__()` and `__set__()` methods are modified to always use the object type instead of

reference https://github.com/liuheng92/tensorflow_PSENet/blob/feature_dev/pse :param kernals: :param min_area: :return:

从图片中裁剪出 cropsize大小的图片和对应区域的文本框 :param im: 图片 :param text_polys: 文本框 :param max_tries: 最大尝试次数 :return: 裁剪

Constructs a ResNet-50 models. Args: pretrained (bool): If True, returns a models pre-trained on ImageNet

Constructs a ShuffleNetV2 with 1.0x output channels, as described in `"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture D

Validates that the points that the 4 points that dlimite a polygon are in clockwise order.

Validate the format of the line. If the line is not valid an exception will be raised. If maxWidth and maxHeight are specified, all points mu

对图片和文本框进行竖直翻转 :param im: 图片 :param text_polys: 文本框 :return: 竖直翻转之后的图片和文本框

If set, the array is writeable (otherwise the buffer is read-only)

初始化pytorch模型 :param model_path: 模型地址(可以是模型的参数或者参数和计算图一起保存的文件) :param net: 网络计算图，如果在model_path中指定的是参数的保存路径，则需要给出网络的计算图

Implement PSE Loss.

Don't warn about an unused variable

对图片加噪声 :param img: 图像array :return: 加噪声后的图像array,由于输出的像素是在[0,1]之间,所以得乘以255

Adds an object to the module using the given name. Throws if an object with the given name already exists. overwrite should almost always be false:

This can only be used inside a pybind11-bound function, either by `argument_loader` at argument preparation time or by `py::cast()` at execution time.

Sets the learning rate # Adapted from PyTorch Imagenet example: # https://github.com/pytorch/examples/blob/master/imagenet/main.py

appends the extents to shape

Constructs an argument with the name of the argument; if null or omitted, this is a positional argument.

Delegating constructor needed when both moving and accessing in the same constructor

Base object