|
|
import numpy as np
|
|
|
import lqmtest_x3_5_pool
|
|
|
import lqmtest_x3_2_load_data
|
|
|
import lqmtest_x3_4_conv_proc
|
|
|
import lqmtest_x3_6_fullconn
|
|
|
|
|
|
|
|
|
class ModelObj: # 网络对象
|
|
|
def __init__(self, ObjID, ObjType, ObjLable, ParaString, ObjX, ObjY):
|
|
|
self.ObjID = ObjID # 图元号
|
|
|
self.ObjType = ObjType # 图元类别
|
|
|
self.ObjLable = ObjLable # 对象标签
|
|
|
self.ParaString = ParaString # 参数字符串
|
|
|
self.ObjX = ObjX # 对象位置x坐标
|
|
|
self.ObjY = ObjY # 对象位置y坐标
|
|
|
class Nonline_Class(ModelObj): # 非线性对象
|
|
|
def __init__(self, ObjID, ObjType, ObjLable, ParaString, ObjX, ObjY):
|
|
|
super().__init__(ObjID, ObjType, ObjLable, ParaString, ObjX, ObjY)
|
|
|
self.NonlinearProc = self.nonlinear_proc # 基本操作函数
|
|
|
self.SetNonLPara = self.setnonl_para # 参数设置函数
|
|
|
def nonlinear_proc(self, inputdata, NonLPara): # 定义非线性函数
|
|
|
# 从NonLPara参数中获取非线性函数类型
|
|
|
nonlinearmode = NonLPara["nonlinearmode"]
|
|
|
if nonlinearmode == "Sigmoid":
|
|
|
# Sigmoid函数，将任何实数的输入映射到0和1之间的输出
|
|
|
output = 1 / (1 + np.exp(-inputdata))
|
|
|
elif nonlinearmode == "ReLU":
|
|
|
# ReLU函数，将负数输入置为0，而正数输入保持不变
|
|
|
output = np.maximum(inputdata, 0)
|
|
|
elif nonlinearmode == "Tanh":
|
|
|
# Tanh函数，将任何实数的输入映射到-1和1之间的输出
|
|
|
output = np.tanh(inputdata)
|
|
|
else:
|
|
|
# 非法的非线性类型，抛出异常
|
|
|
raise ValueError("Invalid nonlinear mode")
|
|
|
return output # 返回计算后的值
|
|
|
def setnonl_para(self): # 定义设置非线性参数的函数
|
|
|
# 确定参数信息：非线性函数的类型。可以选择"Sigmoid", "ReLU" 或 "Tanh"
|
|
|
nonlinearmode = input("请输入非线性函数的类型（Sigmoid/ReLU/Tanh）：")
|
|
|
# 返回NonLPara参数，这里用一个字典来存储
|
|
|
NonLPara = {"nonlinearmode": nonlinearmode}
|
|
|
return NonLPara # 返回NonLPara参数
|
|
|
if __name__ == '__main__':
|
|
|
DataSet = lqmtest_x3_2_load_data.Data_Class("DataSet1", 1, "数据集1", [], 120, 330)
|
|
|
# setload_data()函数，获取加载数据集的参数
|
|
|
DataPara = DataSet.SetDataPara()
|
|
|
train_images, test_images = DataSet.LoadData(DataPara)
|
|
|
|
|
|
Conv = lqmtest_x3_4_conv_proc.Conv_Class("Conv1", 2, "卷积1", [], 250, 330)
|
|
|
ConvPara = Conv.SetConvPara()
|
|
|
for i in range(len(train_images) // 32):
|
|
|
images = train_images[i * 32:(i + 1) * 32]
|
|
|
conv_images = [] # 存储卷积处理后的图片的列表
|
|
|
for image in images: # 获取训练集的图片数据
|
|
|
dim = len(image.shape) # 获取矩阵的维度
|
|
|
if dim == 2: # 如果是二维矩阵,则转化为三维矩阵
|
|
|
image_h, image_w = image.shape
|
|
|
image = np.reshape(image, (1, image_h, image_w))
|
|
|
# 调用ConvProc()函数，根据ConvPara参数完成卷积计算
|
|
|
output = Conv.ConvProc(image, ConvPara)
|
|
|
conv_images.append(output) # 将卷积结果存储到列表
|
|
|
elif dim == 3: # 若为三维矩阵，则保持不变直接卷积处理
|
|
|
output = Conv.ConvProc(image, ConvPara)
|
|
|
conv_images.append(output)
|
|
|
# 将卷积处理后的图片列表转换为数组形式，方便后续处理
|
|
|
conv_images = np.array(conv_images)
|
|
|
|
|
|
Pool = lqmtest_x3_5_pool.Pool_Class("Pool1", 3, "最大池化1", [], 380, 330)
|
|
|
PoolPara = Pool.SetPollPara()
|
|
|
pool_images = [] # 存储池化处理后的图片的列表
|
|
|
for image in conv_images: # 获取卷积后的图片数据
|
|
|
output = Pool.MaxPoolProc(image, PoolPara)
|
|
|
pool_images.append(output) # 将池化结果存储到列表
|
|
|
# 将池化处理后的图片列表转换为数组形式，方便后续处理
|
|
|
pool_images = np.array(pool_images)
|
|
|
|
|
|
_, _, poolH, poolW = pool_images.shape
|
|
|
FullConn = lqmtest_x3_6_fullconn.FullConn_Class("FullConn1", 4, "全连接1", [], 510, 330)
|
|
|
FullConnPara = FullConn.SetFullConnPara(poolH, poolW)
|
|
|
|
|
|
fullconn_images = [] # 存储全连接处理后的图片的列表
|
|
|
for image in pool_images: # 获取池化后的图片数据
|
|
|
output = FullConn.FullConnProc(image, FullConnPara)
|
|
|
fullconn_images.append(output) # 将全连接处理后的结果存储到列表
|
|
|
# 将全连接处理后的图片列表转换为数组形式，方便后续处理
|
|
|
fullconn_images = np.array(fullconn_images)
|
|
|
|
|
|
Nonline = Nonline_Class("Nonline1", 5, "非线性函数1", [], 640, 330)
|
|
|
NonLPara = Nonline.SetNonLPara()
|
|
|
# 存储非线性处理后的图片的列表
|
|
|
nonlinear_images = []
|
|
|
for image in fullconn_images: # 获取全连接处理后的图片数据
|
|
|
output = Nonline.NonlinearProc(image, NonLPara)
|
|
|
# 将非线性处理后的结果存储到列表
|
|
|
nonlinear_images.append(output)
|
|
|
# 将非线性处理后的图片列表转换为数组形式，方便后续处理
|
|
|
nonlinear_images = np.array(nonlinear_images)
|
