|
|
|
|
|
import numpy as np
|
|
|
|
|
|
import pandas as pd
|
|
|
|
|
|
import lqmtest_x3_5_pool
|
|
|
|
|
|
import lqmtest_x3_2_load_data
|
|
|
|
|
|
import lqmtest_x3_4_conv_proc
|
|
|
|
|
|
import lqmtest_x3_6_fullconn
|
|
|
|
|
|
import lqmtest_x3_7_nonlinear
|
|
|
|
|
|
import lqmtest_x3_8_classify
|
|
|
|
|
|
class Label: # 标签
|
|
|
|
|
|
# 设置标签类别列表并将其转化为one-hot向量的形式
|
|
|
|
|
|
def setlabel_para(self):
|
|
|
|
|
|
label_list = input("请输入标签类别列表（用逗号分隔）：")
|
|
|
|
|
|
label_list = [int(x) for x in label_list.split(',')]
|
|
|
|
|
|
num_classes = len(label_list)
|
|
|
|
|
|
identity_matrix = np.eye(num_classes)
|
|
|
|
|
|
label_dict = {label: identity_matrix[i] for
|
|
|
|
|
|
i, label in enumerate(label_list)}
|
|
|
|
|
|
return label_dict
|
|
|
|
|
|
# 读取样本数据集，遍历每个样本，并将样本和对应的标签组成元组
|
|
|
|
|
|
def label_proc(self, samples, labels, label_dict):
|
|
|
|
|
|
labeled_samples = [(sample, label_dict[label]) for
|
|
|
|
|
|
sample, label in zip(samples, labels)]
|
|
|
|
|
|
return labeled_samples
|
|
|
|
|
|
def label_array(self, i):
|
|
|
|
|
|
path_csv = 'train.csv' # 读取标签数据
|
|
|
|
|
|
df = pd.read_csv(path_csv, header=None, skiprows=range(0,
|
|
|
|
|
|
i * 32), nrows=(i + 1) * 32 - i * 32)
|
|
|
|
|
|
# 将标签数据转化成数组
|
|
|
|
|
|
right_label = df.iloc[:, 0].tolist()
|
|
|
|
|
|
right_label = list(map(int, right_label))
|
|
|
|
|
|
right_label = [x for x in right_label]
|
|
|
|
|
|
return right_label
|
|
|
|
|
|
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 = lqmtest_x3_7_nonlinear.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)
|
|
|
|
|
|
|
|
|
|
|
|
Classifier=lqmtest_x3_8_classify.Classifier_Class("Classifier1", 6, "分类1", [], 780, 330)
|
|
|
|
|
|
ClassifyPara = Classifier.SetClassifyPara()
|
|
|
|
|
|
classifier_images = [] # 存储分类处理后的图片的列表
|
|
|
|
|
|
prob_images = [] # 存储分类处理后的概率向量
|
|
|
|
|
|
for image in nonlinear_images: # 获取非线性处理后的图片数据
|
|
|
|
|
|
# 调用softmax函数，得到概率分布向量
|
|
|
|
|
|
prob = Classifier.softmax(image)
|
|
|
|
|
|
prob_images.append(prob) # 将概率向量结果存储到列表
|
|
|
|
|
|
output = Classifier.ClassifierProc(image, ClassifyPara)
|
|
|
|
|
|
classifier_images.append(output) # 将分类结果存储到列表
|
|
|
|
|
|
# 将分类的结果列表转换为数组形式，方便后续处理
|
|
|
|
|
|
classifier_images = np.array(classifier_images)
|
|
|
|
|
|
|
|
|
|
|
|
LabelPara = Label()
|
|
|
|
|
|
label_dict = LabelPara.setlabel_para()
|
|
|
|
|
|
right_label = LabelPara.label_array(i)
|
|
|
|
|
|
labeled_samples = LabelPara.label_proc(images,
|
|
|
|
|
|
right_label, label_dict)
|
