import numpy as np import pandas as pd from sklearn.model_selection import train_test_split from keras.models import Sequential from keras.layers import Dense from pyswarm import pso import matplotlib.pyplot as plt from sklearn.preprocessing import StandardScaler from sklearn.metrics import mean_absolute_error from sklearn.metrics import mean_squared_error from sklearn.metrics import r2_score file = "zhong.xlsx" data = pd.read_excel(file) #reading file X=np.array(data.loc[:,'种植密度':'有效积温']) y=np.array(data.loc[:,'产量']) y.shape=(185,1) # 将数据集分为训练集和测试集 X_train, X_test, y_train, y_test = train_test_split(X,y, test_size=0.25, random_state=10) SC=StandardScaler() X_train=SC.fit_transform(X_train) X_test=SC.fit_transform(X_test) y_train=SC.fit_transform(y_train) y_test=SC.fit_transform(y_test) print("X_train.shape:", X_train.shape) print("X_test.shape:", X_test.shape) print("y_train.shape:", y_train.shape) print("y_test.shape:", y_test.shape) # 定义BP神经网络模型 def nn_model(X): model = Sequential() model.add(Dense(8, input_dim=X_train.shape[1], activation='relu')) model.add(Dense(12, activation='relu')) model.add(Dense(1)) model.compile(loss='mean_squared_error', optimizer='adam') return model # 定义适应度函数 def fitness_func(X): model = nn_model(X) model.fit(X_train, y_train, epochs=60, verbose=2) score = model.evaluate(X_test, y_test, verbose=2) print(score) # 定义变量的下限和上限 lb = [5, 5] ub = [30, 30] # 利用PySwarm库实现改进的粒子群算法来优化BP神经网络预测模型 result = pso(fitness_func, lb, ub) # 输出最优解和函数值 print('最优解:', result[0]) print('最小函数值:', result[1]) mpl.rcParams["font.family"] = "SimHei" mpl.rcParams["axes.unicode_minus"] = False # 绘制预测值和真实值对比图 model = nn_model(X) model.fit(X_train, y_train, epochs=60, verbose=2) y_pred = model.predict(X_test) y_true = SC.inverse_transform(y_test) y_pred=SC.inverse_transform(y_pred) plt.figure() plt.plot(y_true,"bo-",label = '真实值') plt.plot(y_pred,"ro-", label = '预测值') plt.title('神经网络预测展示') plt.xlabel('序号') plt.ylabel('产量') plt.legend(loc='upper right') plt.show() print("R2 = ",r2_score(y_test, y_pred)) # R2 # 绘制损失函数曲线图 model = nn_model(X) history = model.fit(X_train, y_train, epochs=60, validation_data=(X_test, y_test), verbose=2) plt.plot(history.history['loss'], label='train') plt.plot(history.history['val_loss'], label='test') plt.legend() plt.show() mae = mean_absolute_error(y_test, y_pred) print('MAE: %.3f' % mae) mse = mean_squared_error(y_test, y_pred) print('mse: %.3f' % mse)

下载numpy-1.22.4+mkl-cp38-cp38-win_amd64.whl提升深度学习效率

资源摘要信息:"numpy-1.22.4+mkl-cp38-cp38-win-amd64.whl" 知识点详细说明： 1. numpy库概述： numpy是一个开源的Python库，全名为Numerical Python，用于进行科学计算。它提供了高性能的多维数组对象以及相关...

使用Keras加载H5模型权重：load_model与load_weights实战

import numpy as np from network.resnet50 import ResNet50 # 创建ResNet50模型实例 model = ResNet50() # 加载权重，参数默认by_name=False # 如果层名匹配，则自动加载权重，否则需要指定by_name=True进行匹配 ...

import time import pandas as pd from sklearn.model_selection import train_test_split from sklearn.preprocessing import MinMaxScaler import numpy as np import tensorflow as tf from tensorflow.keras.models import Sequential from tensorflow.keras.layers import Dense, Dropout import tkinter as tk from tkinter import ttk from sklearn.neural_network import MLPClassifier from sklearn.preprocessing import StandardScaler from tkinter.messagebox import showinfo # pip install pyserial import serial import serial.tools.list_ports from main import MyClass if name == 'main': detect = MyClass() def collect_data_click(): detect.on_collect_data_click()

1. 导入需要的库：time、pandas、sklearn、numpy、tensorflow、tkinter、serial 等。 2. 从 tensorflow.keras 中导入 Sequential 和 Dense 两个类，用于搭建神经网络模型。 3. 定义了一个名为 MyClass 的类，并...

import numpy as np import pandas as pd from sklearn.model_selection import train_test_split from keras.models import Sequential from keras.layers import Dense from pyswarm import pso file = "zhong.xlsx" data = pd.read_excel(file) #reading file X=np.array(data.loc[:,'种植密度':'有效积温']) y=np.array(data.loc[:,'产量']) # 将数据集分为训练集和测试集 X_train, X_test, y_train, y_test = train_test_split(X,y, test_size=0.2, random_state=42) # 定义BP神经网络模型 def nn_model(X): model = Sequential() model.add(Dense(X[0], input_dim=X_train.shape[1], activation='relu')) model.add(Dense(X[1], activation='relu')) model.add(Dense(1)) model.compile(loss='mean_squared_error', optimizer='adam') return model # 定义适应度函数 def fitness_func(X): model = nn_model(X) model.fit(X_train, y_train, epochs=100, verbose=0) score = model.evaluate(X_test, y_test, verbose=0) return score # 定义变量的下限和上限 lb = [5, 5] ub = [50, 50] # 利用PySwarm库实现改进的粒子群算法来优化BP神经网络预测模型 result = pso(fitness_func, lb, ub) # 输出最优解和函数值 print('最优解:', result[0]) print('最小函数值:', result[1])

这段代码实现了一个改进的粒子群算法来优化BP神经网络预测模型。具体来说，它读取了一个名为"zhong.xlsx"的Excel文件，将其中的数据集分为训练集和测试集，然后定义了一个BP神经网络模型和适应度函数。...

import numpy as np import matplotlib.pyplot as plt import pandas as pd import math from keras.models import Sequential from keras.layers import Dense, Activation, Dropout, LSTM from sklearn.preprocessing import MinMaxScaler from sklearn.metrics import mean_squared_error from keras import optimizers import time解说代码

- numpy 是 Python 中用于科学计算的一个库。 - matplotlib 是 Python 中一个常用的绘图库。 - pandas 是 Python 中用于数据分析的一个库。 - math 是 Python 中的数学库，提供了许多数学函数。 - keras ...

import tensorflow as tf import numpy as np import matplotlib.pyplot as plt import pandas as pd from sklearn.utils import shuffle from sklearn.preprocessing import scale df = pd.read_csv("C:\\boston.csv",header=0) ds = df.values from sklearn.datasets import load_boston boston = load_boston() X = boston.data y = boston.target from sklearn.model_selection import train_test_split X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42) from sklearn.preprocessing import StandardScaler scaler = StandardScaler() X_train = scaler.fit_transform(X_train) X_test = scaler.transform(X_test) from tensorflow.keras.models import Sequential from tensorflow.keras.layers import Dense model = Sequential([ Dense(64, activation='relu', input_shape=(X_train.shape[1],)), Dense(64, activation='relu'), Dense(64, activation='relu'), Dense(1) ]) model.compile(loss='mean_squared_error', optimizer='adam') history = model.fit(X_train, y_train, validation_split=0.1, epochs=100, batch_size=32) from sklearn.metrics import mean_squared_error y_pred = model.predict(x_test)mse = mean_squared_error(y_test, y_pred)print('MSE:’, mse) import matplotlib.pyplot as plt plt.plot(history.history['accuracy'], label='train') plt.plot(history.history['val_accuracy'], label='validation') plt.legend() plt.show()

from sklearn.model_selection import train_test_split X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42) 对训练集和测试集进行标准化处理： from sklearn....

import numpy as np import pandas as pd from sklearn.preprocessing import MinMaxScaler from keras.models import Sequential from keras.layers import Dense, Dropout,LSTM,SimpleRNN,GRU np.random.seed(10) # 指定乱数种子 # 载入Google股价的训练数据集 df_train = pd.read_csv("",index_col="Date",parse_dates=True) df_train这个代码怎么载入数据

在代码中的pd.read_csv()函数中，""中需要填写数据集文件的路径和文件名（包括文件格式后缀）。index_col参数用于指定读取数据集时使用哪一列作为索引列，parse_dates=True参数用于将日期数据解析为日期格式...

import pandas as pd import numpy as np import tushare as ts from sklearn.preprocessing import MinMaxScaler import matplotlib.pyplot as plt import mplfinance as mpf from tensorflow.keras.models import Sequential from tensorflow.keras.layers import Dense, LSTM

这是一段 Python 代码，导入了一些常用的数据分析和机器学习库，包括 Pandas、NumPy、Tushare、Sklearn、Matplotlib、mplfinance 和 TensorFlow。其中，Pandas 用于数据处理和分析，NumPy 用于科学计算，Tushare ...

import numpy as np import tensorflow as tf from keras.models import Sequential from keras.layers import Dense, Activation, Dropout, Flatten from keras.layers.convolutional import Conv2D, MaxPooling2D from keras.utils import np_utils from keras.datasets import mnist from keras import backend as K from keras.optimizers import Adam import skfuzzy as fuzz import pandas as pd from sklearn.model_selection import train_test_split # 绘制损失曲线 import matplotlib.pyplot as plt from sklearn.metrics import accuracy_score data = pd.read_excel(r"D:\pythonProject60\filtered_data1.xlsx") # 读取数据文件 # Split data into input and output variables X = data.iloc[:, :-1].values y = data.iloc[:, -1].values X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42) # 导入MNIST数据集 # 数据预处理 y_train = np_utils.to_categorical(y_train, 3) y_test = np_utils.to_categorical(y_test, 3) # 创建DNFN模型 model = Sequential() model.add(Dense(64, input_shape=(11,), activation='relu')) model.add(Dense(128, activation='relu')) model.add(Dropout(0.5)) model.add(Dense(3, activation='softmax')) # 编译模型 model.compile(loss='categorical_crossentropy', optimizer=Adam(), metrics=['accuracy']) # 训练模型 history = model.fit(X_train, y_train, validation_data=(X_test, y_test), epochs=10, batch_size=128) # 使用DNFN模型进行预测 y_pred = model.predict(X_test) y_pred= np.argmax(y_pred, axis=1) print(y_pred) # 计算模糊分类 fuzzy_pred = [] for i in range(len(y_pred)): fuzzy_class = np.zeros((3,)) fuzzy_class[y_pred[i]] = 1.0 fuzzy_pred.append(fuzzy_class) fuzzy_pred = np.array(fuzzy_pred) print(fuzzy_pred)获得其运行时间

import time start_time = time.time() # Your code here end_time = time.time() print("Total time taken: ", end_time - start_time, "seconds") 这将打印代码的总运行时间，以秒为单位。

import numpy import matplotlib.pyplot as plt from keras.models import Sequential from keras.layers import Dense from keras.layers import LSTM import pandas as pd import os from keras.models import Sequential, load_model

根据您的代码，您导入了一些常用的 Python 库和模块，包括 numpy、matplotlib、pandas 和 keras。您还导入了一些特定的类和函数，例如 Sequential、Dense、LSTM 和 load_model。导入 numpy 库是为了在 Python 中...

mport numpy as np import tensorflow as tf from keras.models import Sequential from keras.layers import Dense, Activation, Dropout, Flatten from keras.layers.convolutional import Conv2D, MaxPooling2D from keras.utils import np_utils from keras.datasets import mnist from keras import backend as K from keras.optimizers import Adam import skfuzzy as fuzz import pandas as pd from sklearn.model_selection import train_test_split # 绘制损失曲线 import matplotlib.pyplot as plt import time from sklearn.metrics import accuracy_score data = pd.read_excel(r"D:\pythonProject60\filtered_data1.xlsx") # 读取数据文件 # Split data into input and output variables X = data.iloc[:, :-1].values y = data.iloc[:, -1].values X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42) # 导入MNIST数据集 # 数据预处理 y_train = np_utils.to_categorical(y_train, 3) y_test = np_utils.to_categorical(y_test, 3) # 创建DNFN模型 start_time=time.time() model = Sequential() model.add(Dense(64, input_shape=(11,), activation='relu')) model.add(Dense(128, activation='relu')) model.add(Dropout(0.5)) model.add(Dense(3, activation='softmax')) # 编译模型 model.compile(loss='categorical_crossentropy', optimizer=Adam(), metrics=['accuracy']) # 训练模型 history = model.fit(X_train, y_train, validation_data=(X_test, y_test), epochs=10, batch_size=128) # 使用DNFN模型进行预测 y_pred = model.predict(X_test) y_pred= np.argmax(y_pred, axis=1) print(y_pred) # 计算模糊分类 fuzzy_pred = [] for i in range(len(y_pred)): fuzzy_class = np.zeros((3,)) fuzzy_class[y_pred[i]] = 1.0 fuzzy_pred.append(fuzzy_class) fuzzy_pred = np.array(fuzzy_pred) end_time = time.time() print("Total time taken: ", end_time - start_time, "seconds")获得运行结果并分析

根据代码，这是一个使用Keras创建DNFN模型，对数据进行分类的代码。数据集使用的是一个Excel文件，通过pandas读取数据，然后分为训练集和测试集。模型使用了三层Dense层，其中第一层有64个神经元，第二层有128个神经...

import pandas as pd data = pd.read_csv('gdpcost.csv') import numpy as np from sklearn.model_selection import train_test_split # 将数据拆分成训练集和测试集 train_data, test_data, train_labels, test_labels = train_test_split(data['GDP'].values, data['Cost'].values, test_size=0.2) # 将数据转换为 NumPy 数组并进行标准化处理 train_data = (train_data - np.mean(train_data)) / np.std(train_data) test_data = (test_data - np.mean(train_data)) / np.std(train_data) train_labels =(train_labels - np.mean(train_labels)) / np.std(train_labels) test_labels= (test_labels - np.mean(train_labels)) / np.std(train_labels) # 将数据转换为 NumPy 数组并进行重塑 train_data = train_data.reshape(-1, 1) test_data = test_data.reshape(-1, 1) train_labels = train_labels.reshape(-1, 1) test_labels = test_labels.reshape(-1, 1) from keras.models import Sequential from keras.layers import Dense # 定义模型 model = Sequential() model.add(Dense(10, activation='relu', input_shape=(1,))) model.add(Dense(1)) # 编译模型 model.compile(optimizer='adam', loss='mse') # 训练模型 model.fit(train_data, train_labels, epochs=100, batch_size=32) # 评估模型 loss = model.evaluate(test_data, test_labels) print('Test loss:', loss)请解释每行代码

4. from sklearn.model_selection import train_test_split：从 sklearn 库中导入 train_test_split 方法，用于拆分数据集成训练集和测试集。 5. train_data, test_data, train_labels, test_labels = train_test...

#导入所需库 import numpy as np import pandas as pd from sklearn.preprocessing import LabelEncoder from keras.utils import to_categorical from keras.models import Sequential from keras.layers import Dense from sklearn.model_selection import KFold #读入数据 train_data = pd.read_csv('ProSeqs_Train.txt', delimiter=' ', header=None) test_data = pd.read_csv('ProSeqs_Test.txt', delimiter=' ', header=None) #预处理训练集数据 X = train_data.iloc[:, 2:].values y = train_data.iloc[:, 1].values le = LabelEncoder() y = le.fit_transform(y) y = to_categorical(y) #定义模型 model = Sequential() model.add(Dense(64, input_dim=X.shape[1], activation='relu')) model.add(Dense(32, activation='relu')) model.add(Dense(2, activation='softmax')) model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy']) #K折交叉验证训练模型 kf = KFold(n_splits=5, shuffle=True, random_state=42) fold_scores = [] for train_index, valid_index in kf.split(X): train_X, train_y = X[train_index], y[train_index] valid_X, valid_y = X[valid_index], y[valid_index] model.fit(train_X, train_y, validation_data=(valid_X, valid_y), epochs=50, batch_size=32, verbose=2) fold_scores.append(model.evaluate(valid_X, valid_y, verbose=0)[1]) print('KFold cross-validation accuracy: {:.2f}%'.format(np.mean(fold_scores) * 100)) #预处理测试集数据 test_X = test_data.iloc[:, 1:].values #预测测试集结果 preds = model.predict(test_X) preds = np.argmax(preds, axis=1) #保存预测结果至文件中 np.savetxt('preds.txt', preds, fmt='%d') #输出预测结果 print('Predictions:') print(preds)该蛋白质功能预测实验涉及分类模型的理论基础

这个蛋白质功能预测实验涉及分类模型的理论基础。具体来说，使用了深度学习中的神经网络模型，通过对蛋白质序列进行预处理和特征提取，将其表示为数值型的特征向量，然后将这些向量作为输入，训练出一个分类模型来对...

import pandas as pd from keras.models import Sequential from keras.layers import Dense import numpy as np from sklearn.metrics import accuracy_score file = pd.read_excel('/Users/zxh-mac/desktop/Edu-Data（A题数据）.xlsx') # 第二阶段：转化定性变量为定量变量使用onehot函数同时读取新的excel x = pd.get_dummies(file, dtype=int) x.to_excel('/Users/zxh-mac/desktop/Edu-Data(onehot_version).xlsx') data = pd.read_excel('/Users/zxh-mac/desktop/Edu-Data(onehot_version).xlsx') # 第三阶段：实现bp神经网络 train_data = data[:320] test_data = data[320:] train_features = train_data.drop('Class', axis=1).values train_labels = train_data['Class'].values test_features = test_data.drop('Class', axis=1).values test_labels = test_data['Class'].values model = Sequential() model.add(Dense(units=72, activation='relu', input_dim=train_features.shape[1])) model.add(Dense(units=72, activation='relu')) model.add(Dense(units=3, activation='sigmoid')) model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy']) model.fit(train_features, train_labels, epochs=10, batch_size=32, validation_data=(test_features, test_labels), verbose=1) predictions = model.predict(test_features) print(predictions)就是这段无法确定问题是什么

from keras.models import Sequential from keras.layers import Dense from sklearn.metrics import accuracy_score # 读取文件 file = pd.read_excel('/Users/zxh-mac/desktop/Edu-Data（A题数据）.xlsx') # ...

import numpy as np import pandas as pd import tensorflow as tf from sklearn.preprocessing import LabelEncoder from sklearn.model_selection import train_test_split from sklearn.decomposition import PCA from tensorflow.keras.models import Sequential from tensorflow.keras.layers import Conv1D, MaxPooling1D, Flatten, Dense, Dropout, Activation from sklearn.metrics import auc, accuracy_score, f1_score, recall_score # 读入数据 data = pd.read_csv('company_data.csv') X = data.iloc[:, :-1].values y = data.iloc[:, -1].values # 利用LabelEncoder将标签进行编码 encoder = LabelEncoder() y = encoder.fit_transform(y) # 划分训练集和测试集 X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42) # 对特征进行PCA降维 pca = PCA(n_components=17) X_train = pca.fit_transform(X_train) X_test = pca.transform(X_test) # 对数据reshape为符合卷积层输入的格式 X_train = X_train.reshape(-1, 17, 1) X_test = X_test.reshape(-1, 17, 1) # 构建卷积神经网络模型 model = Sequential() model.add(Conv1D(filters=128, kernel_size=3, activation='relu', input_shape=(17, 1))) model.add(Conv1D(filters=128, kernel_size=4, activation='relu')) model.add(Conv1D(filters=128, kernel_size=5, activation='relu')) model.add(MaxPooling1D(pool_size=2)) model.add(Flatten()) model.add(Dense(units=64, activation='relu')) model.add(Dense(units=1, activation='sigmoid')) # 编译模型 model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy']) # 训练模型 model.fit(X_train, y_train, batch_size=64, epochs=10, validation_data=(X_test, y_test), verbose=1) # 在测试集上评估模型 y_pred = model.predict(X_test) y_pred = np.round(y_pred).flatten() # 计算各项指标 auc_score = auc(y_test, y_pred) accuracy = accuracy_score(y_test, y_pred) f1score = f1_score(y_test, y_pred) recall = recall_score(y_test, y_pred) # 打印输出各项指标 print("AUC score:", auc_score) print("Accuracy:", accuracy) print("F1 score:", f1score) print("Recall:", recall) 这个代码有什么错误

1, 2, 3, 4, 5, 8, 7, 6, 9] [0, 1, 2, 3, 4, 5, 8, 7, 9, 6] [这段代码没有明显的语法错误，但是有一些潜在的问题： 1. 没有对数据进行标0, 1, 2, 3, 4, 5, 8, 9, 6, 7] 准化处理，可能会影响模型的性能。...

import numpy as np import pandas as pd from keras.models import Sequential from keras.layers import Dense from sklearn.model_selection import train_test_split # 读取数据集 data = pd.read_csv('img_16_10k.txt') X = data.iloc[:, :-1].values y = data.iloc[:, -1].values # 将标签进行one-hot编码 n_classes = len(np.unique(y)) y = np.eye(n_classes)[y] # 划分训练集和验证集 X_train, X_val, y_train, y_val = train_test_split(X, y, test_size=0.1) # 搭建神经网络模型 model = Sequential() model.add(Dense(128, input_dim=X.shape[1], activation='relu')) model.add(Dense(64, activation='relu')) model.add(Dense(n_classes, activation='softmax')) # 编译模型 model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy']) # 训练模型 epochs = 50 batch_size = 32 history = model.fit(X_train, y_train, epochs=epochs, batch_size=batch_size, validation_data=(X_val, y_val)) # 绘制损失值变化图像和准确率变化图像 import matplotlib.pyplot as plt plt.plot(history.history['loss'], label='train_loss') plt.plot(history.history['val_loss'], label='val_loss') plt.legend() plt.show() plt.plot(history.history['accuracy'], label='train_acc') plt.plot(history.history['val_accuracy'], label='val_acc') plt.legend() plt.show()从绘制的可视化途中看得出预测的模型过拟合，帮我重新优化模型，处理过拟合问题

from sklearn.model_selection import train_test_split from keras.regularizers import l2 # 读取数据集 data = pd.read_csv('img_16_10k.txt') X = data.iloc[:, :-1].values y = data.iloc[:, -1].values # 将...

探索numpy_class压缩包中的技术奥秘

import numpy as np # 从现有数据创建数组 data = [1, 2, 3, 4] arr = np.array(data) # 使用arange生成数组 arr_arange = np.arange(10) # 使用ones和zeros生成全1或全0的数组 arr_ones = np.ones((3, 3)) arr_...

理解Keras后端：K.prod与K.cast函数解析

from keras import backend as K input = K.placeholder((2, 3), dtype='float32') # Convert the input tensor to float16 output = K.cast(input, dtype='float16') 在这个例子中，input张量保持不变，而...

Origin教程009所需练习数据

相关推荐

下载numpy-1.22.4+mkl-cp38-cp38-win_amd64.whl提升深度学习效率

使用Keras加载H5模型权重：load_model与load_weights实战

import pandas as pd import numpy as np import tushare as ts from sklearn.preprocessing import MinMaxScaler import matplotlib.pyplot as plt import mplfinance as mpf from tensorflow.keras.models import Sequential from tensorflow.keras.layers import Dense, LSTM

import numpy import matplotlib.pyplot as plt from keras.models import Sequential from keras.layers import Dense from keras.layers import LSTM import pandas as pd import os from keras.models import Sequential, load_model

探索numpy_class压缩包中的技术奥秘

理解Keras后端：K.prod与K.cast函数解析

Origin教程009所需练习数据

最新推荐

Origin教程009所需练习数据

大模型的稀疏激活方法及其高效推理应用研究：基于dReLU激活函数

STM32F103+PWM+DMA精准控制输出脉冲的数量和频率 源程序

RStudio中集成Connections包以优化数据库连接管理

管理建模和仿真的文件

Keil uVision5全面精通指南

flink提交给yarn19个全量同步MYsqlCDC的作业，flink的配置参数怎样设置

PHP博客旅游的探索之旅

"互动学习：行动中的多样性与论文攻读经历"

【单片机编程实战】：掌握流水灯与音乐盒同步控制的高级技巧

STM32F103+PWM+DMA精准控制输出脉冲的数量和频率源程序