diff --git a/main.py b/main.py index b219909..1247b80 100644 --- a/main.py +++ b/main.py @@ -1,20 +1,20 @@ +from tqdm import tqdm +from sklearn.preprocessing import MinMaxScaler +from keras.layers import Dropout +from keras.callbacks import TensorBoard, LearningRateScheduler +from keras import regularizers +import matplotlib.pyplot as plt +import tensorflow as tf import pandas as pd import numpy as np import os import warnings warnings.filterwarnings('ignore') -import tensorflow as tf tf.compat.v1.logging.set_verbosity(tf.compat.v1.logging.ERROR) -import matplotlib.pyplot as plt -from keras import regularizers -from keras.callbacks import TensorBoard, LearningRateScheduler -from keras.layers import Dropout -from sklearn.preprocessing import MinMaxScaler -from tqdm import tqdm def data_read(data_address): - + df = pd.read_csv(data_address) label_mapping = {label: idx for idx, label in enumerate(df['Problem'].unique())} @@ -29,64 +29,72 @@ def data_read(data_address): # 转换为时间序列数据格式 time_steps = 34 X_series, Y_series = [], [] - for i in range(0, len(X) - time_steps): + i = 0 + while i < len(X): X_series.append(X[i:(i + time_steps)]) Y_series.append(Y[i + time_steps - 1]) - + i += time_steps + return np.array(X_series), np.array(Y_series) - + # 编写绘图函数，画出训练集电压数据 def plant_for_voltage(x_train_new, x_train_orginal, gamma, learning_rate, y_train, different_location): - # 绘制X_train的图形 - for i in different_location: - if i % 100 == 0: - plt.figure() - time_Step = list(range(0, 34)) - plt.plot(time_Step, - x_train_new[i]) - # 添加标题和标签 - plt.title(f'gamma:{gamma},learning_rate:{learning_rate},Y:{y_train[i]}') - plt.xlabel('time_step') - plt.ylabel('voltage') - try: - os.makedirs(f'Liu/picture/gamma{gamma} learningrate{learning_rate}') - except FileExistsError: - pass - plt.savefig(f'Liu/picture/gamma{gamma} learningrate{learning_rate}/X_train_new_{i}.png') - plt.close() - plt.clf() - - # 画出原始图像 - plt.figure() - time_Step = list(range(0, 34)) - plt.plot(time_Step, - x_train_orginal[i]) - # 添加标题和标签 - plt.title(f'gamma:{gamma},learning_rate:{learning_rate},Y:{y_train[i]}') - plt.xlabel('time_step') - plt.ylabel('voltage') - try: - os.makedirs(f'Liu/picture/gamma{gamma} learningrate{learning_rate}') - except FileExistsError: - pass - plt.savefig(f'Liu/picture/gamma{gamma} learningrate{learning_rate}/X_train_{i}.png') - plt.close() - plt.clf() + # 绘制X_train的图形 + for i in different_location: + if i % 100 == 0: + plt.figure() + time_Step = list(range(0, 34)) + plt.plot(time_Step, + x_train_new[i]) + # 添加标题和标签 + plt.title( + f'gamma:{gamma},learning_rate:{learning_rate},Y:{y_train[i]}') + plt.xlabel('time_step') + plt.ylabel('voltage') + try: + os.makedirs( + f'Liu/picture/gamma{gamma} learningrate{learning_rate}') + except FileExistsError: + pass + plt.savefig( + f'Liu/picture/gamma{gamma} learningrate{learning_rate}/X_train_new_{i}.png') + plt.close() + plt.clf() + # 画出原始图像 + plt.figure() + time_Step = list(range(0, 34)) + plt.plot(time_Step, + x_train_orginal[i]) + # 添加标题和标签 + plt.title( + f'gamma:{gamma},learning_rate:{learning_rate},Y:{y_train[i]}') + plt.xlabel('time_step') + plt.ylabel('voltage') + try: + os.makedirs( + f'Liu/picture/gamma{gamma} learningrate{learning_rate}') + except FileExistsError: + pass + plt.savefig( + f'Liu/picture/gamma{gamma} learningrate{learning_rate}/X_train_{i}.png') + plt.close() + plt.clf() def if_diff(a, b): - # 比较两个数组相同位置上的元素是否相等 - diff = np.where(a != b) - - list_diff = [] + # 比较两个数组相同位置上的元素是否相等 + diff = np.where(a != b) + + list_diff = [] + + # 打印不同元素的索引及其对应的元素 + for i in range(len(diff[0])): + idx = (diff[0][i], diff[1][i]) + list_diff.append(idx[0]) + return list_diff - # 打印不同元素的索引及其对应的元素 - for i in range(len(diff[0])): - idx = (diff[0][i], diff[1][i]) - list_diff.append(idx[0]) - return list_diff X_train, Y_train = data_read( 'Liu\data\VOLTAGE-QUALITY-CLASSIFICATION-MODEL--main\Voltage Quality.csv') @@ -122,7 +130,7 @@ model = tf.keras.models.Sequential([ tf.keras.layers.SimpleRNN(100), Dropout(0.2), tf.keras.layers.Dense(n_classes, activation='relu', - ) # kernel_regularizer=regularizers.l2(0.3) + ) # kernel_regularizer=regularizers.l2(0.3) ]) # 编译模型 @@ -132,30 +140,39 @@ model.compile( metrics=['accuracy']) # 定义学习率指数递减的函数 + + def lr_schedule(epoch): initial_learning_rate = 0.01 decay_rate = 0.1 decay_steps = 250 - new_learning_rate = initial_learning_rate * decay_rate ** (epoch / decay_steps) + new_learning_rate = initial_learning_rate * \ + decay_rate ** (epoch / decay_steps) return new_learning_rate + # 定义学习率调度器 lr_scheduler = LearningRateScheduler(lr_schedule) -# Save initial weights -initial_weights = model.get_weights() - # TensorBoard 回调 log_dir = "logs/fit" tensorboard_callback = TensorBoard(log_dir=log_dir, histogram_freq=1) +# 训练模型，添加 TensorBoard 回调 +model.fit(X_train, Y_train, epochs=500, + batch_size=32, callbacks=[tensorboard_callback, lr_scheduler]) + +# 评估模型 +loss, accuracy = model.evaluate(X_test, Y_test) +print("Test original accuracy:", accuracy) + # 制作扰动数据 -# 转换X_train和Y_train为TensorFlow张量 -X_train_tensor = tf.convert_to_tensor(X_train, dtype=tf.float64) -Y_train_tensor = tf.convert_to_tensor(Y_train, dtype=tf.int32) +# 转换X_test和Y_test为TensorFlow张量 +X_train_tensor = tf.convert_to_tensor(X_test, dtype=tf.float64) +Y_train_tensor = tf.convert_to_tensor(Y_test, dtype=tf.int32) # 使用tf.GradientTape来计算梯度 with tf.GradientTape() as tape: @@ -176,7 +193,7 @@ accuracy_per_gamma = {} flattened_gradients = tf.reshape(gradients, [-1]) # 选择最大的γ * |X|个梯度 -for gamma in tqdm([0.6, 0.7, 0.8, 0.9, 0.99]): +for gamma in [0.05, 0.1, 0.2, 0.4]: num_gradients_to_select = int( gamma * tf.size(flattened_gradients, out_type=tf.dtypes.float32)) top_gradients_indices = tf.argsort(flattened_gradients, direction='DESCENDING')[ @@ -200,33 +217,23 @@ for gamma in tqdm([0.6, 0.7, 0.8, 0.9, 0.99]): # 创建准确率列表 accuracy_list = [] - for learning_rate in tqdm([0.1, 0.2, 0.3, 0.4, 0.5]): + for learning_rate in [0.1, 0.2, 0.3, 0.4, 0.5]: # 应用学习率到梯度 - scaled_gradients = (learning_rate * 100) * updated_gradients + scaled_gradients = (learning_rate * 17000) * updated_gradients # 使用缩放后的梯度更新X_train_tensor X_train_updated = tf.add(X_train_tensor, scaled_gradients) X_train_updated = X_train_updated.numpy() - - list_diff = if_diff(X_train, X_train_updated) - + # 显示扰动数据和原始数据的可视化图像 # plant_for_voltage(X_train_updated, X_train, gamma, learning_rate, Y_train, list_diff) - - # Reset model weights to initial weights - model.set_weights(initial_weights) - - # 训练模型，添加 TensorBoard 回调 - history = model.fit(X_train_updated, Y_train, epochs=500, - batch_size=32, callbacks=[tensorboard_callback, lr_scheduler], verbose=0) # 评估模型 - loss, accuracy = model.evaluate(X_test, Y_test) + loss, accuracy = model.evaluate(X_train_updated, Y_test) print(f"Accuracy gamma: {gamma},learning:{learning_rate}", accuracy) # 记录准确率 accuracy_list.append(accuracy) - # 记录该gamma下的准确率 accuracy_per_gamma[gamma] = accuracy_list @@ -254,5 +261,3 @@ plt.legend() # 显示图像 plt.show() - -# tensorboard --logdir logs/fit \ No newline at end of file