模型蒸餾 import pandas as pd import tensorflow as tf from sklearn.model_selection import train_test_split from sklearn.metrics import confusion_matrix, f1_score from sklearn.metrics import roc_auc_score import numpy as np import random # 設定 Python 的隨機種子 seed_value = 42 np.random.seed(seed_value) random.seed(seed_value) # 設定 TensorFlow 的全域性隨機種子 tf.random.set_seed(seed_value) def action_recall_accuracy(y_pred, y_true): cm = confusion_matrix(y_true, y_pred) # 計算每個類別的準確率和召回率 num_classes = cm.shape[0] accuracy = [] recall = [] for i in range(num_classes): # 計算準確率：預測正確的樣本數 / 實際屬於該類別的樣本數 acc = cm[i, i] / sum(cm[i, :]) accuracy.append(acc) # 計算召回率：預測正確的樣本數 / 預測為該類別的樣本數 rec = cm[i, i] / sum(cm[:, i]) recall.append(rec) # 列印結果 for i in range(num_classes): print(f"類別 {i} 的準確率: {accuracy[i]:.3f}") print(f"類別 {i} 的召回率: {recall[i]:.3f}") scores = [] for i in range(num_classes): # 計算F1分數 f1 = f1_score(y_true, y_pred, average=None)[i] scores.append(f1) # 列印F1分數 print(f"類別 {i} 的F1分數: {scores[i]:.3f}") # 列印各類別F1-score的平均值 average_f1 = sum(scores) / len(scores) print(f"各類別F1-score的平均值: {average_f1:.3f}") # 讀取訓練檔案 train_data = pd.read_csv('train_new.csv') # 將特徵與標籤分開 X = train_data.drop('label', axis=1) y = train_data['label'] # 資料預處理 X = X.astype('float32') y = y.astype('int32') # 劃分訓練集和驗證集 X_train, X_val, y_train, y_val = train_test_split(X, y, test_size=0.001, random_state=42) # 讀取測試檔案 test_data = pd.read_csv('test_new.csv') # 對測試樣本進行預測 X_test = test_data.drop('label', axis=1).astype('float32') true_labels = test_data['label'].astype('int32') def custom_loss(y_true, y_pred, soft_labels, T, rate): # Adjust the predictions and soft_labels with temperature T y_pred_T = tf.nn.softmax(tf.keras.layers.Lambda(lambda x: x / T)(y_pred)) soft_labels_T = tf.nn.softmax(tf.keras.layers.Lambda(lambda x: x / T)(soft_labels)) # Compute the binary cross-entropy loss for hard labels hard_loss = tf.keras.losses.binary_crossentropy(tf.reshape(y_true, (-1, 1)), y_pred) # Compute the binary cross-entropy loss for soft labels, scaled by T^2 soft_loss = tf.keras.losses.binary_crossentropy(soft_labels_T, y_pred_T) * (T ** 2) return hard_loss * rate + soft_loss * (1 - rate) optimizer = tf.keras.optimizers.Adam(learning_rate=0.001, beta_1=0.9, beta_2=0.999, epsilon=1e-07, amsgrad=True, name='Adam') optimizer_teacher = tf.keras.optimizers.Adam(learning_rate=0.001, beta_1=0.9, beta_2=0.999, epsilon=1e-07, amsgrad=True, name='Adam') @tf.function def train_step(batch_X_student, batch_X_teacher, model_student, model_teacher, batch_y, T, rate): with tf.GradientTape(persistent=True) as tape: predictions = model_student(batch_X_student, training=True) batch_soft_labels = model_teacher(batch_X_teacher, training=True) loss = custom_loss(batch_y, predictions, batch_soft_labels, T=T, rate=rate) teacher_loss = tf.keras.losses.binary_crossentropy(tf.reshape(batch_y, (-1, 1)), batch_soft_labels) gradients = tape.gradient(loss, model_student.trainable_variables) optimizer.apply_gradients(zip(gradients, model_student.trainable_variables)) gradients_teacher = tape.gradient(teacher_loss, model_teacher.trainable_variables) optimizer_teacher.apply_gradients(zip(gradients_teacher, model_teacher.trainable_variables)) del tape # 刪除持久化tape以釋放資源 return loss, teacher_loss def build_student_model(): # 構建學生模型 student_input = tf.keras.layers.Input(shape=(60,), name='relevance_input', dtype='float32') x = tf.keras.layers.Dense(128, activation='relu')(student_input) x = tf.keras.layers.Dense(64, activation='relu')(x) x = tf.keras.layers.Dense(32, activation='relu')(x) outputs = tf.keras.layers.Dense(1, activation='sigmoid', name='student_output')(x) student_model = tf.keras.Model(inputs=student_input, outputs=outputs) return student_model def build_teacher_model(): # 構建教師模型 teacher_input = tf.keras.layers.Input(shape=(124,), name='relevance_input', dtype='float32') x = tf.keras.layers.Dense(128, activation='relu')(teacher_input) x = tf.keras.layers.Dense(64, activation='relu')(x) x = tf.keras.layers.Dense(32, activation='relu')(x) outputs = tf.keras.layers.Dense(1, activation='sigmoid', name='teacher_output')(x) teacher_model = tf.keras.Model(inputs=teacher_input, outputs=outputs) return teacher_model class DataGenerator(tf.keras.utils.Sequence): def __init__(self, X_data, y_data, batch_size): self.X_data_student = X_data.iloc[:, :60] self.X_data_teacher = X_data self.y_data = y_data self.batch_size = batch_size # self.on_epoch_end() # Shuffle data at the end of each epoch def __len__(self): return int(np.ceil(len(self.y_data) / self.batch_size)) def __getitem__(self, index): batch_X_student = self.X_data_student[index * self.batch_size:(index + 1) * self.batch_size].to_numpy() batch_X_teacher = self.X_data_teacher[index * self.batch_size:(index + 1) * self.batch_size].to_numpy() batch_y = self.y_data[index * self.batch_size:(index + 1) * self.batch_size].to_numpy() return batch_X_student, batch_X_teacher, batch_y # def on_epoch_end(self): # # Shuffle the data # indices = np.arange(len(self.y_data)) # np.random.shuffle(indices) # self.X_data_student = self.X_data_student.iloc[indices] # self.X_data_teacher = self.X_data_teacher.iloc[indices] # self.y_data = self.y_data.iloc[indices] # 建立資料生成器 train_generator = DataGenerator(X_train, y_train, batch_size=16) # 構建teacher和student模型 student_model = build_student_model() teacher_model = build_teacher_model() # loss中溫度引數T和損失比例引數的調參 t_list = [1, 2, 3, 4, 5, 6, 7,8,0.5] rate_list = [0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9] for t in t_list: for rate in rate_list: print("當前的引數T和rate值為：", t, rate) for epoch in range(11): print("...............................epoch:", epoch) # 使用自定義資料生成器進行訓練 for batch_X_student, batch_X_teacher, batch_y in train_generator: loss, teacher_loss = train_step(batch_X_student, batch_X_teacher, student_model, teacher_model, batch_y, t, rate) # # 在每個epoch之後打亂資料 # train_generator.on_epoch_end() predictions = student_model.predict(X_test.iloc[:, :60]) auc = roc_auc_score(list(np.array(true_labels)), predictions[:, 0]) print(f"Testing AUC: {auc}") # 使用最佳閾值進行預測 pred_labels = [int(i > 0.5) for i in predictions[:, 0]] true_labels_list = list(np.array(true_labels)) action_recall_accuracy(pred_labels, true_labels_list) if epoch == 10: student_model.save(f"./dnn2_student_model", save_format='tf') print("||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||")