我正在尝试训练一个模型来解决多类分类问题。我遇到的问题是训练精度和验证精度在所有轮次中都没有变化。就像这样：
Train on 4642 samples, validate on 516 samplesEpoch 1/100- 1s - loss: 1.7986 - acc: 0.4649 - val_loss: 1.7664 - val_acc: 0.4942Epoch 2/100- 1s - loss: 1.6998 - acc: 0.5017 - val_loss: 1.7035 - val_acc: 0.4942Epoch 3/100- 1s - loss: 1.6956 - acc: 0.5022 - val_loss: 1.7000 - val_acc: 0.4942Epoch 4/100- 1s - loss: 1.6900 - acc: 0.5022 - val_loss: 1.6954 - val_acc: 0.4942Epoch 5/100- 1s - loss: 1.6931 - acc: 0.5017 - val_loss: 1.7058 - val_acc: 0.4942...Epoch 98/100- 1s - loss: 1.6842 - acc: 0.5022 - val_loss: 1.6995 - val_acc: 0.4942Epoch 99/100- 1s - loss: 1.6844 - acc: 0.5022 - val_loss: 1.6977 - val_acc: 0.4942Epoch 100/100- 1s - loss: 1.6838 - acc: 0.5022 - val_loss: 1.6934 - val_acc: 0.4942我在使用Keras时的代码：
y_train = to_categorical(y_train, num_classes=11)X_train, X_test, Y_train, Y_test = train_test_split(x_train, y_train, test_size=0.1, random_state=42)model = Sequential()model.add(Dense(64, init='normal', activation='relu', input_dim=160))model.add(Dropout(0.3))model.add(Dense(32, init='normal', activation='relu'))model.add(BatchNormalization())model.add(Dense(11, init='normal', activation='softmax'))model.summary()print("[INFO] compiling model...")model.compile(optimizer=keras.optimizers.Adam(lr=0.01, beta_1=0.9, beta_2=0.999, epsilon=None, decay=0.0, amsgrad=False), loss='categorical_crossentropy', metrics=['accuracy'])print("[INFO] training network...")model.fit(X_train, Y_train, epochs=100, batch_size=32, verbose=2, validation_data = (X_test, Y_test))请帮助我。谢谢！
回答：
我曾经遇到过类似的问题。对我来说，确保x_train中没有太多缺失值（需要用代表未知的值或中位数来填充），删除那些确实没有帮助的列（所有值都相同），以及对x_train数据进行归一化都很有帮助。
来自我的数据/模型的示例，
# 加载数据 x_main = pd.read_csv("glioma DB X.csv") y_main = pd.read_csv("glioma DB Y.csv") # 用中位数填充（以后需要改进，目前未完成） fill_median =['Surgery_SBRT','df','Dose','Ki67','KPS','BMI','tumor_size'] x_main[fill_median] = x_main[fill_median].fillna(x_main[fill_median].median()) x_main['Neurofc'] = x_main['Neurofc'].fillna(2) x_main['comorbid'] = x_main['comorbid'].fillna(int(x_main['comorbid'].median())) # 删除手术相关列 x_main = x_main.drop(['Surgery'], axis=1) # 归一化所有x x_main_normalized = x_main.apply(lambda x: (x-np.mean(x))/(np.std(x)+1e-10))