如何提高 CNN 模型的验证准确度

Posted 2023-02-16

【中文标题】如何提高 CNN 模型的验证准确度

【英文标题】：How to increase the validation accuracy in CNN model

【发布时间】：2022-01-12 03:39:43

【问题描述】：

我想建立一个 CNN 模型来将唐氏综合症的面孔与正常人脸进行分类，然后通过另一个模型对性别进行分类。我尝试更改层数、节点数、时期数、优化器数。另外，我尝试了彩色图像和灰度。该数据集是 799 张图像，包括正常和唐氏综合症。 这是我的代码

model.add(Conv2D(filters=16, kernel_size=(5,5), activation="relu",
                 input_shape=X_train[0].shape))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2,2), strides=(2,2))) 
model.add(Dropout(0.2))

model.add(Conv2D(filters=32, kernel_size=(5,5), activation='relu'))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2,2), strides=(2,2)))
model.add(Dropout(0.3))

model.add(Conv2D(filters=64, kernel_size=(5,5), activation="relu"))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2,2), strides=(2,2)))
model.add(Dropout(0.3))

model.add(Conv2D(filters=64, kernel_size=(5,5), activation="relu"))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2,2), strides=(2,2)))
model.add(Dropout(0.2))

model.add(Flatten())

#Two dense layers and then output layer
model.add(Dense(256, activation='relu'))
model.add(BatchNormalization())
model.add(Dropout(0.5)) #Using dropouts to make sure that 
                        #the model isn't overfitting

model.add(Dense(128, activation='relu'))
model.add(BatchNormalization())
model.add(Dropout(0.5))


model.add(Dense(2, activation='softmax'))

我尝试将最后一个激活层从 softmax 更改为 sigmoid，反之亦然，但没有成功。输入图像的大小为 200x200

Model: "sequential_4"
_________________________________________________________________
 Layer (type)                Output Shape              Param #   
=================================================================
 conv2d_16 (Conv2D)          (None, 196, 196, 16)      416       
                                                                 
 batch_normalization_24 (Bat  (None, 196, 196, 16)     64        
 chNormalization)                                                
                                                                 
 max_pooling2d_16 (MaxPoolin  (None, 98, 98, 16)       0         
 g2D)                                                            
                                                                 
 dropout_24 (Dropout)        (None, 98, 98, 16)        0         
                                                                 
 conv2d_17 (Conv2D)          (None, 94, 94, 32)        12832     
                                                                 
 batch_normalization_25 (Bat  (None, 94, 94, 32)       128       
 chNormalization)                                                
                                                                 
 max_pooling2d_17 (MaxPoolin  (None, 47, 47, 32)       0         
 g2D)                                                            
                                                                 
 dropout_25 (Dropout)        (None, 47, 47, 32)        0         
                                                                 
 conv2d_18 (Conv2D)          (None, 43, 43, 64)        51264     
                                                                 
 batch_normalization_26 (Bat  (None, 43, 43, 64)       256       
 chNormalization)                                                
                                                                 
 max_pooling2d_18 (MaxPoolin  (None, 21, 21, 64)       0         
 g2D)                                                            
                                                                 
 dropout_26 (Dropout)        (None, 21, 21, 64)        0         
                                                                 
 conv2d_19 (Conv2D)          (None, 17, 17, 64)        102464    
                                                                 
 batch_normalization_27 (Bat  (None, 17, 17, 64)       256       
 chNormalization)                                                
                                                                 
 max_pooling2d_19 (MaxPoolin  (None, 8, 8, 64)         0         
 g2D)                                                            
                                                                 
 dropout_27 (Dropout)        (None, 8, 8, 64)          0         
                                                                 
 flatten_4 (Flatten)         (None, 4096)              0         
                                                                 
 dense_12 (Dense)            (None, 256)               1048832   
                                                                 
 batch_normalization_28 (Bat  (None, 256)              1024      
 chNormalization)                                                
                                                                 
 dropout_28 (Dropout)        (None, 256)               0         
                                                                 
 dense_13 (Dense)            (None, 128)               32896     
                                                                 
 batch_normalization_29 (Bat  (None, 128)              512       
 chNormalization)                                                
                                                                 
 dropout_29 (Dropout)        (None, 128)               0         
                                                                 
 dense_14 (Dense)            (None, 2)                 258       
                                                                 
=================================================================
Total params: 1,251,202
Trainable params: 1,250,082
Non-trainable params: 1,120
_________________________________________________________________

model.compile(optimizer='Adam',  loss='binary_crossentropy', metrics=['accuracy'])
# split train and VALID data
X_train, X_valid, y_train, y_valid = train_test_split(X_train, y_train, test_size=0.15)

我想将准确率至少提高到 70，但我达到的最高分数是 47%

history = model.fit(X_train, y_train, epochs=50, validation_data=(X_valid, y_valid), batch_size=64)

Epoch 1/50
5/5 [==============================] - 23s 4s/step - loss: 0.9838 - accuracy: 0.5390 - val_loss: 0.6931 - val_accuracy: 0.4800
Epoch 2/50
5/5 [==============================] - 21s 4s/step - loss: 0.8043 - accuracy: 0.6348 - val_loss: 0.7109 - val_accuracy: 0.4800
Epoch 3/50
5/5 [==============================] - 21s 4s/step - loss: 0.6745 - accuracy: 0.6915 - val_loss: 0.7554 - val_accuracy: 0.4800
Epoch 4/50
5/5 [==============================] - 21s 4s/step - loss: 0.6429 - accuracy: 0.7589 - val_loss: 0.8261 - val_accuracy: 0.4800
Epoch 5/50
5/5 [==============================] - 21s 4s/step - loss: 0.5571 - accuracy: 0.8014 - val_loss: 0.9878 - val_accuracy: 0.4800

有什么办法可以增加更多吗？以及如何组合两个模型？ 任何帮助将不胜感激。非常感谢。

【参考方案1】：

尝试图像增强。 我是说;很明显，模型过度拟合了数据

甚至可以更改train_test_split 比率（增加它。）

【参考方案2】：

我认为发生了两件事之一。训练数据会指向过度拟合，但考虑到模型中的辍学量，我不会怀疑是这种情况。我认为可能是训练数据的概率分布与验证数据的概率分布明显不同。如果您的训练样本很少，就会发生这种情况。那么，您的 2 个班级中的每个班级有多少个训练样本？如果每个类少于 120 个样本，则使用图像增强来创建更多训练样本。您是如何生成验证图像的？如果您有单独的验证图像，最好将训练集与验证集结合起来，然后使用 sklearn train_test_split 将组合数据随机拆分为训练集和验证集。注意：只对训练集使用扩充，而不是验证集。我还建议您使用 Keras 回调在高原上降低学习率来实现可调整的学习率。文档是 here. 下面的代码显示了我使用的设置

rlronp=tf.keras.callbacks.ReduceLROnPlateau(monitor="val_loss", factor=0.5, 
                                            patience=1,  verbose=1)

还建议使用 Keras 回调 Early Stopping，文档是 here. 下面的代码显示了我的实现

estop=tf.keras.callbacks.EarlyStopping( monitor="val_loss",  patience=3,
                                         verbose=1, 
                                         restore_best_weights=True)

在 model.fit 中包含代码

history=model.fit(.....  callbacks[estop, rlronp])

将要运行的 epoch 数设置为一个相当大的值。