Keras CNN 立即过拟合，而不是数据集问题

Question

一直在尝试构建 CNN 来对 MFCC 数据进行分类，但模型立即过拟合。

数据：

• 18 000 个文件（80% 训练，20% 测试）
• 5 个标签

数据中的 5 个类别都是等量的。这个模型被创建用来处理比 18k 更多的文件，所以我被告知要尽我所能减少网络，这可能会有所帮助。

将过滤器从 (3,3) 减少到 (1,1)，尝试减少隐藏神经元数量甚至减少层数量。我只是卡住了，有人有什么想法吗？

无论发生什么，在使用测试数据测量准确度时，我的准确度从未超过 60-65%。

型号代码：

time_start_train = time.time()
i = Input(shape=(feature_count,feature_count,1))
m = Conv2D(16, d, activation='elu', padding='same')(i)
m = MaxPooling2D()(m)
m = Conv2D(32, d, activation='elu', padding='same')(m)
m = MaxPooling2D()(m)
m = Conv2D(64, d, activation='elu', padding='same')(m)
m = MaxPooling2D()(m)
m = Conv2D(128, d, activation='elu', padding='same')(m)
m = MaxPooling2D()(m)
m = Conv2D(256, d, activation='elu', padding='same')(m)
m = MaxPooling2D()(m)
m = Flatten()(m)
m = Dense(512, activation='elu')(m)
m = Dropout(0.2)(m)
o = Dense(out_dim, activation='softmax')(m)

model = Model(inputs=i, outputs=o)

model.compile(loss='categorical_crossentropy', optimizer=Nadam(lr=1e-3), metrics=['accuracy'])

history = model.fit(data_train[0], data_train[1], epochs=10, verbose=1, validation_split = 0.1, shuffle=True)

模型总结：

    _________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
input_1 (InputLayer)         (None, 192, 192, 1)       0         
_________________________________________________________________
conv2d_1 (Conv2D)            (None, 192, 192, 16)      32        
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 96, 96, 16)        0         
_________________________________________________________________
conv2d_2 (Conv2D)            (None, 96, 96, 32)        544       
_________________________________________________________________
max_pooling2d_2 (MaxPooling2 (None, 48, 48, 32)        0         
_________________________________________________________________
conv2d_3 (Conv2D)            (None, 48, 48, 64)        2112      
_________________________________________________________________
max_pooling2d_3 (MaxPooling2 (None, 24, 24, 64)        0         
_________________________________________________________________
conv2d_4 (Conv2D)            (None, 24, 24, 128)       8320      
_________________________________________________________________
max_pooling2d_4 (MaxPooling2 (None, 12, 12, 128)       0         
_________________________________________________________________
conv2d_5 (Conv2D)            (None, 12, 12, 256)       33024     
_________________________________________________________________
max_pooling2d_5 (MaxPooling2 (None, 6, 6, 256)         0         
_________________________________________________________________
flatten_1 (Flatten)          (None, 9216)              0         
_________________________________________________________________
dense_1 (Dense)              (None, 512)               4719104   
_________________________________________________________________
dropout_1 (Dropout)          (None, 512)               0         
_________________________________________________________________
dense_2 (Dense)              (None, 5)                 2565      
=================================================================
Total params: 4,765,701
Trainable params: 4,765,701
Non-trainable params: 0

MFCC example (192x192)

model accuracy

model loss

Answer 1

尝试应用 L1/L2 正则化。

Answer 2

如果您对 ML/DL 模型没有深入了解，请使用 AUTOML 而不是 KERAS。在 AUTOML 中，无需过多考虑不同的参数。