Skip to main content
 首页 » 编程设计

python之CNN with keras,精度保持不变,没有提高

2024年12月31日11grandyang

我正在尝试通过 finetuning 训练我的模型预训练 model (vggface)。我的模型有 12 个类,有 1774 个训练图像和 313 个验证图像,每个类有大约 150 个图像。 到目前为止,我已经能够使用 keras 中的以下脚本实现大约 80% 的最大准确度:

img_width, img_height = 224, 224 
 
vggface = VGGFace(model='resnet50', include_top=False, input_shape=(img_width, img_height, 3)) 
 
last_layer = vggface.get_layer('avg_pool').output 
x = Flatten(name='flatten')(last_layer) 
out = Dense(12, activation='softmax', name='classifier')(x) 
custom_vgg_model = Model(vggface.input, out) 
 
 
# Create the model 
model = models.Sequential() 
 
# Add the convolutional base model 
model.add(custom_vgg_model) 
 
train_datagen = ImageDataGenerator( 
      rescale=1./255, 
      rotation_range=20, 
      width_shift_range=0.2, 
      height_shift_range=0.2, 
      horizontal_flip=True, 
      fill_mode='nearest') 
 
validation_datagen = ImageDataGenerator(rescale=1./255) 
 
# Change the batchsize according to your system RAM 
train_batchsize = 16 
val_batchsize = 16 
 
train_generator = train_datagen.flow_from_directory( 
        train_data_path, 
        target_size=(img_width, img_height), 
        batch_size=train_batchsize, 
        class_mode='categorical') 
 
validation_generator = validation_datagen.flow_from_directory( 
        validation_data_path, 
        target_size=(img_width, img_height), 
        batch_size=val_batchsize, 
        class_mode='categorical', 
        shuffle=True) 
 
# Compile the model 
model.compile(loss='categorical_crossentropy', 
              optimizer=optimizers.SGD(lr=1e-3), 
              metrics=['acc']) 
# Train the model 
history = model.fit_generator( 
      train_generator, 
      steps_per_epoch=train_generator.samples/train_generator.batch_size , 
      epochs=50, 
      validation_data=validation_generator, 
      validation_steps=validation_generator.samples/validation_generator.batch_size, 
      verbose=1) 

到目前为止我已经尝试过:

  • 将 epochs 增加到 100。
  • 通过改变学习率。
  • 通过将优化器更改为 rmsprop。但这给出了更糟糕的结果。
  • 有人建议我添加更多带有 dropout 和 batch normalization 的 FC 层。我 这样做了,验证准确率仍然在 79% 左右。

这是我的零钱:

vggface = VGGFace(model='resnet50', include_top=False, input_shape=(img_width, img_height, 3)) 
 
#vgg_model = VGGFace(include_top=False, input_shape=(224, 224, 3)) 
 
last_layer = vggface.get_layer('avg_pool').output 
x = Flatten(name='flatten')(last_layer) 
xx = Dense(256, activation = 'relu')(x) 
x1 = BatchNormalization()(xx) 
x2 = Dropout(0.3)(xx) 
 
y = Dense(256, activation = 'relu')(x2) 
yy = BatchNormalization()(y) 
y1 = Dropout(0.3)(y) 
 
z = Dense(256, activation = 'relu')(y1) 
zz = BatchNormalization()(z) 
z1 = Dropout(0.6)(zz) 
 
x3 = Dense(12, activation='softmax', name='classifier')(z1) 
 
custom_vgg_model = Model(vggface.input, x3) 

我现在按照 SymbolixAU 的建议将我的激活设为 softmax here . val acc 现在仍然是 81%,而 training acc 接近 99%

我做错了什么?

请您参考如下方法:

小心你的连接。在前两个 block 中,BatchNormalization 没有连接到 dropout。改变两个第一个dropout的输入。

xx = Dense(256, activation = 'relu')(x) 
x1 = BatchNormalization()(xx) 
x2 = Dropout(0.3)(x1) 
 
y = Dense(256, activation = 'relu')(x2) 
yy = BatchNormalization()(y) 
y1 = Dropout(0.3)(yy) 

您提供的值暗示您的网络过度拟合。批量归一化或添加更多 dropout 可能会有所帮助。但是,鉴于图像数量较少,您真的应该尝试图像增强来增加训练图像的数量。