将我的数据拟合到 VGG16 cnn --Keras 时出现形状错误

Question

我想使用 VGG16 作为 cnn 使用数据增强和迁移学习对狗品种进行分类。

首先，我使用 keras 的 ImageDataGenerator 进行一些数据扩充

train_datagen = ImageDataGenerator(rotation_range = 30,
                               width_shift_range = 0.2,
                               height_shift_range = 0.2,
                               rescale = 1./255,
                               shear_range = 0.2,
                               zoom_range = 0.2,
                               horizontal_flip = True,
                               fill_mode = 'nearest')

train_generator = train_datagen.flow_from_directory('../data/train/',
                                                target_size = (224, 224),
                                                batch_size = batch_size,
                                                class_mode = 'categorical')

flow_from_directory 方法 return 是一个 DirectoryIterator，它产生 (x, y) 的元组，其中 x 是一个 numpy 数组，包含一批形状为 (batch_size, *target_size, channels) 和 y 是相应标签的 numpy 数组。由于这里 class_mode 是 caterogical，它应该 return y 的 2D one-hot 编码标签。

然后我进行迁移学习，仅删除最后一层，用具有 softmax 激活的密集层替换它。

model = VGG16(weights="imagenet", include_top=False, input_shape=(224, 224, 3))

for layer in model.layers:
    layer.trainable = False

x = model.output

predictions = Dense(120, activation='softmax')(x)

new_model = Model(inputs=model.input, outputs=predictions)

然后我将我的数据拟合到模型中：

new_model.fit_generator(train_generator,
                        steps_per_epoch = 6680 // batch_size,
                        epochs = 50,
                        validation_data = validation_generator,
                        validation_steps = 835 // batch_size,
                        verbose=2)

我得到错误：ValueError：检查目标时出错：预计 dense_3 有 4 个维度，但得到形状为 (16, 120)[ 的数组=14=]

我不知道问题出在哪里:(

感谢您的帮助！

Answer 1

VGG16的总结给出：

Layer (type)                 Output Shape              Param #   
=================================================================
input_1 (InputLayer)         [(None, 224, 224, 3)]     0         
_________________________________________________________________
block1_conv1 (Conv2D)        (None, 224, 224, 64)      1792      
_________________________________________________________________
block1_conv2 (Conv2D)        (None, 224, 224, 64)      36928     
_________________________________________________________________
block1_pool (MaxPooling2D)   (None, 112, 112, 64)      0         
_________________________________________________________________
block2_conv1 (Conv2D)        (None, 112, 112, 128)     73856     
_________________________________________________________________
block2_conv2 (Conv2D)        (None, 112, 112, 128)     147584    
_________________________________________________________________
block2_pool (MaxPooling2D)   (None, 56, 56, 128)       0         
_________________________________________________________________
block3_conv1 (Conv2D)        (None, 56, 56, 256)       295168    
_________________________________________________________________
block3_conv2 (Conv2D)        (None, 56, 56, 256)       590080    
_________________________________________________________________
block3_conv3 (Conv2D)        (None, 56, 56, 256)       590080    
_________________________________________________________________
block3_pool (MaxPooling2D)   (None, 28, 28, 256)       0         
_________________________________________________________________
block4_conv1 (Conv2D)        (None, 28, 28, 512)       1180160   
_________________________________________________________________
block4_conv2 (Conv2D)        (None, 28, 28, 512)       2359808   
_________________________________________________________________
block4_conv3 (Conv2D)        (None, 28, 28, 512)       2359808   
_________________________________________________________________
block4_pool (MaxPooling2D)   (None, 14, 14, 512)       0         
_________________________________________________________________
block5_conv1 (Conv2D)        (None, 14, 14, 512)       2359808   
_________________________________________________________________
block5_conv2 (Conv2D)        (None, 14, 14, 512)       2359808   
_________________________________________________________________
block5_conv3 (Conv2D)        (None, 14, 14, 512)       2359808   
_________________________________________________________________
block5_pool (MaxPooling2D)   (None, 7, 7, 512)         0         
=================================================================
Total params: 14,714,688
Trainable params: 14,714,688
Non-trainable params: 0
_________________________________________________________________

最后一层有 3-d 特征，在应用 Dense 和 softmax 之前需要将其展平。

在最后一个 Dense 层之前添加一个 Flatten()。

x = model.output

x = Flatten()(x) # add this line

predictions = Dense(120, activation='softmax')(x)

将我的数据拟合到 VGG16 cnn --Keras 时出现形状错误

Shape error when fitting my data to VGG16 cnn --Keras

python

keras

vgg-net