预训练模型的 Keras 输入形状不变

Question

我正在尝试在 Keras 中使用迁移学习。我已经为不同的任务训练了一个模型，但现在我想将它用于类似的任务，但输入和输出形状不同。我使用 load_model 加载了经过训练的模型。我的原始模型是：

model = Sequential()
model.add(Conv2D(32, (5,5), input_shape=(28,28,1), padding='same', activation='relu'))
model.add(Conv2D(32, (5,5), padding='same', activation='relu'))
model.add(BatchNormalization())
model.add(Dropout(0.25))
model.add(MaxPool2D(padding='same', strides=2))
model.add(Conv2D(128, (5, 5), padding='same', activation='relu'))
model.add(BatchNormalization())
model.add(Dropout(0.25))
model.add(MaxPool2D(padding='same', strides=2))
model.add(Conv2D(64, (4,4), padding='same', activation='relu'))
model.add(Conv2D(64, (4,4), padding='same', activation='relu'))
model.add(BatchNormalization())
model.add(Dropout(0.25))
model.add(MaxPool2D(padding='same', strides=2))
model.add(Flatten())
model.add(Dense(256, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(26, activation='softmax'))
rmsdrp = optimizers.rmsprop(lr=0.001, epsilon=1e-08)

model.compile( loss = "categorical_crossentropy", 
               optimizer = rmsdrp, 
               metrics=['accuracy']
             )

然后，我做了以下输出：

    model.pop()
    model.add(Dense(3*168,activation='softmax'))
    model.add(Reshape((3,168)))

这是有效的。对于输入，我这样做了：

model.layers[0] = Input(shape=(137,236))

但是当我打印出模型摘要时，它仍然给出了模型之前的输入形状。我究竟做错了什么？我还应该如何更改输入形状？这是最后的模型总结：

Model: "sequential_1"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv2d_1 (Conv2D)            (None, 28, 28, 32)        832       
_________________________________________________________________
conv2d_2 (Conv2D)            (None, 28, 28, 32)        25632     
_________________________________________________________________
batch_normalization_1 (Batch (None, 28, 28, 32)        128       
_________________________________________________________________
dropout_1 (Dropout)          (None, 28, 28, 32)        0         
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 14, 14, 32)        0         
_________________________________________________________________
conv2d_3 (Conv2D)            (None, 14, 14, 128)       102528    
_________________________________________________________________
batch_normalization_2 (Batch (None, 14, 14, 128)       512       
_________________________________________________________________
dropout_2 (Dropout)          (None, 14, 14, 128)       0         
_________________________________________________________________
max_pooling2d_2 (MaxPooling2 (None, 7, 7, 128)         0         
_________________________________________________________________
conv2d_4 (Conv2D)            (None, 7, 7, 64)          131136    
_________________________________________________________________
conv2d_5 (Conv2D)            (None, 7, 7, 64)          65600     
_________________________________________________________________
batch_normalization_3 (Batch (None, 7, 7, 64)          256       
_________________________________________________________________
dropout_3 (Dropout)          (None, 7, 7, 64)          0         
_________________________________________________________________
max_pooling2d_3 (MaxPooling2 (None, 4, 4, 64)          0         
_________________________________________________________________
flatten_1 (Flatten)          (None, 1024)              0         
_________________________________________________________________
dense_1 (Dense)              (None, 256)               262400    
_________________________________________________________________
dropout_4 (Dropout)          (None, 256)               0         
_________________________________________________________________
dense_2 (Dense)              (None, 504)               129528    
_________________________________________________________________
reshape_1 (Reshape)          (None, 3, 168)            0         
=================================================================
Total params: 595,706
Trainable params: 595,258
Non-trainable params: 448
_________________________________________________________________

Answer 1

看起来问题出在 Input(shape=(137,236)) 的使用上，它通常用于功能模型，而不是顺序模型。您可以通过本质上更改模型来更改输入层：

input = Input(shape=(137,236))
x = model.layers[1](input) #assuming you are ignoring the first conv layer as implied in your code
for layer in model.layers[2:]:
    x = layer(x)
model = Model(inputs=input, outputs=x)
model.compile(*args, **kwargs)

编辑：

为了确保权重不获取，你需要添加一个for循环来将它们设置为不可训练。

for layer in model.layers[1:-2]:
    layer.trainable=False

预训练模型的 Keras 输入形状不变

Keras Input shape of a pretrained model not changing

python

tensorflow

keras

deep-learning

transfer-learning

编辑：