Question

我正在使用具有预训练权重的AlexNet（heuritech / convnets-keras）来解决8个类而不是1000个的分类问题。在用Model(input=..,output=..)初始化网络并加载初始权重之后，我放弃了最后两个层，密集（1000）和激活（softmax），并添加我自己的两个层：密集（8）和激活（softmax）。但是，在运行后我得到一个错误

Error when checking model target: expected softmax to have shape (None, 1000) but got array with shape (32, 8)

32是我猜的生成器的批量大小，但我不明白为什么softmax仍然需要前一层的1000个维度。

有人能帮助我吗？我认为它有一些事情可以做模型的输出参数，但这只是在尝试和谷歌搜索后的半疯狂猜测。谢谢！

代码：

import ...

pp = os.path.dirname(os.path.abspath(__file__))

##### Define Model #####
inputs = Input(shape=(3,227,227))
conv_1 = Convolution2D(96, 11, 11,subsample=(4,4),activation='relu', name='conv_1')(inputs)
...
...
...
dense_1 = MaxPooling2D((3, 3), strides=(2,2),name="convpool_5")(conv_5)
dense_1 = Flatten(name="flatten")(dense_1)
dense_1 = Dense(4096, activation='relu',name='dense_1')(dense_1)
dense_2 = Dropout(0.5)(dense_1)
dense_2 = Dense(4096, activation='relu',name='dense_2')(dense_2)
dense_3 = Dropout(0.5)(dense_2)  
dense_3 = Dense(1000,name='dense_3')(dense_3)
prediction = Activation("softmax",name="softmax")(dense_3)

model = Model(input=inputs, output=prediction)

for layer in model.layers[:27]:
    print layer.name
    layer.trainable = False

model.load_weights(pp+"/weights/alexnet_weights.h5")
print model.output_shape

print model.layers[-1]
model.layers.pop()
print model.output_shape
model.layers.pop()
print model.layers[-1]
print model.output_shape
model.layers.append(Dense(8, activation='softmax',name='dense_4'))

print model.layers[-1]
#####  Get Data #####
train_datagen = ImageDataGenerator(
        rescale=1./255,
        shear_range=0.2,
        zoom_range=0.2)

test_datagen = ImageDataGenerator(rescale=1./255)

train_generator = train_datagen.flow_from_directory(
        pp+'/dataset/training', 
        target_size=(227,227), 
        class_mode='categorical')  

validation_generator = test_datagen.flow_from_directory(
        pp+'/dataset/test',
        target_size=(227,227),
        class_mode='categorical')

##### Compile and Fit ####
sgd = SGD(lr=1e-4, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(optimizer=sgd, loss='mse')

model.fit_generator(
        train_generator,
        samples_per_epoch=500,
        nb_epoch=5,
        validation_data=validation_generator,
        nb_val_samples=150)

model.save_weights('first_try.h5')

Answer 1

好吧，我似乎无法改变网络定义，因为即使在弹出/放入新图层之后，似乎也没有任何改变。所以我这样做了：

1) Load the default AlexNet

2) Load the pre-trained weights

3) Pop the 2 top layers

4) Add two new top layers

5) Save the weights

6) Change Network definition to use the two new layers

7) Load the new AlexNet with the saved weights

8) Profit!

虽然我仍然想知道如何更改功能api定义的加载网络。

在Keras中更改预训练的AlexNet分类

1 个答案: