我试图在2个类的某些数据上创建模型，但我一直收到错误说：
ValueError: Error when checking target: expected softmax to have shape (1100,) but got array with shape (2,)
我知道这是一个相当common error，但我似乎无法解决我的问题。我相信错误表明模型的输出形状为(1100,)，但输出的维度为(2,)。任何人都知道如何修复它？
这是我的模特：
def TestModel(nb_classes=2, inputs=(3, 224, 224)):
input_img = Input(shape=inputs)
conv1 = Convolution2D(
96, 7, 7, activation='relu', init='glorot_uniform',
subsample=(2, 2), border_mode='same', name='conv1')(input_img)
maxpool1 = MaxPooling2D(
pool_size=(3, 3), strides=(2, 2), name='maxpool1', dim_ordering="th")(conv1)
fire2_squeeze = Convolution2D(
16, 1, 1, activation='relu', init='glorot_uniform',
border_mode='same', name='fire2_squeeze')(maxpool1)
fire2_expand1 = Convolution2D(
64, 1, 1, activation='relu', init='glorot_uniform',
border_mode='same', name='fire2_expand1')(fire2_squeeze)
fire2_expand2 = Convolution2D(
64, 3, 3, activation='relu', init='glorot_uniform',
border_mode='same', name='fire2_expand2')(fire2_squeeze)
merge2 = merge(
[fire2_expand1, fire2_expand2], mode='concat', concat_axis=1)
fire3_squeeze = Convolution2D(
16, 1, 1, activation='relu', init='glorot_uniform',
border_mode='same', name='fire3_squeeze')(merge2)
fire3_expand1 = Convolution2D(
64, 1, 1, activation='relu', init='glorot_uniform',
border_mode='same', name='fire3_expand1')(fire3_squeeze)
fire3_expand2 = Convolution2D(
64, 3, 3, activation='relu', init='glorot_uniform',
border_mode='same', name='fire3_expand2')(fire3_squeeze)
merge3 = merge(
[fire3_expand1, fire3_expand2], mode='concat', concat_axis=1)
fire4_squeeze = Convolution2D(
32, 1, 1, activation='relu', init='glorot_uniform',
border_mode='same', name='fire4_squeeze')(merge3)
fire4_expand1 = Convolution2D(
128, 1, 1, activation='relu', init='glorot_uniform',
border_mode='same', name='fire4_expand1')(fire4_squeeze)
fire4_expand2 = Convolution2D(
128, 3, 3, activation='relu', init='glorot_uniform',
border_mode='same', name='fire4_expand2')(fire4_squeeze)
merge4 = merge(
[fire4_expand1, fire4_expand2], mode='concat', concat_axis=1)
maxpool4 = MaxPooling2D(
pool_size=(3, 3), strides=(2, 2), name='maxpool4')(merge4)
fire5_squeeze = Convolution2D(
32, 1, 1, activation='relu', init='glorot_uniform',
border_mode='same', name='fire5_squeeze')(maxpool4)
fire5_expand1 = Convolution2D(
128, 1, 1, activation='relu', init='glorot_uniform',
border_mode='same', name='fire5_expand1')(fire5_squeeze)
fire5_expand2 = Convolution2D(
128, 3, 3, activation='relu', init='glorot_uniform',
border_mode='same', name='fire5_expand2')(fire5_squeeze)
merge5 = merge(
[fire5_expand1, fire5_expand2], mode='concat', concat_axis=1)
fire6_squeeze = Convolution2D(
48, 1, 1, activation='relu', init='glorot_uniform',
border_mode='same', name='fire6_squeeze')(merge5)
fire6_expand1 = Convolution2D(
192, 1, 1, activation='relu', init='glorot_uniform',
border_mode='same', name='fire6_expand1')(fire6_squeeze)
fire6_expand2 = Convolution2D(
192, 3, 3, activation='relu', init='glorot_uniform',
border_mode='same', name='fire6_expand2')(fire6_squeeze)
merge6 = merge(
[fire6_expand1, fire6_expand2], mode='concat', concat_axis=1)
fire7_squeeze = Convolution2D(
48, 1, 1, activation='relu', init='glorot_uniform',
border_mode='same', name='fire7_squeeze')(merge6)
fire7_expand1 = Convolution2D(
192, 1, 1, activation='relu', init='glorot_uniform',
border_mode='same', name='fire7_expand1')(fire7_squeeze)
fire7_expand2 = Convolution2D(
192, 3, 3, activation='relu', init='glorot_uniform',
border_mode='same', name='fire7_expand2')(fire7_squeeze)
merge7 = merge(
[fire7_expand1, fire7_expand2], mode='concat', concat_axis=1)
fire8_squeeze = Convolution2D(
64, 1, 1, activation='relu', init='glorot_uniform',
border_mode='same', name='fire8_squeeze')(merge7)
fire8_expand1 = Convolution2D(
256, 1, 1, activation='relu', init='glorot_uniform',
border_mode='same', name='fire8_expand1')(fire8_squeeze)
fire8_expand2 = Convolution2D(
256, 3, 3, activation='relu', init='glorot_uniform',
border_mode='same', name='fire8_expand2')(fire8_squeeze)
merge8 = merge(
[fire8_expand1, fire8_expand2], mode='concat', concat_axis=1)
maxpool8 = MaxPooling2D(
pool_size=(3, 3), strides=(2, 2), name='maxpool8')(merge8)
fire9_squeeze = Convolution2D(
64, 1, 1, activation='relu', init='glorot_uniform',
border_mode='same', name='fire9_squeeze')(maxpool8)
fire9_expand1 = Convolution2D(
256, 1, 1, activation='relu', init='glorot_uniform',
border_mode='same', name='fire9_expand1')(fire9_squeeze)
fire9_expand2 = Convolution2D(
256, 3, 3, activation='relu', init='glorot_uniform',
border_mode='same', name='fire9_expand2')(fire9_squeeze)
merge9 = merge(
[fire9_expand1, fire9_expand2], mode='concat', concat_axis=1)
fire9_dropout = Dropout(0.5, name='fire9_dropout')(merge9)
conv10 = Convolution2D(
nb_classes, 1, 1, init='glorot_uniform',
border_mode='valid', name='conv10')(fire9_dropout)
# The size should match the output of conv10
avgpool10 = AveragePooling2D((13, 13), name='avgpool10')(conv10)
flatten = Flatten(name='flatten')(avgpool10)
softmax = Activation("softmax", name='softmax')(flatten)
return Model(input=input_img, output=softmax)
这是创建模型的代码：
def main():
np.random.seed(45)
nb_class = 2
width, height = 224, 224
sn = model.TestModel(nb_classes=nb_class, inputs=(height, width, 3))
print('Build model')
sgd = SGD(lr=0.001, decay=0.0002, momentum=0.9, nesterov=True)
sn.compile(
optimizer=sgd, loss='categorical_crossentropy', metrics=['accuracy'])
print(sn.summary())
# Training
train_data_dir = 'data/train'
validation_data_dir = 'data/validation'
nb_train_samples = 2000
nb_validation_samples = 800
nb_epoch = 500
# Generator
train_datagen = ImageDataGenerator(
rescale=1./255,
shear_range=0.2,
zoom_range=0.2,
horizontal_flip=True)
#train_datagen = ImageDataGenerator(rescale=1./255)
test_datagen = ImageDataGenerator(rescale=1./255)
train_generator = train_datagen.flow_from_directory(
train_data_dir,
target_size=(width, height),
batch_size=32,
class_mode='categorical')
validation_generator = test_datagen.flow_from_directory(
validation_data_dir,
target_size=(width, height),
batch_size=32,
class_mode='categorical')
# Instantiate AccLossPlotter to visualise training
plotter = AccLossPlotter(graphs=['acc', 'loss'], save_graph=True)
early_stopping = EarlyStopping(monitor='val_loss', patience=3, verbose=0)
checkpoint = ModelCheckpoint(
'weights.{epoch:02d}-{val_loss:.2f}.h5',
monitor='val_loss',
verbose=0,
save_best_only=True,
save_weights_only=True,
mode='min',
period=1)
sn.fit_generator(
train_generator,
samples_per_epoch=nb_train_samples,
nb_epoch=nb_epoch,
validation_data=validation_generator,
nb_val_samples=nb_validation_samples,
callbacks=[plotter, checkpoint])
sn.save_weights('weights.h5')
此处summary()：
____________________________________________________________________________________________________
Layer (type) Output Shape Param # Connected to
====================================================================================================
input_1 (InputLayer) (None, 224, 224, 3) 0
____________________________________________________________________________________________________
conv1 (Convolution2D) (None, 112, 112, 96) 14208 input_1[0][0]
____________________________________________________________________________________________________
maxpool1 (MaxPooling2D) (None, 112, 55, 47) 0 conv1[0][0]
____________________________________________________________________________________________________
fire2_squeeze (Convolution2D) (None, 112, 55, 16) 768 maxpool1[0][0]
____________________________________________________________________________________________________
fire2_expand1 (Convolution2D) (None, 112, 55, 64) 1088 fire2_squeeze[0][0]
____________________________________________________________________________________________________
fire2_expand2 (Convolution2D) (None, 112, 55, 64) 9280 fire2_squeeze[0][0]
____________________________________________________________________________________________________
merge_1 (Merge) (None, 224, 55, 64) 0 fire2_expand1[0][0]
fire2_expand2[0][0]
____________________________________________________________________________________________________
fire3_squeeze (Convolution2D) (None, 224, 55, 16) 1040 merge_1[0][0]
____________________________________________________________________________________________________
fire3_expand1 (Convolution2D) (None, 224, 55, 64) 1088 fire3_squeeze[0][0]
____________________________________________________________________________________________________
fire3_expand2 (Convolution2D) (None, 224, 55, 64) 9280 fire3_squeeze[0][0]
____________________________________________________________________________________________________
merge_2 (Merge) (None, 448, 55, 64) 0 fire3_expand1[0][0]
fire3_expand2[0][0]
____________________________________________________________________________________________________
fire4_squeeze (Convolution2D) (None, 448, 55, 32) 2080 merge_2[0][0]
____________________________________________________________________________________________________
fire4_expand1 (Convolution2D) (None, 448, 55, 128) 4224 fire4_squeeze[0][0]
____________________________________________________________________________________________________
fire4_expand2 (Convolution2D) (None, 448, 55, 128) 36992 fire4_squeeze[0][0]
____________________________________________________________________________________________________
merge_3 (Merge) (None, 896, 55, 128) 0 fire4_expand1[0][0]
fire4_expand2[0][0]
____________________________________________________________________________________________________
maxpool4 (MaxPooling2D) (None, 447, 27, 128) 0 merge_3[0][0]
____________________________________________________________________________________________________
fire5_squeeze (Convolution2D) (None, 447, 27, 32) 4128 maxpool4[0][0]
____________________________________________________________________________________________________
fire5_expand1 (Convolution2D) (None, 447, 27, 128) 4224 fire5_squeeze[0][0]
____________________________________________________________________________________________________
fire5_expand2 (Convolution2D) (None, 447, 27, 128) 36992 fire5_squeeze[0][0]
____________________________________________________________________________________________________
merge_4 (Merge) (None, 894, 27, 128) 0 fire5_expand1[0][0]
fire5_expand2[0][0]
____________________________________________________________________________________________________
fire6_squeeze (Convolution2D) (None, 894, 27, 48) 6192 merge_4[0][0]
____________________________________________________________________________________________________
fire6_expand1 (Convolution2D) (None, 894, 27, 192) 9408 fire6_squeeze[0][0]
____________________________________________________________________________________________________
fire6_expand2 (Convolution2D) (None, 894, 27, 192) 83136 fire6_squeeze[0][0]
____________________________________________________________________________________________________
merge_5 (Merge) (None, 1788, 27, 192) 0 fire6_expand1[0][0]
fire6_expand2[0][0]
____________________________________________________________________________________________________
fire7_squeeze (Convolution2D) (None, 1788, 27, 48) 9264 merge_5[0][0]
____________________________________________________________________________________________________
fire7_expand1 (Convolution2D) (None, 1788, 27, 192) 9408 fire7_squeeze[0][0]
____________________________________________________________________________________________________
fire7_expand2 (Convolution2D) (None, 1788, 27, 192) 83136 fire7_squeeze[0][0]
____________________________________________________________________________________________________
merge_6 (Merge) (None, 3576, 27, 192) 0 fire7_expand1[0][0]
fire7_expand2[0][0]
____________________________________________________________________________________________________
fire8_squeeze (Convolution2D) (None, 3576, 27, 64) 12352 merge_6[0][0]
____________________________________________________________________________________________________
fire8_expand1 (Convolution2D) (None, 3576, 27, 256) 16640 fire8_squeeze[0][0]
____________________________________________________________________________________________________
fire8_expand2 (Convolution2D) (None, 3576, 27, 256) 147712 fire8_squeeze[0][0]
____________________________________________________________________________________________________
merge_7 (Merge) (None, 7152, 27, 256) 0 fire8_expand1[0][0]
fire8_expand2[0][0]
____________________________________________________________________________________________________
maxpool8 (MaxPooling2D) (None, 3575, 13, 256) 0 merge_7[0][0]
____________________________________________________________________________________________________
fire9_squeeze (Convolution2D) (None, 3575, 13, 64) 16448 maxpool8[0][0]
____________________________________________________________________________________________________
fire9_expand1 (Convolution2D) (None, 3575, 13, 256) 16640 fire9_squeeze[0][0]
____________________________________________________________________________________________________
fire9_expand2 (Convolution2D) (None, 3575, 13, 256) 147712 fire9_squeeze[0][0]
____________________________________________________________________________________________________
merge_8 (Merge) (None, 7150, 13, 256) 0 fire9_expand1[0][0]
fire9_expand2[0][0]
____________________________________________________________________________________________________
fire9_dropout (Dropout) (None, 7150, 13, 256) 0 merge_8[0][0]
____________________________________________________________________________________________________
conv10 (Convolution2D) (None, 7150, 13, 2) 514 fire9_dropout[0][0]
____________________________________________________________________________________________________
avgpool10 (AveragePooling2D) (None, 550, 1, 2) 0 conv10[0][0]
____________________________________________________________________________________________________
flatten (Flatten) (None, 1100) 0 avgpool10[0][0]
____________________________________________________________________________________________________
softmax (Activation) (None, 1100) 0 flatten[0][0]
====================================================================================================
Total params: 683,954
Trainable params: 683,954
Non-trainable params: 0
____________________________________________________________________________________________________
None
Found 22778 images belonging to 2 classes.
Found 2222 images belonging to 2 classes.
Epoch 1/500
任何想法都赞赏。
答案 0 :(得分：1)
您不应该使用AveragePooling2D，而是GlobalAveragePooling2D，这会将空间维度减少到1，从而使Flatten工作并产生(None, 2)的输出。