Keras多類模型錯了尺寸

新來Keras，試圖重新實現從這個以下這些二進制圖像分類例如：https://blog.keras.io/building-powerful-image-classification-models-using-very-little-data.html Keras多類模型錯了尺寸

它適用於二元分類我。重建它的3類分類我得到以下尺寸不匹配錯誤：

 60   epochs=50, 
    61   validation_data=validation_generator, 
---> 62   validation_steps=250 // batch_size) 
ValueError: Error when checking target: expected activation_50 to have shape (None, 1) but got array with shape (16, 3)

這是我目前實施：

from keras.preprocessing.image import ImageDataGenerator 
from keras.models import Sequential 
from keras.layers import Conv2D, MaxPooling2D 
from keras.layers import Activation, Dropout, Flatten, Dense 
from keras import backend as K 
K.set_image_dim_ordering('th') 
batch_size = 16 

# this is the augmentation configuration we will use for training 
train_datagen = ImageDataGenerator(
     rescale=1./255, 
     shear_range=0.2, 
     zoom_range=0.2, 
     horizontal_flip=True) 

# this is the augmentation configuration we will use for testing: 
# only rescaling 
test_datagen = ImageDataGenerator(rescale=1./255) 

# this is a generator that will read pictures found in 
# subfolers of 'data/train', and indefinitely generate 
# batches of augmented image data 
train_generator = train_datagen.flow_from_directory(
     'F://train_data//', # this is the target directory 
     target_size=(150, 150), # all images will be resized to 150x150 
     batch_size=batch_size, 
     class_mode='categorical') # since we use binary_crossentropy loss, we need binary labels 

# this is a similar generator, for validation data 
validation_generator = test_datagen.flow_from_directory(
     'F://validation_data//', 
     target_size=(150, 150), 
     batch_size=batch_size, 
     class_mode='categorical') 

model = Sequential() 

model.add(Conv2D(32, (3, 3), input_shape=(3, 150, 150))) 
model.add(Activation('relu')) 
model.add(MaxPooling2D(pool_size=(2, 2), data_format="channels_first")) 

model.add(Conv2D(32, (3, 3))) 
model.add(Activation('relu')) 
model.add(MaxPooling2D(pool_size=(2, 2), data_format="channels_first")) 

model.add(Conv2D(64, (3, 3))) 
model.add(Activation('relu')) 
model.add(MaxPooling2D(pool_size=(2, 2), data_format="channels_first")) 

model.add(Flatten()) # this converts our 3D feature maps to 1D feature vectors 
model.add(Dense(64)) 
model.add(Activation('relu')) 
model.add(Dropout(0.5)) 
model.add(Dense(1)) 
model.add(Activation('softmax')) # instead of sigmoid 

model.compile(loss='mean_squared_error', 
       optimizer='adam', 
       metrics=['accuracy']) 

# another loss: sparse_categorical_crossentropy 

model.fit_generator(
     train_generator, 
     steps_per_epoch=1800 // batch_size, 
     epochs=50, 
     validation_data=validation_generator, 
     validation_steps=250 // batch_size)

到目前爲止，我已經改變了輸出層的激活功能從sigmoid到softmax。將class_mode從二進制更改爲分類。似乎無法找到問題。

而且，我知道類似的問題在計算器上： Multi-Output Multi-Class Keras Model

Train multi-class image classifier in Keras

Multi-class classification using keras

但沒有解決方案的幫助了我。

來源

2017-09-01 ivan_bilan

您需要將最終的Dense圖層更改爲model.add(Dense(3))。 Softmax激活期望Dense圖層中的units與類的數量相匹配。

此外，如果您打算使用loss='sparse_categorical_crossentropy'，請記得將class_mode更改爲'sparse'。您當前的設置class_mode='categorical'應與loss='categorical_crossentropy'一起使用。

來源

2017-09-01 08:00:32

Keras多類模型錯了尺寸

回答

相關問題