我正在尝试使用InceptionV4来解决一些分类问题。在将其应用于实际问题之前，我正在进行一些实验。

我替换了最后一个密集层（大小为1001）为一个新的密集层，编译了模型并尝试进行拟合

from keras import backend as Kimport inception_v4import numpy as npimport cv2import osfrom keras import optimizersfrom keras.preprocessing.image import ImageDataGeneratorfrom keras.models import Sequentialfrom keras.layers import Convolution2D, MaxPooling2D, ZeroPadding2Dfrom keras.layers import Activation, Dropout, Flatten, Dense, Inputfrom keras.models import Modelos.environ['CUDA_VISIBLE_DEVICES'] = ''my_batch_size=32train_data_dir ='//shared_directory/projects/try_CDFxx/data/train/'validation_data_dir ='//shared_directory/projects/try_CDFxx/data/validation/'img_width, img_height = 299, 299num_classes=3nb_epoch=50nbr_train_samples = 24nbr_validation_samples = 12def train_top_model (num_classes):    v4 = inception_v4.create_model(weights='imagenet')    predictions = Dense(output_dim=num_classes, activation='softmax', name="newDense")(v4.layers[-2].output) # replacing the 1001 categories dense layer with my own     main_input= v4.layers[1].input    main_output=predictions    t_model = Model(input=[main_input], output=[main_output])    train_datagen = ImageDataGenerator(            rescale=1./255,            shear_range=0.1,            zoom_range=0.1,            rotation_range=10.,            width_shift_range=0.1,            height_shift_range=0.1,            horizontal_flip=True)    val_datagen = ImageDataGenerator(rescale=1./255)    train_generator = train_datagen.flow_from_directory(            train_data_dir,            target_size = (img_width, img_height),            batch_size = my_batch_size,            shuffle = True,            class_mode = 'categorical')    validation_generator = val_datagen.flow_from_directory(            validation_data_dir,            target_size=(img_width, img_height),            batch_size=my_batch_size,            shuffle = True,            class_mode = 'categorical')#    t_model.compile(optimizer='rmsprop', loss='sparse_categorical_crossentropy', metrics=['accuracy'])#    t_model.fit_generator(            train_generator,            samples_per_epoch = nbr_train_samples,            nb_epoch = nb_epoch,            validation_data = validation_generator,            nb_val_samples = nbr_validation_samples)train_top_model(num_classes)

但我遇到了以下错误

Traceback (most recent call last):  File "re_try.py", line 76, in <module>    train_top_model(num_classes)  File "re_try.py", line 72, in train_top_model    nb_val_samples = nbr_validation_samples)  File "/usr/local/lib/python2.7/dist-packages/keras/engine/training.py", line 1508, in fit_generator    class_weight=class_weight)  File "/usr/local/lib/python2.7/dist-packages/keras/engine/training.py", line 1261, in train_on_batch    check_batch_dim=True)  File "/usr/local/lib/python2.7/dist-packages/keras/engine/training.py", line 985, in _standardize_user_data    exception_prefix='model target')  File "/usr/local/lib/python2.7/dist-packages/keras/engine/training.py", line 113, in standardize_input_data    str(array.shape))ValueError: Error when checking model target: expected newDense to have shape (None, 1) but got array with shape (24, 3)Exception in thread Thread-1:Traceback (most recent call last):  File "/usr/lib/python2.7/threading.py", line 801, in __bootstrap_inner    self.run()  File "/usr/lib/python2.7/threading.py", line 754, in run    self.__target(*self.__args, **self.__kwargs)  File "/usr/local/lib/python2.7/dist-packages/keras/engine/training.py", line 409, in data_generator_task    generator_output = next(generator)  File "/usr/local/lib/python2.7/dist-packages/keras/preprocessing/image.py", line 693, in next    x = self.image_data_generator.random_transform(x)  File "/usr/local/lib/python2.7/dist-packages/keras/preprocessing/image.py", line 403, in random_transform    fill_mode=self.fill_mode, cval=self.cval)  File "/usr/local/lib/python2.7/dist-packages/keras/preprocessing/image.py", line 109, in apply_transform    final_offset, order=0, mode=fill_mode, cval=cval) for x_channel in x]AttributeError: 'NoneType' object has no attribute 'interpolation'

我做错了什么？为什么在定义了大小为3的新密集层后，它仍然期望具有(None,1)的形状？

非常感谢

PS我添加了模型总结的结尾部分

merge_25 (Merge)                 (None, 8, 8, 1536)    0           activation_140[0][0]                                                                   merge_23[0][0]                                                                   merge_24[0][0]                                                                   activation_149[0][0]____________________________________________________________________________________________________averagepooling2d_15 (AveragePool (None, 1, 1, 1536)    0           merge_25[0][0]____________________________________________________________________________________________________dropout_1 (Dropout)              (None, 1, 1, 1536)    0           averagepooling2d_15[0][0]____________________________________________________________________________________________________flatten_1 (Flatten)              (None, 1536)          0           dropout_1[0][0]____________________________________________________________________________________________________newDense (Dense)                 (None, 3)             4611        flatten_1[0][0]====================================================================================================Total params: 41,210,595Trainable params: 41,147,427Non-trainable params: 63,168

回答：

好的，问题出在

validation_generator = val_datagen.flow_from_directory(...        class_mode = 'categorical')

Categorical使你的生成器返回一个独热编码向量。在你的情况下是一个3-d的向量。但你将loss设置为sparse_categorical_crossentropy，它接受int作为标签。你应该更改class_mode="sparse"或loss="categorical_crossentropy"。