这是我的模型和数据生成器，当我进行预测时，得到的是array([0., 0., 0., 1., 0., 0., 0., 0.])而不是概率。我认为应该是概率。

model = keras.models.Sequential()model.add ...model.add(keras.layers.Dense(num_class))model.add(keras.layers.Softmax())sgd_opt = keras.optimizers.SGD(lr=0.001, momentum=0.9)cce_loss = keras.losses.categorical_crossentropymodel.compile(optimizer=sgd_opt, loss='sparse_categorical_crossentropy', metrics=['accuracy'])train_generator = train_datagen.flow_from_directory(train_data_dir,target_size=IMAGE_SIZE,batch_size=batch_size,class_mode='sparse') validation_generator = train_datagen.flow_from_directory(test_data_dir, # same directory as training datatarget_size=IMAGE_SIZE,batch_size=batch_size,class_mode='sparse') 

回答：

看起来你的模型直接记住了样本的标签。
在训练数据上进行验证是坏习惯。试着分割数据集：

from tensorflow.keras.preprocessing.image import ImageDataGeneratortrain_datagen = ImageDataGenerator(  validation_split=0.2)train_generator = train_datagen.flow_from_directory(    train_data_dir,    target_size=IMAGE_SIZE,    batch_size=batch_size,    subset='training',    class_mode='sparse') validation_generator = train_datagen.flow_from_directory(    train_data_dir,    target_size=IMAGE_SIZE,    batch_size=batch_size,    subset='validation',    class_mode='sparse')