我在尝试使用tf.keras中的model.predict()来预测单张图像的类别，结果返回的类概率高于1，这是不合理的。我不确定为什么会出现这种情况。以下是我训练CNN的方式：

class_names = ['Angry','Disgust','Fear','Happy','Sad','Surprise','Neutral']model = models.Sequential()model.add(layers.Conv2D(64, (3, 3), activation='relu', input_shape=(48, 48, 1), kernel_regularizer=tf.keras.regularizers.l1(0.01)))model.add(layers.Conv2D(128, (3, 3), padding='same', activation='relu'))model.add(layers.MaxPooling2D((2, 2)))model.add(tf.keras.layers.Dropout(0.5))model.add(layers.Conv2D(64, (3, 3), activation='relu'))model.add(layers.MaxPooling2D((2, 2)))model.add(tf.keras.layers.Dropout(0.5))model.add(layers.Conv2D(64, (3, 3), activation='relu'))model.summary()model.add(layers.Flatten())model.add(layers.Dense(64, activation='relu'))model.add(layers.Dense(7))#model.summary()model.compile(optimizer='adam',loss=tf.keras.losses.CategoricalCrossentropy(from_logits=True),metrics=['accuracy'])lr_reducer = tf.keras.callbacks.ReduceLROnPlateau(monitor='val_loss', factor=0.9, patience=3) #monitors the validation loss for signs of a plateau and then alter the learning rate by the specified factor if a plateau is detectedearly_stopper = tf.keras.callbacks.EarlyStopping(monitor='val_accuracy', min_delta=0, patience=6, mode='auto')  #This will monitor and stop the model training if it is not further convergingcheckpointer = tf.keras.callbacks.ModelCheckpoint('C:\\Users\\rtlum\\Documents\\DataSci_Projects\\PythonTensorFlowProjects\\Datasets\\FER2013_Model_Weights\\Model\\weights.hd5', monitor='val_loss', verbose=1, save_best_only=True) #This allows checkpoints to be saved each epoch just in case the model stops trainingepochs = 100batch_size = 64learning_rate = 0.001model.fit(          train_data,          train_labels,          epochs = epochs,          batch_size = batch_size,          validation_split = 0.2,          shuffle = True,          callbacks=[lr_reducer, checkpointer, early_stopper]          )

以下是我调用model.predict()并传入单张图像进行预测的方式：

    model = tf.keras.models.load_model('Model\\weights.hd5')    img = Image.open(test_image).convert('L')    img = img.resize([48, 48])    image_data = np.asarray(img, dtype=np.uint8)    #image_data = np.resize(img,3072)    image_data = image_data / 255    image_data_test = image_data.reshape((1, 48, 48, 1))    class_names = ['Angry','Disgust','Fear','Happy','Sad','Surprise','Neutral']    x = model.predict(image_data_test)    app.logger.info(x)    image_pred = np.argmax(x)    y = round(x[0][np.argmax(x)], 2)    confidence = y * 100    print(class_names[image_pred], confidence)

最后，以下是我从model.predict()接收到的类概率：

>>> x = model.predict(image_data_test)>>> xarray([[ 1.0593076 , -3.5140653 ,  0.7505076 ,  2.1341033 ,  0.02394461,        -0.08749148,  0.6640976 ]], dtype=float32)

回答：

您的最后一层 model.add(layers.Dense(7)) 使用的是线性激活函数。为了获得7个类的概率，您应该使用 softmax 激活函数。

将您的最后一层更改为

model.add(layers.Dense(7 , activation='softmax'))