我是机器学习领域的新手。目前，我正在开发一个使用 keras 深度学习的水果/蔬菜分类项目。我能够训练模型。到目前为止，它可以正确检测已经训练过的对象，但是当我提供其他未经训练的水果/蔬菜时，它会根据训练后的模型进行预测，而它应该将其识别为未知水果。
假设我用苹果、马铃薯和香蕉图像训练了一个模型。只要我提供苹果/土豆/香蕉的图像，它的预测就会正确。但当我提供橙子的图像时，它会像土豆或柠檬一样预测苹果。这是我用来训练和预测水果的代码片段：
import os.path
import numpy as np
np.random.seed(123)
from keras import applications
from keras.models import Sequential
from keras.layers import Dropout, Flatten, Dense
from keras.utils.np_utils import to_categorical
from keras.preprocessing.image import ImageDataGenerator, img_to_array, load_img
from keras.layers.normalization import BatchNormalization
import matplotlib.pyplot as plt
import math
import cv2
#dimensions of images
img_width, img_height = 224, 224
#file paths & directories
top_model_weights_path = 'bottleneck_fc_model.h5'
bottleneck_train_path = 'bottleneck_features_train.npy'
bottleneck_validation_path = 'bottleneck_features_validation.npy'
train_data_dir = 'data/train'
validation_data_dir = 'data/validation/'
#hyperparameters
epochs = 10
batch_size = 16
def save_bottleneck_features():
model = applications.VGG16(include_top=False, weights='imagenet')
datagen = ImageDataGenerator(rescale=1./255,
shear_range=0.2,
zoom_range=0.2,
horizontal_flip=True)
generator = datagen.flow_from_directory(train_data_dir,
target_size=(img_width, img_height),
batch_size=batch_size,
shuffle=False)
no_train_samples = len(generator.filenames)
predict_size_train = int(math.ceil(no_train_samples / batch_size))
bottleneck_features_train = model.predict_generator(generator, predict_size_train)
np.save(bottleneck_train_path, bottleneck_features_train)
datagen = ImageDataGenerator(rescale=1./255)
generator = datagen.flow_from_directory(validation_data_dir,
target_size=(img_width, img_height),
batch_size=batch_size,
class_mode=None,
shuffle=False)
no_validation_samples = len(generator.filenames)
predict_size_validation = int(math.ceil(no_validation_samples / batch_size))
bottleneck_features_validation = model.predict_generator(generator, predict_size_validation)
np.save(bottleneck_validation_path, bottleneck_features_validation)
def train_top_model():
datagen_top = ImageDataGenerator(rescale=1./255)
generator_top = datagen_top.flow_from_directory(train_data_dir,
target_size=(img_width, img_height),
batch_size=batch_size,
class_mode='categorical',
shuffle=False)
num_classes = len(generator_top.class_indices)
# save the class indices to use later in predictions
np.save('class_indices.npy', generator_top.class_indices)
# get the class labels for the training data, in the original order
train_labels = generator_top.classes
# convert the training labels to categorical vectors
train_labels = to_categorical(train_labels, num_classes=num_classes)
generator_top = datagen_top.flow_from_directory(validation_data_dir,
target_size=(img_width, img_height),
batch_size=batch_size,
class_mode=None,
shuffle=False)
validation_labels = generator_top.classes
validation_labels = to_categorical(validation_labels, num_classes=num_classes)
# load the bottleneck features saved earlier
train_data = np.load('bottleneck_features_train.npy')
validation_data = np.load('bottleneck_features_validation.npy')
# build the model
model = Sequential()
model.add(Flatten(input_shape=train_data.shape[1:]))
model.add(BatchNormalization())
model.add(Dense(256, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes, activation='softmax'))
model.compile(optimizer='rmsprop', loss='categorical_crossentropy', metrics=['accuracy'])
history = model.fit(train_data, train_labels, epochs=epochs, batch_size=batch_size)
model.save_weights(top_model_weights_path)
def predict(image_path):
class_dictionary = np.load('class_indices.npy').item()
#print("Values: ",class_dictionary)
num_classes = len(class_dictionary)
orig = cv2.imread(image_path)
print('[INFO] loading and preprocessing image...')
image = load_img(image_path, target_size=(224, 224))
image = img_to_array(image)
image = image / 255
image = np.expand_dims(image, axis=0)
model = applications.VGG16(include_top=False, weights='imagenet')
bottleneck_prediction = model.predict(image)
# build top model
model = Sequential()
model.add(Flatten(input_shape=bottleneck_prediction.shape[1:]))
model.add(BatchNormalization())
model.add(Dense(256, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes, activation='sigmoid'))
model.load_weights(top_model_weights_path)
# use the bottleneck prediction on the top model to get the final classification
class_predicted = model.predict_classes(bottleneck_prediction)
probabilities = model.predict_proba(bottleneck_prediction)
inID = class_predicted[0]
inv_map = {v: k for k, v in class_dictionary.items()}
label = inv_map[inID]
print("Image ID: {}, Label: {}".format(inID, label))
cv2.putText(orig, "Predicted: {}".format(label), (10, 30),
cv2.FONT_HERSHEY_PLAIN, 1.5, (0, 0, 0), 2)
cv2.imshow('Classification', orig)
cv2.imwrite('predicted.jpg', orig)
cv2.waitKey(0)
if __name__ == '__main__':
if not os.path.exists(bottleneck_train_path):
save_bottleneck_features()
if not os.path.exists(top_model_weights_path):
train_top_model()
image_path = 'fruits/orange.jpg'
predict(image_path)
如何克服这种情况？任何帮助将不胜感激。
当在最后一层使用
loss='categorical_crossentropy'activation='softmax'softmaxcategorial_crossentropy0.33 banana, 0.33 apple, 0.34 potato编辑：
请注意，虽然我上面的建议可能对您有用，但训练它可能非常困难，因为它可能需要大量已知和未知的样本，因为“未知”特征更难概括，并且可能会产生负面影响其他类的概括。
正如我之前提到的，一种更实用的方法是定义一个阈值，在预测之后，您将收到每个可能标签的值。选择标签时，该值是标签的“置信度”分数。
检查上面的例子，我们将以 0.34 的置信度挑选土豆。
您可以定义一个阈值，例如 0.6，然后在假设图像的标签时检查置信度得分。如果最高（“选择”）标签低于阈值，您可以将其标记为“未知水果”。
另一个编辑：
此后出现了一些关于该主题的好作品，供将来参考：
https://github.com/hendrycks/outlier-exposure
将是一个很好的起点。