我试图用经过预先训练和微调的DL模型预测验证数据。该代码遵循Keras博客中提供的示例＆＃34;使用非常少的数据构建图像分类模型＆＃34;。这是代码：
import numpy as np
from keras.preprocessing.image import ImageDataGenerator
import matplotlib.pyplot as plt
from keras.models import Sequential
from keras.models import Model
from keras.layers import Flatten, Dense
from sklearn.metrics import classification_report,confusion_matrix
from sklearn.metrics import roc_auc_score
import itertools
from keras.optimizers import SGD
from sklearn.metrics import roc_curve, auc
from keras import applications
from keras import backend as K
K.set_image_dim_ordering('tf')
# Plotting the confusion matrix
def plot_confusion_matrix(cm, classes,
normalize=False, #if true all values in confusion matrix is between 0 and 1
title='Confusion matrix',
cmap=plt.cm.Blues):
"""
This function prints and plots the confusion matrix.
Normalization can be applied by setting `normalize=True`.
"""
plt.imshow(cm, interpolation='nearest', cmap=cmap)
plt.title(title)
plt.colorbar()
tick_marks = np.arange(len(classes))
plt.xticks(tick_marks, classes, rotation=45)
plt.yticks(tick_marks, classes)
if normalize:
cm = cm.astype('float') / cm.sum(axis=1)[:, np.newaxis]
print("Normalized confusion matrix")
else:
print('Confusion matrix, without normalization')
print(cm)
thresh = cm.max() / 2.
for i, j in itertools.product(range(cm.shape[0]), range(cm.shape[1])):
plt.text(j, i, cm[i, j],
horizontalalignment="center",
color="white" if cm[i, j] > thresh else "black")
plt.tight_layout()
plt.ylabel('True label')
plt.xlabel('Predicted label')
#plot data
def generate_results(validation_labels, y_pred):
fpr, tpr, _ = roc_curve(validation_labels, y_pred) ##(this implementation is restricted to a binary classification task)
roc_auc = auc(fpr, tpr)
plt.figure()
plt.plot(fpr, tpr, label='ROC curve (area = %0.2f)' % roc_auc)
plt.plot([0, 1], [0, 1], 'k--')
plt.xlim([0.0, 1.05])
plt.ylim([0.0, 1.05])
plt.xlabel('False Positive Rate (FPR)')
plt.ylabel('True Positive Rate (TPR)')
plt.title('Receiver operating characteristic (ROC) curve')
plt.show()
print('Area Under the Curve (AUC): %f' % roc_auc)
img_width, img_height = 100,100
top_model_weights_path = 'modela.h5'
train_data_dir = 'data4/train'
validation_data_dir = 'data4/validation'
nb_train_samples = 20
nb_validation_samples = 20
epochs = 50
batch_size = 10
def save_bottleneck_features():
datagen = ImageDataGenerator(rescale=1. / 255)
model = applications.VGG16(include_top=False, weights='imagenet', input_shape=(100,100,3))
generator = datagen.flow_from_directory(
train_data_dir,
target_size=(img_width, img_height),
batch_size=batch_size,
class_mode='binary',
shuffle=False)
bottleneck_features_train = model.predict_generator(
generator, nb_train_samples // batch_size)
np.save(open('bottleneck_features_train', 'wb'),bottleneck_features_train)
generator = datagen.flow_from_directory(
validation_data_dir,
target_size=(img_width, img_height),
batch_size=batch_size,
class_mode='binary',
shuffle=False)
bottleneck_features_validation = model.predict_generator(
generator, nb_validation_samples // batch_size)
np.save(open('bottleneck_features_validation', 'wb'),bottleneck_features_validation)
def train_top_model():
train_data = np.load(open('bottleneck_features_train', 'rb'))
train_labels = np.array([0] * (nb_train_samples // 2) + [1] * (nb_train_samples // 2))
validation_data = np.load(open('bottleneck_features_validation', 'rb'))
validation_labels = np.array([0] * (nb_validation_samples // 2) + [1] * (nb_validation_samples // 2))
model = Sequential()
model.add(Flatten(input_shape=train_data.shape[1:]))
model.add(Dense(512, activation='relu'))
model.add(Dense(1, activation='sigmoid'))
sgd = SGD(lr=1e-3, decay=0.00, momentum=0.99, nesterov=False)
model.compile(optimizer=sgd,
loss='binary_crossentropy', metrics=['accuracy'])
model.fit(train_data, train_labels,
epochs=epochs,
batch_size=batch_size,
validation_data=(validation_data, validation_labels))
model.save_weights(top_model_weights_path)
print('Predicting on test data')
y_pred = model.predict_classes(validation_data)
print(y_pred.shape)
print('Generating results')
generate_results(validation_labels[:,], y_pred[:,])
print('Generating the ROC_AUC_Scores') #Compute Area Under the Curve (AUC) from prediction scores
print(roc_auc_score(validation_labels,y_pred)) #this implementation is restricted to the binary classification task or multilabel classification task in label indicator format.
target_names = ['class 0(Normal)', 'class 1(Abnormal)']
print(classification_report(validation_labels,y_pred,target_names=target_names))
print(confusion_matrix(validation_labels,y_pred))
cnf_matrix = (confusion_matrix(validation_labels,y_pred))
np.set_printoptions(precision=2)
plt.figure()
# Plot non-normalized confusion matrix
plot_confusion_matrix(cnf_matrix, classes=target_names,
title='Confusion matrix')
plt.show()
save_bottleneck_features()
train_top_model()
# path to the model weights files.
weights_path = '../keras/examples/vgg16_weights.h5'
top_model_weights_path = 'modela.h5'
# dimensions of our images.
img_width, img_height = 100, 100
train_data_dir = 'data4/train'
validation_data_dir = 'data4/validation'
nb_train_samples = 20
nb_validation_samples = 20
epochs = 50
batch_size = 10
# build the VGG16 network
base_model = applications.VGG16(weights='imagenet', include_top=False, input_shape=(100,100,3))
print('Model loaded.')
train_datagen = ImageDataGenerator(
rescale=1. / 255,
shear_range=0.2,
zoom_range=0.2,
horizontal_flip=True)
test_datagen = ImageDataGenerator(rescale=1. / 255)
train_generator = train_datagen.flow_from_directory(
train_data_dir,
target_size=(img_height, img_width),
batch_size=batch_size,
class_mode='binary')
validation_generator = test_datagen.flow_from_directory(
validation_data_dir,
target_size=(img_height, img_width),
batch_size=batch_size,
class_mode='binary')
top_model = Sequential()
top_model.add(Flatten(input_shape=base_model.output_shape[1:]))
top_model.add(Dense(512, activation='relu'))
top_model.add(Dense(1, activation='softmax'))
top_model.load_weights(top_model_weights_path)
model = Model(inputs=base_model.input, outputs=top_model(base_model.output))
# set the first 15 layers (up to the last conv block)
# to non-trainable (weights will not be updated)
for layer in model.layers[:15]: #up to the layer before the last convolution block
layer.trainable = False
model.summary()
# fine-tune the model
model.compile(loss='binary_crossentropy', optimizer=SGD(lr=1e-4, momentum=0.99), metrics=['accuracy'])
model.fit_generator(train_generator,
steps_per_epoch=nb_train_samples // batch_size,
epochs=epochs,
validation_data=validation_generator,
validation_steps=nb_validation_samples // batch_size,
verbose=1)
model.save_weights(top_model_weights_path)
bottleneck_features_validation = model.predict_generator(validation_generator, nb_validation_samples // batch_size)
np.save(open('bottleneck_features_validation','wb'), bottleneck_features_validation)
validation_data = np.load(open('bottleneck_features_validation', 'rb'))
y_pred1 = model.predict_classes(validation_data)
问题在于预训练模型正在接受数据训练并完美地预测类并给出混淆矩阵。当我继续微调模型时，我发现model.predict_classes不起作用。这是错误：
File "C:/Users/rajaramans2/codes/untitled12.py", line 220, in <module> y_pred1 = model.predict_classes(validation_data) AttributeError: 'Model' object has no attribute 'predict_classes'
我很困惑，因为model.predict_classes与预训练的模型配合得很好，但在微调阶段却没有。验证数据的大小为（20,1）和float32类型。任何帮助，将不胜感激。
答案 0 :(得分：19)
predict_classes方法仅适用于Sequential类（您的第一个模型的类），但不适用于Model类（第二个模型的类）。
使用Model类，您可以使用predict方法，该方法将为您提供概率向量，然后获取此向量的argmax（使用np.argmax(y_pred1,axis=1)）。