CNN图像分类计算混淆矩阵时出现LabelBinarizer无classes_属性报错

错误根因 #

你实例化LabelBinarizer后没有对原始标签数据执行拟合操作，classes_是LabelBinarizer拟合数据后才会生成的属性，未拟合直接调用就会触发该报错。你查到的「在model.fit执行后再实例化LabelBinarizer」的方案是错误的，LabelBinarizer的实例化和拟合应该在标签编码阶段完成，和模型训练顺序无关。

修复方法 #

根据你的使用场景二选一即可：

场景1：你原本就是用LabelBinarizer做标签独热编码 #

把LabelBinarizer的实例化、拟合逻辑移到标签处理阶段，全程使用同一个实例即可，修改后完整代码如下：

from keras.models import Sequential
from keras.layers import Dense,Activation,Flatten,Dropout
from keras.layers import Conv2D,MaxPooling2D
from keras.callbacks import ModelCheckpoint
import numpy as np
from sklearn.preprocessing import LabelBinarizer
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report, confusion_matrix

# 提前初始化LabelBinarizer并拟合原始标签
lb = LabelBinarizer()
# 你的target已经是独热编码，所以用解码后的标签拟合即可
lb.fit(np.argmax(target, axis=1))

model=Sequential()
model.add(Conv2D(200,(3,3),input_shape=data.shape[1:]))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2,2)))

model.add(Conv2D(100,(3,3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2,2)))

model.add(Flatten())
model.add(Dropout(0.5))
model.add(Dense(50,activation='relu'))
model.add(Dense(2,activation='softmax'))

model.compile(loss='categorical_crossentropy',optimizer='adam',metrics=['accuracy'])

train_data,test_data,train_target,test_target=train_test_split(data,target,test_size=0.1)

checkpoint = ModelCheckpoint('model-{epoch:03d}.model',monitor='val_loss',verbose=0,save_best_only=True,mode='auto')
history=model.fit(train_data,train_target,epochs=4,callbacks=[checkpoint],validation_split=0.2)

print("[INFO] evaluating network...")
predIdxs = model.predict(test_data, batch_size=28)
predIdxs = np.argmax(predIdxs, axis=1)

print(classification_report(test_target.argmax(axis=1), predIdxs,
    target_names=lb.classes_))

cm = confusion_matrix(test_target.argmax(axis=1), predIdxs)
total = sum(sum(cm))
acc = (cm[0, 0] + cm[1, 1]) / total
sensitivity = cm[0, 0] / (cm[0, 0] + cm[0, 1])
specificity = cm[1, 1] / (cm[1, 0] + cm[1, 1])

print(cm)
print("acc: {:.4f}".format(acc))
print("sensitivity: {:.4f}".format(sensitivity))
print("specificity: {:.4f}".format(specificity))

场景2：你已经手动完成了标签独热编码，不需要复用LabelBinarizer #

直接删掉LabelBinarizer相关代码，手动传入分类名称即可，修改对应部分代码为：

# 删掉 lb = LabelBinarizer() 这一行
print(classification_report(test_target.argmax(axis=1), predIdxs,
    target_names=["类别1名称", "类别2名称"])) # 替换为你实际的分类名称

内容的提问来源于stack exchange，提问作者Khalid Hasan