问题描述
我正在尝试训练CNN以按主题对文本进行分类.当我使用二进制交叉熵时，我获得了〜80％的准确度，而使用分类交叉熵时，我获得了〜50％的准确度.
I'm trying to train a CNN to categorize text by topic. When I use binary cross-entropy I get ~80% accuracy, with categorical cross-entropy I get ~50% accuracy.
我不明白为什么会这样.这是一个多类问题，这并不意味着我必须使用分类交叉熵，而具有二进制交叉熵的结果却毫无意义吗?
I don't understand why this is. It's a multiclass problem, doesn't that mean that I have to use categorical cross-entropy and that the results with binary cross-entropy are meaningless?
model.add(embedding_layer)
model.add(Dropout(0.25))
# convolution layers
model.add(Conv1D(nb_filter=32,
filter_length=4,
border_mode='valid',
activation='relu'))
model.add(MaxPooling1D(pool_length=2))
# dense layers
model.add(Flatten())
model.add(Dense(256))
model.add(Dropout(0.25))
model.add(Activation('relu'))
# output layer
model.add(Dense(len(class_id_index)))
model.add(Activation('softmax'))
然后使用categorical_crossentropy作为损失函数像这样编译它:
Then I compile it either it like this using categorical_crossentropy as the loss function:
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
或
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
从直觉上讲，为什么我要使用分类交叉熵是合理的，我不明白为什么使用二进制得到好的结果，而使用分类不好的结果.
Intuitively it makes sense why I'd want to use categorical cross-entropy, I don't understand why I get good results with binary, and poor results with categorical.
推荐答案
此明显的性能差异与分类和测试之间存在差异的原因@ xtof54已经在他的答案中报告了二进制交叉熵，即:
The reason for this apparent performance discrepancy between categorical & binary cross entropy is what @xtof54 has already reported in his answer, i.e.:
我想对此进行详细说明，演示实际的潜在问题，对其进行解释，并提供补救措施.
I would like to elaborate more on this, demonstrate the actual underlying issue, explain it, and offer a remedy.
此行为不是错误；根本原因是一个相当微妙的&当您在模型编译中仅包含metrics=['accuracy']时，Keras如何实际猜测使用哪种精度(取决于您选择的损失函数)的未公开问题.换句话说，当您的第一个编译选项
This behavior is not a bug; the underlying reason is a rather subtle & undocumented issue at how Keras actually guesses which accuracy to use, depending on the loss function you have selected, when you include simply metrics=['accuracy'] in your model compilation. In other words, while your first compilation option
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
有效，您的第二个有效
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
不会产生您所期望的结果，但是原因不是使用二进制交叉熵(至少在原则上是绝对有效的损失函数).
will not produce what you expect, but the reason is not the use of binary cross entropy (which, at least in principle, is an absolutely valid loss function).
那是为什么?如果您查看指标源代码，则Keras不会定义单个精度度量标准，但有几个不同的度量标准，其中包括binary_accuracy和categorical_accuracy. 在幕后发生的事情是: ，因为您选择了二进制交叉熵作为损失函数，并且未指定特定的精度指标，所以Keras(错误地...)推断您对binary_accuracy感兴趣，这就是它返回的内容-实际上，您对categorical_accuracy感兴趣.
Why is that? If you check the metrics source code, Keras does not define a single accuracy metric, but several different ones, among them binary_accuracy and categorical_accuracy. What happens under the hood is that, since you have selected binary cross entropy as your loss function and have not specified a particular accuracy metric, Keras (wrongly...) infers that you are interested in the binary_accuracy, and this is what it returns - while in fact you are interested in the categorical_accuracy.
使用 MNIST CNN示例在Keras中，进行了以下修改:
Let's verify that this is the case, using the MNIST CNN example in Keras, with the following modification:
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy']) # WRONG way
model.fit(x_train, y_train,
batch_size=batch_size,
epochs=2, # only 2 epochs, for demonstration purposes
verbose=1,
validation_data=(x_test, y_test))
# Keras reported accuracy:
score = model.evaluate(x_test, y_test, verbose=0)
score[1]
# 0.9975801164627075
# Actual accuracy calculated manually:
import numpy as np
y_pred = model.predict(x_test)
acc = sum([np.argmax(y_test[i])==np.argmax(y_pred[i]) for i in range(10000)])/10000
acc
# 0.98780000000000001
score[1]==acc
# False
要对此进行补救，即使用确实的二进制交叉熵作为损失函数(如我所说，至少在原则上没有错)，同时仍能获得问题所需的绝对精度现在，您应该在模型编译中明确要求categorical_accuracy，如下所示:
To remedy this, i.e. to use indeed binary cross entropy as your loss function (as I said, nothing wrong with this, at least in principle) while still getting the categorical accuracy required by the problem at hand, you should ask explicitly for categorical_accuracy in the model compilation as follows:
from keras.metrics import categorical_accuracy
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=[categorical_accuracy])
在MNIST的示例中，经过如上所示的训练，评分和预测测试集之后，这两个指标现在应该相同，它们应该是相同的:
In the MNIST example, after training, scoring, and predicting the test set as I show above, the two metrics now are the same, as they should be:
# Keras reported accuracy:
score = model.evaluate(x_test, y_test, verbose=0)
score[1]
# 0.98580000000000001
# Actual accuracy calculated manually:
y_pred = model.predict(x_test)
acc = sum([np.argmax(y_test[i])==np.argmax(y_pred[i]) for i in range(10000)])/10000
acc
# 0.98580000000000001
score[1]==acc
# True
系统设置:
Python version 3.5.3
Tensorflow version 1.2.1
Keras version 2.0.4
更新:发布后，我发现此问题已在.
UPDATE: After my post, I discovered that this issue had already been identified in this answer.
这篇关于为什么对同一问题，binary_crossentropy和categorical_crossentropy具有不同的性能?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持！