Keras:如何为多标签分类计算准确性?

我正在做有毒评论文本分类Kaggle挑战.有6个类别:['threat', 'severe_toxic', 'obscene', 'insult', 'identity_hate', 'toxic'].注释可以是这些类的多个，所以这是一个多标签分类问题.

I'm doing the Toxic Comment Text Classification Kaggle challenge. There are 6 classes: ['threat', 'severe_toxic', 'obscene', 'insult', 'identity_hate', 'toxic']. A comment can be multiple of these classes so it's a multi-label classification problem.

我用Keras构建了一个基本的神经网络，如下所示:

I built a basic neural network with Keras as follows:

model = Sequential()
model.add(Embedding(10000, 128, input_length=250))
model.add(Flatten())
model.add(Dense(100, activation='relu'))
model.add(Dense(len(classes), activation='sigmoid'))
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])

我运行以下行:

model.fit(X_train, train_y, validation_split=0.5, epochs=3)

并在3个纪元后获得99.11％的准确性.

and get 99.11% accuracy after 3 epochs.

但是，99.11％的准确度比最好的Kaggle提交要高得多.这让我觉得我要么是(a)过拟合，要么是b)滥用Keras的准确性.

However, 99.11% accuracy is a good bit higher than the best Kaggle submission. This makes me think I'm either (possibly both) a) overfitting or b) misusing Keras's accuracy.

1)当我将50％的数据用作验证拆分并且仅使用3个历元时，似乎有点难以适应.

1) Seems a bit hard to overfit when I'm using 50% of my data as a validation split and only 3 epochs.

2)此处的准确性仅仅是模型获取每个类的时间正确的百分比吗?

2) Is accuracy here just the percentage of the time the model gets each class correct?

因此，如果我输出[0, 0, 0, 0, 0, 1]并且正确的输出是[0, 0, 0, 0, 0, 0]，我的精度将是5/6?

So if I output [0, 0, 0, 0, 0, 1] and the correct output was [0, 0, 0, 0, 0, 0], my accuracy would be 5/6?

经过一番思考，我觉得这里的accuracy指标只是看我的模型以最高的置信度预测的类，并与实际情况进行比较.

After a bit of thought, I sort of think the accuracy metric here is just looking at the class my model predicts with highest confidence and comparing vs. ground truth.

因此，如果我的模型输出[0, 0, 0.9, 0, 0, 0]，它将把索引2(淫秽")的类与真实值进行比较.您认为这是怎么回事吗?

So if my model outputs [0, 0, 0.9, 0, 0, 0], it will compare the class at index 2 ('obscene') with the true value. Do you think this is what's happening?

感谢您提供的任何帮助！

Thanks for any help you can offer!