计算keras中的微观F1分数

Question

我有一个包含15个不平衡类的数据集，并试图用keras进行多标签分类

我试着用微F-1分数作为衡量标准

我的模型：

# Create a VGG instance
model_vgg = tf.keras.applications.VGG19(weights = 'imagenet', pooling = 'max', include_top = False, 
input_shape = (512, 512, 3))

# Freeze the layers which you don't want to train. 
for layer in model_vgg.layers[:-5]:
layer.trainable = False

# Adding custom Layers 
x = model_vgg.output
x = Flatten()(x)
x = Dense(1024, activation = "relu")(x)
x = Dropout(0.5)(x)
x = Dense(1024, activation = "relu")(x)
predictions = Dense(15, activation = "sigmoid")(x)

# creating the final model 
model_vgg_final = Model(model_vgg.input, predictions)

# Print the summary
model_vgg_final.summary()

对于F1分数，我使用来自this question的自定义指标

from keras import backend as K

def f1(y_true, y_pred):
    def recall(y_true, y_pred):
        """Recall metric.

    Only computes a batch-wise average of recall.

    Computes the recall, a metric for multi-label classification of
    how many relevant items are selected.
    """
    true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))
    possible_positives = K.sum(K.round(K.clip(y_true, 0, 1)))
    recall = true_positives / (possible_positives + K.epsilon())
    return recall

    def precision(y_true, y_pred):
        """Precision metric.

    Only computes a batch-wise average of precision.

    Computes the precision, a metric for multi-label classification of
    how many selected items are relevant.
    """
    true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))
    predicted_positives = K.sum(K.round(K.clip(y_pred, 0, 1)))
    precision = true_positives / (predicted_positives + K.epsilon())
    return precision

    precision = precision(y_true, y_pred)
    recall = recall(y_true, y_pred)
    return 2*((precision*recall)/(precision+recall+K.epsilon()))

在编译模型时，我使用了二进制交叉熵和自定义F-1

# Compile a model
model_vgg_final.compile(optimizer = 'adam', loss = 'binary_crossentropy', metrics = [f1]) 

我监控F-1是否提前停止

# Early stopping
early_stopping = EarlyStopping(monitor = 'f1', patience = 5)

# Training the model
history_vgg = model_vgg_final.fit(train_generator, steps_per_epoch = 10, epochs = 30, verbose = 1, 
callbacks = [early_stopping], validation_data = valid_generator)

如何更新此自定义函数并获得micro F-1作为度量？我也很感激关于我的方法的建议

在scikit-learn documentation中有信息，但不确定如何将其合并到keras中

Answer 1

好问题

您在那里提供的链接指向在旧版本的Keras中如何计算指标（请注意，简短的解释）。问题是，在旧的Keras（1.X）中，度量是按批计算的，这当然会导致不正确的全局结果。在keras2.X中，内置的it度量被删除

但是，您的问题有解决方案

1. 您可以实现自己的自定义回调。您可以在这里检查我的答案，它保证在TensorFlow2.x:How to get other metrics in Tensorflow 2.0 (not only accuracy)?中工作
2. 您可以使用tensorflow-addons>pip install tensorflow-addonsTensorFlow addons是一个非常好的包，它包含了基本TensorFlow包中不可用的多种功能和特性。这里，F1Score是一个内置的度量，因此您可以直接使用它

例如：

model.compile(optimizer=tf.keras.optimizers.Adam(learning_rate=0.00001),
                      loss=tf.keras.losses.BinaryCrossentropy(),
                      metrics=[tf.keras.metrics.BinaryAccuracy(),
                               tfa.metrics.F1Score(num_classes=number_of_classes, average='micro',threshold=0.5),

请注意“micro”参数的用法，它实际上正好代表您想要的内容，即microf1-score