을 계산하는 방법 F1 매크로에서 Keras?

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()))

model.compile(loss='binary_crossentropy',
          optimizer= "adam",
          metrics=[f1])

return 2*((precision*recall)/(precision+recall+K.epsilon()))

    for mini_batch in range(epochs):
        model_hist = model.fit(X_train, Y_train, batch_size=batch_size, epochs=1,
                            verbose=2, validation_data=(X_val, Y_val))

        precision = model_hist.history['val_precision'][0]
        recall = model_hist.history['val_recall'][0]
        f_score = (2.0 * precision * recall) / (precision + recall)
        print 'F1-SCORE {}'.format(f_score)

from sklearn.model_selection import train_test_split
import tensorflow as tf
from tensorflow import keras
import numpy as np

def create_f1():
    def f1_function(y_true, y_pred):
        y_pred_binary = tf.where(y_pred>=0.5, 1., 0.)
        tp = tf.reduce_sum(y_true * y_pred_binary)
        predicted_positives = tf.reduce_sum(y_pred_binary)
        possible_positives = tf.reduce_sum(y_true)
        return tp, predicted_positives, possible_positives
    return f1_function

class F1_score(keras.metrics.Metric):
    def __init__(self, **kwargs):
        super().__init__(**kwargs) # handles base args (e.g., dtype)
        self.f1_function = create_f1()
        self.tp_count = self.add_weight("tp_count", initializer="zeros")
        self.all_predicted_positives = self.add_weight('all_predicted_positives', initializer='zeros')
        self.all_possible_positives = self.add_weight('all_possible_positives', initializer='zeros')

    def update_state(self, y_true, y_pred,sample_weight=None):
        tp, predicted_positives, possible_positives = self.f1_function(y_true, y_pred)
        self.tp_count.assign_add(tp)
        self.all_predicted_positives.assign_add(predicted_positives)
        self.all_possible_positives.assign_add(possible_positives)

    def result(self):
        precision = self.tp_count / self.all_predicted_positives
        recall = self.tp_count / self.all_possible_positives
        f1 = 2*(precision*recall)/(precision+recall)
        return f1

X = np.random.random(size=(1000, 10))     
Y = np.random.randint(0, 2, size=(1000,))
X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=0.2)

model = keras.models.Sequential([
    keras.layers.Dense(5, input_shape=[X.shape[1], ]),
    keras.layers.Dense(1, activation='sigmoid')
])

model.compile(loss='binary_crossentropy', optimizer='SGD', metrics=[F1_score()])

history = model.fit(X_train, y_train, epochs=5, validation_data=(X_test, y_test))

from tensorflow.python.keras.models import Sequential, Model
from sklearn.metrics import  f1_score
from tensorflow.keras.callbacks import Callback
from tensorflow.python.keras import optimizers

optimizer = optimizers.SGD(lr=0.0001, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(optimizer=optimizer, loss="binary_crossentropy", metrics=['accuracy'])
model.summary()

class Metrics(Callback):
    def __init__(self, model, valid_data, true_outputs):
        super(Callback, self).__init__()
        self.model=model
        self.valid_data=valid_data    #the validation data I'm getting metrics on
        self.true_outputs=true_outputs    #the ground truth of my validation data
        self.steps=len(self.valid_data)

    def on_epoch_end(self, args,*kwargs):
        gen=generator(self.valid_data)     #generator yielding the validation data
        val_predict = (np.asarray(self.model.predict(gen, batch_size=1, verbose=0, steps=self.steps)))

        """
        The function from_proba_to_output is used to transform probabilities  
        into an understandable format by sklearn's f1_score function
        """
        val_predict=from_proba_to_output(val_predict, 0.5)
        _val_f1 = f1_score(self.true_outputs, val_predict)
        print ("val_f1: ", _val_f1, "   val_precision: ", _val_precision, "   _val_recall: ", _val_recall)

def from_proba_to_output(probabilities, threshold):
    outputs = np.copy(probabilities)
    for i in range(len(outputs)):

        if (float(outputs[i])) > threshold:
            outputs[i] = int(1)
        else:
            outputs[i] = int(0)
    return np.array(outputs)

    model.fit_generator(
train_generator, epochs=nbr_epochs, verbose=1, validation_data=valid_generator, callbacks=[Metrics(model, valid_data)])