在自定義回調中訪問驗證數據

Question

我正在安裝 train_generator 並通過自定義回調我想在我的validation_generator 上計算自定義指標。 如何在自定義回調中訪問參數validation_steps和validation_data ？ 它不在self.params ，也無法在self.model找到。 這就是我想要做的。 歡迎任何不同的方法。

model.fit_generator(generator=train_generator,
                    steps_per_epoch=steps_per_epoch,
                    epochs=epochs,
                    validation_data=validation_generator,
                    validation_steps=validation_steps,
                    callbacks=[CustomMetrics()])


class CustomMetrics(keras.callbacks.Callback):

    def on_epoch_end(self, batch, logs={}):        
        for i in validation_steps:
             # features, labels = next(validation_data)
             # compute custom metric: f(features, labels) 
        return

keras：2.1.1

更新

我設法將我的驗證數據傳遞給自定義回調的構造函數。 但是，這會導致令人討厭的“內核似乎已經死了。它將自動重新啟動”。 信息。 我懷疑這是否是正確的方法。 有什么建議嗎？

class CustomMetrics(keras.callbacks.Callback):

    def __init__(self, validation_generator, validation_steps):
        self.validation_generator = validation_generator
        self.validation_steps = validation_steps


    def on_epoch_end(self, batch, logs={}):

        self.scores = {
            'recall_score': [],
            'precision_score': [],
            'f1_score': []
        }

        for batch_index in range(self.validation_steps):
            features, y_true = next(self.validation_generator)            
            y_pred = np.asarray(self.model.predict(features))
            y_pred = y_pred.round().astype(int) 
            self.scores['recall_score'].append(recall_score(y_true[:,0], y_pred[:,0]))
            self.scores['precision_score'].append(precision_score(y_true[:,0], y_pred[:,0]))
            self.scores['f1_score'].append(f1_score(y_true[:,0], y_pred[:,0]))
        return

metrics = CustomMetrics(validation_generator, validation_steps)

model.fit_generator(generator=train_generator,
                    steps_per_epoch=steps_per_epoch,
                    epochs=epochs,
                    validation_data=validation_generator,
                    validation_steps=validation_steps,
                    shuffle=True,
                    callbacks=[metrics],
                    verbose=1)

Answer 1

您可以直接迭代 self.validation_data 以在每個時期結束時聚合所有驗證數據。 如果要計算整個驗證數據集的准確率、召回率和 F1：

# Validation metrics callback: validation precision, recall and F1
# Some of the code was adapted from https://medium.com/@thongonary/how-to-compute-f1-score-for-each-epoch-in-keras-a1acd17715a2
class Metrics(callbacks.Callback):

    def on_train_begin(self, logs={}):
        self.val_f1s = []
        self.val_recalls = []
        self.val_precisions = []

    def on_epoch_end(self, epoch, logs):
        # 5.4.1 For each validation batch
        for batch_index in range(0, len(self.validation_data)):
            # 5.4.1.1 Get the batch target values
            temp_targ = self.validation_data[batch_index][1]
            # 5.4.1.2 Get the batch prediction values
            temp_predict = (np.asarray(self.model.predict(
                                self.validation_data[batch_index][0]))).round()
            # 5.4.1.3 Append them to the corresponding output objects
            if(batch_index == 0):
                val_targ = temp_targ
                val_predict = temp_predict
            else:
                val_targ = np.vstack((val_targ, temp_targ))
                val_predict = np.vstack((val_predict, temp_predict))

        val_f1 = round(f1_score(val_targ, val_predict), 4)
        val_recall = round(recall_score(val_targ, val_predict), 4)
        val_precis = round(precision_score(val_targ, val_predict), 4)

        self.val_f1s.append(val_f1)
        self.val_recalls.append(val_recall)
        self.val_precisions.append(val_precis)

        # Add custom metrics to the logs, so that we can use them with
        # EarlyStop and csvLogger callbacks
        logs["val_f1"] = val_f1
        logs["val_recall"] = val_recall
        logs["val_precis"] = val_precis

        print("— val_f1: {} — val_precis: {} — val_recall {}".format(
                 val_f1, val_precis, val_recall))
        return

valid_metrics = Metrics()

然后您可以將 valid_metrics 添加到回調參數中：

your_model.fit_generator(..., callbacks = [valid_metrics])

請務必將其放在回調的開頭，以防您希望其他回調使用這些措施。

Answer 2

我正在鎖定相同問題的解決方案，然后我在此處接受的答案中找到了您的解決方案和另一個解決方案。 如果第二個解決方案有效，我認為這比在“紀元結束時”再次迭代徹底的所有驗證要好

這個想法是將目標和 pred 占位符保存在變量中，並通過“批處理結束時”的自定義回調更新變量

Answer 3

就是這樣：

from sklearn.metrics import r2_score

class MetricsCallback(keras.callbacks.Callback):
    def on_epoch_end(self, epoch, logs=None):
        if epoch:
            print(self.validation_data[0])
            x_test = self.validation_data[0]
            y_test = self.validation_data[1]
            predictions = self.model.predict(x_test)
            print('r2:', r2_score(prediction, y_test).round(2))

model.fit( ..., callbacks=[MetricsCallback()])

參考

凱拉斯 2.2.4

Answer 4

Verdant89 犯了幾個錯誤，沒有實現所有功能。 下面的代碼應該可以工作。

class Metrics(callbacks.Callback):

def on_train_begin(self, logs={}):
    self.val_f1s = []
    self.val_recalls = []
    self.val_precisions = []

def on_epoch_end(self, epoch, logs):
    # 5.4.1 For each validation batch
    for batch_index in range(0, len(self.validation_data[0])):
        # 5.4.1.1 Get the batch target values
        temp_target = self.validation_data[1][batch_index]
        # 5.4.1.2 Get the batch prediction values
        temp_predict = (np.asarray(self.model.predict(np.expand_dims(
                            self.validation_data[0][batch_index],axis=0)))).round()
        # 5.4.1.3 Append them to the corresponding output objects
        if batch_index == 0:
            val_target = temp_target
            val_predict = temp_predict
        else:
            val_target = np.vstack((val_target, temp_target))
            val_predict = np.vstack((val_predict, temp_predict))

    tp, tn, fp, fn = self.compute_tptnfpfn(val_target, val_predict)
    val_f1 = round(self.compute_f1(tp, tn, fp, fn), 4)
    val_recall = round(self.compute_recall(tp, tn, fp, fn), 4)
    val_precis = round(self.compute_precision(tp, tn, fp, fn), 4)

    self.val_f1s.append(val_f1)
    self.val_recalls.append(val_recall)
    self.val_precisions.append(val_precis)

    # Add custom metrics to the logs, so that we can use them with
    # EarlyStop and csvLogger callbacks
    logs["val_f1"] = val_f1
    logs["val_recall"] = val_recall
    logs["val_precis"] = val_precis

    print("— val_f1: {} — val_precis: {} — val_recall {}".format(
             val_f1, val_precis, val_recall))
    return

def compute_tptnfpfn(self,val_target,val_predict):
    # cast to boolean
    val_target = val_target.astype('bool')
    val_predict = val_predict.astype('bool')

    tp = np.count_nonzero(val_target * val_predict)
    tn = np.count_nonzero(~val_target * ~val_predict)
    fp = np.count_nonzero(~val_target * val_predict)
    fn = np.count_nonzero(val_target * ~val_predict)

    return tp, tn, fp, fn

def compute_f1(self,tp, tn, fp, fn):
    f1 = tp*1. / (tp + 0.5*(fp+fn) + sys.float_info.epsilon)
    return f1

def compute_recall(self,tp, tn, fp, fn):
    recall = tp*1. / (tp + fn + sys.float_info.epsilon)
    return recall

def compute_precision(self,tp, tn, fp, fn):
    precision = tp*1. / (tp + fp + sys.float_info.epsilon)
    return precision