在自定义回调中访问验证数据 [英] Accessing validation data within a custom callback

问题描述

我正在安装train_generator，并且希望通过自定义回调在我的validate_generator上计算自定义指标. 如何在自定义回调中访问参数validation_steps和validation_data? 它不在self.params中，也无法在self.model中找到.这就是我想要做的.任何其他方法都将受到欢迎.

I'm fitting a train_generator and by means of a custom callback I want to compute custom metrics on my validation_generator. How can I access params validation_steps and validation_data within a custom callback? It’s not in self.params, can’t find it in self.model either. Here's what I'd like to do. Any different approach'd be welcomed.

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

keras: 2.1.1

更新

我设法将验证数据传递给自定义回调的构造函数.但是，这会导致令人讨厌的内核似乎已经死亡.它将自动重新启动."信息.我怀疑这是否是正确的方法.有什么建议吗?

I managed to pass my validation data to a custom callback's constructor. However, this results in an annoying "The kernel appears to have died. It will restart automatically." message. I doubt if this is the right way to do it. Any suggestion?

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)

推荐答案

您可以直接在self.validation_data上进行迭代，以在每个时期结束时汇总所有验证数据.如果要计算精度，请在整个验证数据集中调用和F1:

You can iterate directly over self.validation_data to aggregate all the validation data at the end of each epoch. If you want to calculate precision, recall and F1 across the complete validation dataset:

# 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，您可以将有效参数添加到回调参数:

Then you can add valid_metrics to the callback argument:

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

如果您希望其他回调使用这些措施，请确保将其放在回调的开头.

Be sure to put it at the beginning of the callbacks in case you want other callbacks to use these measures.

这篇关于在自定义回调中访问验证数据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IT屋！