我正在尝试在每个时期的末尾获取y_true和y_pred。我使用fit_generator训练我的模型。我试图在每个时期后找到特异性。
class LossHistory(keras.callbacks.Callback):
def on_epoch_end(self, epoch, logs={}):
y_true = ?
y_pred = ?
loss_history = LossHistory
fit_generator(train_data, .. callbacks=[loss_history])
答案 0 :(得分:1)
默认情况下,您无权访问此信息,但可以通过将其传递给构造函数来为Callback
提供所需的任何属性。例如,如果您使用的是生成器(数据存储在generator.y
属性中):
class LossHistory(keras.callbacks.Callback):
def __init__(self, data_generator, **kwargs):
self.generator = data_generator
Super(LossHistory, self).__init__(**kwargs)
def on_epoch_end(self, epoch, logs={}):
y_true = self.generator.y
y_pred = self.model.predict_generator(self.generator)
loss_history = LossHistory(train_data_generator)