python - 每个纪元后的自定义回调以记录某些信息

Question

我知道如何 save the model after every epoch :

savemodel = ModelCheckpoint(filepath='models/model_{epoch:02d}-{loss:.2f}.h5')
model.fit(X, Y, batch_size=4, epochs=32, verbose=1, callbacks=[savemodel])

如何使用自定义回调函数来记录某些信息:

def write_metrics(): 
    with open('log.txt', 'a') as f:  # append to the log file
        f.write('{epoch:02d}: loss = {loss:.1f}')

model.fit(X, Y, batch_size=4, epochs=32, verbose=1, callbacks=[savemodel, write_metrics])

?

使用此代码将无法工作，因为 {loss} 和 {epoch} 未在 f.write('{epoch:02d} : loss = {loss:.1f}').

Answer 1

这是解决方案，通过子类化 Callback:

from keras.callbacks import Callback

class MyLogger(Callback):
    def on_epoch_end(self, epoch, logs=None):
        with open('log.txt', 'a+') as f:
            f.write('%02d %.3f\n' % (epoch, logs['loss']))

然后

mylogger = MyLogger()
model.fit(X, Y, batch_size=32, epochs=32, verbose=1, callbacks=[mylogger])

甚至

model.fit(X, Y, batch_size=32, epochs=32, verbose=1, callbacks=[MyLogger()])