[英]How do I plot steps_per_epoch against loss using fit_generator in Keras?
我有以下代码,我想 plot loss
与steps_per_epoch
的关系图
model = unet(pretrained=False)
model.compile(optimizer=Adam(0.005), loss="binary_crossentropy",
metrics=["accuracy"])
history = model.fit_generator(train_gen, steps_per_epoch=500, epochs=5,
callbacks=[dynamic_lr, chkp])
其中lr
和chkp
是我对 model 的回调:
def lr_scheduler(epoch, lr):
if epoch <= 2:
lr = 0.002
return lr
lr = 0.001
return lr
chkp = keras.callbacks.ModelCheckpoint(
filepath="mypath/model.hdf5",
monitor="loss",
verbose=1,
save_best_only=True,
mode="min",
)
dynamic_lr = LearningRateScheduler(lr_scheduler, verbose=1)
我不认为history
字典会为时代的每一步都带来loss
,但是有什么办法吗?
您可以从历史 object 中获取训练准确率、训练损失、验证准确率和验证损失的值。 请参阅下面的代码。
training_accuracy=history.history['accuracy']
training_loss=history.history['loss']
valid_accuracy=history.history['val_accuracy']
valid_loss=history.history['val_loss']
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.