[英]How does the Keras training loop filter the loss values?
我有一个keras模型,设置如下(TF 1.2.1):
import tensorflow.contrib.keras as keras
model = keras.models.Sequential()
...
model.compile(loss=keras.losses.mean_squared_error,
optimizer=keras.optimizers.Adam(lr=1e-4))
model.summary()
Layer (type) Output Shape Param #
=================================================================
conv2d_1 (Conv2D) (None, 29, 29, 64) 6336
_________________________________________________________________
conv2d_2 (Conv2D) (None, 13, 13, 128) 204928
_________________________________________________________________
conv2d_3 (Conv2D) (None, 11, 11, 256) 295168
_________________________________________________________________
conv2d_4 (Conv2D) (None, 5, 5, 256) 590080
_________________________________________________________________
flatten_1 (Flatten) (None, 6400) 0
_________________________________________________________________
dense_1 (Dense) (None, 2) 12802
=================================================================
Total params: 1,109,314
Trainable params: 1,109,314
Non-trainable params: 0
输出是一个简单的浮点向量,并且根据需要收敛。 损失是均方误差。 输出示例:
18/100 [====>.........................] - ETA: 30s - loss: 31.5118
19/100 [====>.........................] - ETA: 29s - loss: 30.7577
20/100 [=====>........................] - ETA: 29s - loss: 29.7815
21/100 [=====>........................] - ETA: 28s - loss: 29.0535
22/100 [=====>........................] - ETA: 28s - loss: 28.1963
23/100 [=====>........................] - ETA: 28s - loss: 27.3314
24/100 [======>.......................] - ETA: 28s - loss: 26.7219
25/100 [======>.......................] - ETA: 28s - loss: 25.9702
26/100 [======>.......................] - ETA: 27s - loss: 25.4181
27/100 [=======>......................] - ETA: 27s - loss: 25.0638
28/100 [=======>......................] - ETA: 27s - loss: 24.6081
29/100 [=======>......................] - ETA: 26s - loss: 24.0928
损失似乎在稳步减少。 但是,当我查看实际损失( keras.callbacks.LambdaCallback@on_batch_end
)时,它并不是那么平滑:
25.473383
28.051779
20.519075
13.204493
20.74946
21.246254
25.611149
13.194682
13.268744
15.408422
17.183851
11.232637
14.493115
10.196851
我试图挖掘Keras源代码,但不了解幕后情况。 Keras如何过滤实际损失? 在源代码中哪里可以找到它?
谢谢!
因此,在进度条中实际显示的是在打印时在给定时期内执行的所有批次的损失的平均值。 (表示从2个批处理中的前2个开始,表示从3个时代后的前3个开始,依此类推)。 所以-您可以通过对第n
损失值取平均值来获得第n
n-th
纪元后打印的值。 您可以在此处在Progbar
定义中阅读。
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.