python - Keras 训练循环如何过滤损失值？

Question

我的 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，它会根据需要收敛。损失是均方误差。示例输出:

 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，情况并不那么顺利:

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

我试图深入研究 Keras 源代码，但无法理解幕后发生的事情。 Keras 如何过滤实际损失？在源代码中哪里可以找到这个？

谢谢!

Answer 1

因此，progbar 中实际显示的是打印时给定时期内执行的所有批处理的损失平均值。 (2 个批处理后前 2 个的平均值，3 个时期后前 3 个的平均值，依此类推)。因此，您可以通过对第一个 n 损失值取平均值来获得第 n 个 epoch 之后打印的值。您可以阅读here在 Progbar 定义中。