打印损失函数张量流 2.0 的所有项

Question

我正在定义一个自定义损失函数。例如，让我们采取loss function = L1 loss + L2 loss.当我做model.fit_generator()时，每批后都会打印整体损失函数。但我想看看L1 loss和L2 loss的个人价值观.我该怎么做？ 我想知道单个术语的值，以了解它们的相对尺度。

1. tf.print(l1_loss, output_stream=sys.stdout)抛出一个异常说tensorflow.python.eager.core._FallbackException: This function does not handle the case of the path where all inputs are not already EagerTensors..

2. 即使是tf.print('---')也只是在开始时打印---，而不是每批。

3. tf.keras.backend.print_tensor(l1_loss)没有打印任何内容

Answer 1

没有看到你的代码，我只能猜测你没有用@tf.function装饰器装饰你的自定义损失函数。

import numpy as np
import tensorflow as tf
@tf.function  # <-- Be sure to use this decorator.
def custom_loss(y_true, y_pred):
loss = tf.reduce_mean(tf.math.abs(y_pred - y_true))
tf.print(loss)  # <-- Use tf.print(), instead of print(). You can print not just 'loss', but any TF tensor in this function using this approach.
return loss
model = tf.keras.Sequential()
model.add(tf.keras.layers.Dense(1, input_shape=[8]))
model.compile(loss=custom_loss, optimizer="sgd")
x_data = tf.data.Dataset.from_tensor_slices([np.ones(8)] * 100)
y_data = tf.data.Dataset.from_tensor_slices([np.ones(1)] * 100)
data = tf.data.Dataset.zip((x_data, y_data)).batch(2)
model.fit_generator(data, steps_per_epoch=10, epochs=2)

输出如下所示，告诉您逐批损失值。

Epoch 1/2
0.415590227  1/10 [==>...........................] - ETA: 0s - loss: 0.41560.325590253
0.235590339
0.145590425
0.0555904508
0.034409523
0.0555904508
0.034409523
0.0555904508
0.034409523 10/10 [==============================] - 0s 11ms/step - loss: 0.1392 Epoch 2/2
0.0555904508  1/10 [==>...........................] - ETA: 0s - loss: 0.05560.034409523
0.0555904508
0.034409523
0.0555904508
0.034409523
0.0555904508
0.034409523
0.0555904508
0.034409523 10/10 [==============================] - 0s 498us/step - loss: 0.0450