渴望执行功能的输入不能是Keras符号张量 [英] Inputs to eager execution function cannot be Keras symbolic tensors
问题描述
我正在尝试在 tf.Keras （TensorFlow 2.0.0rc0）中针对稀疏的3-D U-Net实现与样本和像素相关的损耗加权注释数据（Cicek 2016，arxiv：1606.06650）。
I am trying to implement sample- and pixel-dependent dependent loss weighting in tf.Keras (TensorFlow 2.0.0rc0) for a 3-D U-Net with sparse annotation data (Cicek 2016, arxiv:1606.06650).
这是我的代码：
import numpy as np
import tensorflow as tf
from tensorflow.keras import layers, losses, models
# disabling eager execution makes this example work:
# tf.python.framework_ops.disable_eager_execution()
def get_loss_fcn(w):
def loss_fcn(y_true, y_pred):
loss = w * losses.mse(y_true, y_pred)
return loss
return loss_fcn
data_x = np.random.rand(5, 4, 1)
data_w = np.random.rand(5, 4)
data_y = np.random.rand(5, 4, 1)
x = layers.Input([4, 1])
w = layers.Input([4])
y = layers.Activation('tanh')(x)
model = models.Model(inputs=[x, w], outputs=y)
loss = get_loss_fcn(model.input[1])
# using another loss makes it work, too:
# loss = 'mse'
model.compile(loss=loss)
model.fit((data_x, data_w), data_y)
print('Done.')
在禁用急切执行时，此方法运行良好，但默认情况下，TensorFlow 2的要点之一是急切执行。我和那个目标之间是自定义损失函数，如您所见（使用'mse'作为损失也可以消除该错误）：
This runs fine when disabling eager execution, but one of the points of TensorFlow 2 is to have eager execution by default. What stands between me and that goal is the custom loss function, as you can see (using 'mse' as a loss removes that error, too):
File "MWE.py", line 30, in <module>
model.fit((data_x, data_w), data_y)
[...]
tensorflow.python.eager.core._SymbolicException: Inputs to eager execution function cannot be Keras symbolic tensors, but found [<tf.Tensor 'input_2:0' shape=(None, 4) dtype=float32>]
如何使这种结构以热切的执行力工作？
What can I do to make this kind of structure work with eager execution?
我曾经想过的一个想法是将 w 到输出 y 并将 y_pred 分成原始的 y_pred 和 w 的损失函数，但这是我要避免的技巧。不过，它的工作原理是用＃HERE 标记：
One idea that I had was to concatenate w to the output y and separate y_pred into the original y_pred and w in the loss function, but this is a hack I'd like to avoid. It works, though, with changes marked by # HERE:
import numpy as np
import tensorflow as tf
from tensorflow.keras import layers, losses, models
# HERE
def loss_fcn(y_true, y_pred):
w = y_pred[:, :, -1] # HERE
y_pred = y_pred[:, :, :-1] # HERE
loss = w * losses.mse(y_true, y_pred)
return loss
data_x = np.random.rand(5, 4, 1)
data_w = np.random.rand(5, 4, 1) # HERE
data_y = np.random.rand(5, 4, 1)
x = layers.Input([4, 1])
w = layers.Input([4, 1]) # HERE
y = layers.Activation('tanh')(x)
output = layers.Concatenate()([y, w]) # HERE
model = models.Model(inputs=[x, w], outputs=output) # HERE
loss = loss_fcn # HERE
model.compile(loss=loss)
model.fit((data_x, data_w), data_y)
print('Done.')
还有其他想法吗？
推荐答案
另一种解决方案是将权重作为附加的输出特征而不是输入特征。
One alternative solution is to pass weights as additional output features rather than input features.
完全没有权重相关的任何权重，权重仅出现在损失函数和 .fit（）调用中：
This keeps the model completely free of anything weights related, and the weights appear only in the loss function and the .fit() call:
import numpy as np
import tensorflow as tf
from tensorflow.keras import layers, losses, models
data_x = 2 * np.ones((7, 11, 15, 3), dtype=float)
data_y = 5 * np.ones((7, 9, 13, 5), dtype=float)
x = layers.Input(data_x.shape[1:])
y = layers.Conv2D(5, kernel_size=3)(x)
model = models.Model(inputs=x, outputs=y)
def loss(y_true, y_pred):
(y_true, w) = tf.split(y_true, num_or_size_splits=[-1, 1], axis=-1)
loss = tf.squeeze(w, axis=-1) * losses.mse(y_true, y_pred)
tf.print(tf.math.reduce_mean(y_true), "== 5")
tf.print(tf.math.reduce_mean(w), "== 3")
return loss
model.compile(loss=loss)
data_w = 3 * np.ones((7, 9, 13, 1), dtype=float)
data_yw = np.concatenate((data_y, data_w), axis=-1)
model.fit(data_x, data_yw)
一个缺点仍然是，合并 y 和
One drawback still is that you need to manipulate (potentially) large arrays when merging y and w in numpy.stack(), so anymore more TensorFlow-like will be appreciated.
这篇关于渴望执行功能的输入不能是Keras符号张量的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！
