[英]Inputs to eager execution function cannot be Keras symbolic tensors, but found
[英]Inputs to eager execution function cannot be Keras symbolic tensors
我正在尝试在tf.Keras
(TensorFlow 2.0.0rc0) 中为具有稀疏注释数据的 3-D U-Net (Cicek 2016, arxiv:1606.06650) 实现依赖于tf.Keras
和像素的相关损失加权。
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.')
这在禁用 Eager Execution 时运行良好,但 TensorFlow 2 的要点之一是默认情况下具有 Eager Execution。 正如你所看到的,我和那个目标之间的区别是自定义损失函数(使用'mse'
作为损失也消除了该错误):
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>]
我该怎么做才能使这种结构与急切执行一起工作?
我的一个想法是将w
连接到输出y
并将y_pred
分离为损失函数中的原始y_pred
和w
,但这是我想避免的一种黑客行为。 不过,它的工作原理是用# HERE
标记的更改:
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?
一种替代解决方案是将权重作为附加输出特征而不是输入特征传递。
这使模型完全没有任何与权重相关的东西,权重只出现在损失函数和.fit()
调用中:
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,在numpy.stack()
合并y
和w
时,您需要操作(可能)大型数组,因此将不胜感激更多类似 TensorFlow 的方法。
其它的办法:
from tensorflow.keras import layers, models, losses
import numpy as np
def loss_fcn(y_true, y_pred, w):
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)
data_y = np.random.rand(5, 4, 1)
x = layers.Input([4, 1])
y_true = layers.Input([4, 1])
w = layers.Input([4])
y = layers.Activation('tanh')(x)
model = models.Model(inputs=[x, y_true, w], outputs=y)
model.add_loss(loss_fcn(y, y_true, w))
model.compile()
model.fit((data_x, data_y, data_w))
我认为这是最优雅的解决方案。
如果您将 fit 行替换为
model.fit((data_x, data_y, data_w))
所以:
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_y, data_w))
print('Done.')
此外,我发现在损失函数中实现的 tf.reduce_mean、K.mean、tf.square、tf.exp 等会导致相同的错误。
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.