急切執行函數的輸入不能是 Keras 符號張量

Question

我正在嘗試在tf.Keras (TensorFlow 2.0.0rc0) 中為具有稀疏注釋數據的 3-D U-Net (Cicek 2016, arxiv:1606.06650) 實現依賴於tf.Keras和像素的相關損失加權。

這是我的代碼：

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.')

這在禁用 Eager Execution 時運行良好，但 TensorFlow 2 的要點之一是默認情況下具有 Eager Execution。 正如你所看到的，我和那個目標之間的區別是自定義損失函數（使用'mse'作為損失也消除了該錯誤）：

  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>]

我該怎么做才能使這種結構與急切執行一起工作？

我的一個想法是將w連接到輸出y並將y_pred分離為損失函數中的原始y_pred和w ，但這是我想避免的一種黑客行為。 不過，它的工作原理是用# HERE標記的更改：

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.')

還有其他想法嗎？

Answer 1

一種替代解決方案是將權重作為附加輸出特征而不是輸入特征傳遞。

這使模型完全沒有任何與權重相關的東西，權重只出現在損失函數和.fit()調用中：

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)

一個缺點仍然是，在numpy.stack()合並y和w時，您需要操作（可能）大型數組，因此將不勝感激更多類似 TensorFlow 的方法。

Answer 2

其它的辦法：

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))

我認為這是最優雅的解決方案。

Answer 3

如果您將 fit 行替換為

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，我發現在損失函數中實現的 tf.reduce_mean、K.mean、tf.square、tf.exp 等會導致相同的錯誤。