TypeError:模型的输出张量必须是Keras张量 [英] TypeError: Output tensors to a Model must be Keras tensors

问题描述

我想拍摄一个输入图像img(也具有负值)并将其输入两个激活层.但是，我想做一个简单的转换，例如将整个图像乘以-1.0:

I want to take an input image img (which also has negative values) and feed it into two activation layers. However, I want to make a simple transformation e.g. multiply the whole image with -1.0:

left = Activation('relu')(img)
right = Activation('relu')(tf.mul(img, -1.0))

如果我这样做，我会得到:

If I do it this way I am getting:

TypeError: Output tensors to a Model must be Keras tensors. Found: Tensor("add_1:0", shape=(?, 5, 1, 3), dtype=float32)

，我不确定该如何解决.有没有可以用于这种情况的Keras侧mul()方法?还是可以以某种方式包装tf.mul(img, -1.0)的结果，以便可以将其传递给Activation?

and I am not sure how I can fix that. Is there a Keras side mul() method that I can use for such a thing? Or can I wrap the result of tf.mul(img, -1.0) somehow such that I can pass it on to Activation?

请注意:负值可能很重要.从而变换图像最小只是0.0在这里不是解决方案.

Please note: The negative values may be important. Thus transforming the image s.t. the minimum is simply 0.0 is not a solution here.

我也遇到相同的错误

left = Activation('relu')(conv)
right = Activation('relu')(-conv)

---

相同的错误:

---

The same error for:

import tensorflow as tf

minus_one = tf.constant([-1.])

# ...

    right = merge([conv, minus_one], mode='mul')

推荐答案

是否创建Lambda层来包装功能?

Does creating a Lambda Layer to wrap your function work?

请参见文档此处

from keras.layers import Lambda
import tensorflow as tf

def mul_minus_one(x):
    return tf.mul(x,-1.0)
def mul_minus_one_output_shape(input_shape):
    return input_shape

myCustomLayer = Lambda(mul_minus_one, output_shape=mul_minus_one_output_shape)
right = myCustomLayer(img)
right = Activation('relu')(right)

这篇关于TypeError:模型的输出张量必须是Keras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！