ValueError:模型的输出张量必须是TensorFlow`Layer`的输出 [英] ValueError: Output tensors to a Model must be the output of a TensorFlow `Layer`

问题描述

我正在Keras的最后一层中使用一些tensorflow函数(reduce_sum和l2_normalize)构建模型，同时遇到此问题.我一直在寻找解决方案，但所有解决方案都与"Keras张量"有关.

I'm building a model in Keras using some tensorflow function (reduce_sum and l2_normalize) in the last layer while encountered this problem. I have searched for a solution but all of it related to "Keras tensor".

这是我的代码:

import tensorflow as tf;
from tensorflow.python.keras import backend as K

vgg16_model = VGG16(weights = 'imagenet', include_top = False, input_shape = input_shape);

fire8 = extract_layer_from_model(vgg16_model, layer_name = 'block4_pool');

pool8 = MaxPooling2D((3,3), strides = (2,2), name = 'pool8')(fire8.output);

fc1 = Conv2D(64, (6,6), strides= (1, 1), padding = 'same', name = 'fc1')(pool8);

fc1 = Dropout(rate = 0.5)(fc1);

fc2 = Conv2D(3, (1, 1), strides = (1, 1), padding = 'same', name = 'fc2')(fc1);

fc2 = Activation('relu')(fc2);

fc2 = Conv2D(3, (15, 15), padding = 'valid', name = 'fc_pooling')(fc2);

fc2_norm = K.l2_normalize(fc2, axis = 3);

est = tf.reduce_sum(fc2_norm, axis = (1, 2));
est = K.l2_normalize(est);

FC_model = Model(inputs = vgg16_model.input, outputs = est);

，然后显示错误:

ValueError:模型的输出张量必须是a的输出 TensorFlow Layer(因此保留过去的层元数据).成立: 张量("l2_normalize_3:0"，shape =(?, 3)，dtype = float32)

ValueError: Output tensors to a Model must be the output of a TensorFlow Layer (thus holding past layer metadata). Found: Tensor("l2_normalize_3:0", shape=(?, 3), dtype=float32)

我注意到在不将fc2层传递给这些函数的情况下，该模型可以正常工作:

I noticed that without passing fc2 layer to these functions, the model works fine:

FC_model = Model(inputs = vgg16_model.input, outputs = fc2);

有人可以向我解释这个问题以及如何解决的建议吗?

Can someone please explain to me this problem and some suggestion on how to fix it?

推荐答案

我已经找到一种解决此问题的方法. 对于遇到相同问题的任何人，您都可以使用Lambda层包装张量流操作，这就是我所做的:

I have found a way to work around to solve the problem. For anyone who encounters the same issue, you can use the Lambda layer to wrap your tensorflow operations, this is what I did:

from tensorflow.python.keras.layers import Lambda;

def norm(fc2):

    fc2_norm = K.l2_normalize(fc2, axis = 3);
    illum_est = tf.reduce_sum(fc2_norm, axis = (1, 2));
    illum_est = K.l2_normalize(illum_est);

    return illum_est;

illum_est = Lambda(norm)(fc2);

这篇关于ValueError:模型的输出张量必须是TensorFlow`Layer`的输出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！