'attributeError:'Tensor'对象在使用keras通过预训练的VGG实现感知损失的过程中没有属性'_keras_history' [英] 'attributeError: 'Tensor' object has no attribute '_keras_history' during implementing perceptual loss with pretrained VGG using keras

问题描述

我正在尝试为视频输入的模型训练实现VGG感知损失. 我在问题 AttributeError:'Tensor'中实施了建议中的感知损失对象没有属性"_keras_history" :

I'm trying to implement the VGG perceptual loss for a model training for video inputs. I implemented the perceptual loss like the recommendation in the question AttributeError: 'Tensor' object has no attribute '_keras_history':

我的mainModel如下图所示: mainModel图

My mainModel looks like the following graph: Graph of mainModel

输入大小为(bathsize, frame_num, row, col, channel).我想获得中间帧的感知损失，即frame_num/2.

The input size is (bathsize, frame_num, row, col, channel). And I want to get the perceptual loss for the middle frame, that is, frame_num/2.

因此，我实现了以下lossModel:

So, I implemented the following lossModel:

lossModel = VGG19(weights='imagenet')
lossModel = Model(inputs=lossModel.input,outputs=lossModel.get_layer('block3_conv4').output)
lossOut = lossModel(mainModel.output[:,frame_num/2])
fullModel = Model(mainModel.input,lossOut)

但是我在fullModel = Model(mainModel.input, lossOut)行遇到错误消息:

But I faced an error message in the line fullModel = Model(mainModel.input, lossOut):

attributeError:张量"对象没有属性"_keras_history"

attributeError: 'Tensor' object has no attribute '_keras_history'

顺便说一句，我使用的是keras版本是'2.0.9'.

BTW, I'm using keras version is '2.0.9'.

有人可以帮我吗?

非常感谢！

推荐答案

大多数情况下，这意味着您要在图层外部进行计算.

This most of the times means that you're doing calculations outside layers.

一个keras模型需要由keras图层组成.不允许在层外进行操作.

A keras model needs to be made of keras layers. Operations outside layers are not allowed.

进行所有计算并将其放在Lambda层中: https://keras.io /layers/core/#lambda

Take all your calculations and put them inside Lambda layers: https://keras.io/layers/core/#lambda

在这里，mainModel.output[:,frame_num/2]是层外的操作.

Here, the mainModel.output[:,frame_num/2] is an operation outside a layer.

将其传输到Lambda层:

Transfer it to a Lambda layer:

lossModel = VGG19(weights='imagenet')
lossModel = Model(inputs=lossModel.input,outputs=lossModel.get_layer('block3_conv4').output)

#you must connect lossmodel and mainmodel somewhere!!!
output = lossModel(mainModel.output)

output = Lambda(lambda x: x[:,frame_num/2])(output)

fullModel = Model(mainModel.input, output)

这篇关于'attributeError:'Tensor'对象在使用keras通过预训练的VGG实现感知损失的过程中没有属性'_keras_history'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！