Graph disconnected: cannot obtain value for tensor Tensor

在keras中，如果要将一个模型的输出与另一个模型的输出连接起来，第二个模型的接收的输入而不是直接传递的该张量：

def Generator(image_shape=(512,512,3):inputs = Input(image_shape)# 5 convolution Layers# 5 Deconvolution Layers along with concatenation# output shape is (512,512,3) model=Model(inputs=inputs,outputs=outputs, name='Generator')return model, outputdef Discriminator(Generator_output, image_shape=(512,512,3)):inputs=Input(image_shape)concatenated_input=concatenate([Generator_output, inputs], axis=-1)# Now start applying Convolution Layers on concatenated_input# Deconvolution Layersreturn Model(inputs=inputs,outputs=outputs, name='Discriminator')#启动架构G, Generator_output=Generator(image_shape=(512,512,3))
G.summaryD=Discriminator(Generator_output, image_shape=(512,512,3))
D.summary()

像上述代码则会出现如下错误：

Graph disconnected: cannot obtain value for tensor Tensor("input_1:0", shape=(?, 512, 512, 3), dtype=float32) at layer "input_1". The following previous layers were accessed without issue: []

所以为了避免这样的错误，在接收另一个模型输出时应该为：

def Discriminator(gen_output_shape, image_shape=(512,512,3)):inputs=Input(image_shape)gen_output=Input(gen_output_shape)concatenated_input=concatenate([gen_output, inputs], axis=-1)# Now start applying Convolution Layers on concatenated_input# Deconvolution Layersreturn Model(inputs=[inputs, gen_output],outputs=outputs, name='Discriminator')#然后你可以像层一样使用它：G=Generator(image_shape=(512,512,3))
D=Discriminator((512,512,3), image_shape=(512,512,3))
some_other_image_input = Input((512,512,3))
discriminator_output = D(some_other_image_input, G) # model is used like a layer
# so the output of G is connected to the input of D
D.summary()
gan = Model(inputs=[all,your,inputs], outputs=[outputs,for,training])
# you can still use G and D like separate models, save them, train them etc

这是在keras多模型融合时出现的问题。

Graph disconnected: cannot obtain value for tensor Tensor相关推荐

解决tf报Graph disconnected错误
WARNING:tensorflow:Functional model inputs must come from tf.keras.Input (thus holding past layer me ...
Cannot interpret feed_dict key as Tensor: Tensor Tensor(“keras_learning_phase:0“, shape=(),
报错信息:Cannot interpret feed_dict key as Tensor: Tensor Tensor("keras_learning_phase:0", sha ...
Tracer cannot set value trace for type None. Supported types are tensor, tensor list, and tuple
Tracer cannot set value trace for type None. Supported types are tensor, tensor list, and tuple of t ...
Tensorflow学习笔记2：About Session, Graph, Operation and Tensor
简介上一篇笔记:Tensorflow学习笔记1:Get Started 我们谈到Tensorflow是基于图(Graph)的计算系统.而图的节点则是由操作(Operation)来构成的,而图的各个节 ...
tensor torch 构造_TORCH.TENSOR
tensor 是一个由单一数据类型数据组成的多维矩阵 torch 定义了8种 CPU 张量和 GPU张量 tensor可以用torch.tensor(data)创建,data可以是 python li ...
tensor判断是否相等_PyTorch的Tensor(中)
背景在PyTorch的Tensor系列上一篇文章中: Gemfield:PyTorch的Tensor(上)zhuanlan.zhihu.com Gemfield介绍了一个Tensor的创建过程,特 ...
pytorch一天速成第一部分——基础入门Tensor和cuda
PyTorch是什么? 这是一个基于Python的科学计算包,其旨在服务两类场合: 替代numpy发挥GPU潜能一个提供了高度灵活性和效率的深度学习实验性平台导入包和版本查询 import tor ...
对tensorflow中的tensor、placeholder及feed_dict的理解
以前不知道tf.placeholder的feed_dict格式要求,以为随便是什么格式都可以,直到自己在做测试的时候出现以下错误才知道tf.placeholder 的feed_dict填充内容不可以 ...
【pytorch】|tensor grad
计算图与动态图机制计算图是用来描述运算的有向无环图.计算图有两个主要元素:结点(Node)和边(Edge).结点表示数据,如向量,矩阵,张量:边表示运算,如加减乘除卷积等. 下面用计算图表示:y = ...

Graph disconnected: cannot obtain value for tensor Tensor

Graph disconnected: cannot obtain value for tensor Tensor相关推荐

最新文章

热门文章