ValueError异常：输入“平坦”的形状不完全定义

Question

我试图运行this code，但得到以下错误：

Using TensorFlow backend. 
E c:\tf_jenkins\home\workspace\release-win\device\cpu\os\windows\tensorflow\core\framework\op_kernel.cc:943] OpKernel ('op: "BestSplits" device_type: "CPU"') for unknown op: BestSplits 
E c:\tf_jenkins\home\workspace\release-win\device\cpu\os\windows\tensorflow\core\framework\op_kernel.cc:943] OpKernel ('op: "CountExtremelyRandomStats" device_type: "CPU"') for unknown op: CountExtremelyRandomStats 
E c:\tf_jenkins\home\workspace\release-win\device\cpu\os\windows\tensorflow\core\framework\op_kernel.cc:943] OpKernel ('op: "FinishedNodes" device_type: "CPU"') for unknown op: FinishedNodes 
E c:\tf_jenkins\home\workspace\release-win\device\cpu\os\windows\tensorflow\core\framework\op_kernel.cc:943] OpKernel ('op: "GrowTree" device_type: "CPU"') for unknown op: GrowTree 
E c:\tf_jenkins\home\workspace\release-win\device\cpu\os\windows\tensorflow\core\framework\op_kernel.cc:943] OpKernel ('op: "ReinterpretStringToFloat" device_type: "CPU"') for unknown op: ReinterpretStringToFloat 
E c:\tf_jenkins\home\workspace\release-win\device\cpu\os\windows\tensorflow\core\framework\op_kernel.cc:943] OpKernel ('op: "SampleInputs" device_type: "CPU"') for unknown op: SampleInputs 
E c:\tf_jenkins\home\workspace\release-win\device\cpu\os\windows\tensorflow\core\framework\op_kernel.cc:943] OpKernel ('op: "ScatterAddNdim" device_type: "CPU"') for unknown op: ScatterAddNdim 
E c:\tf_jenkins\home\workspace\release-win\device\cpu\os\windows\tensorflow\core\framework\op_kernel.cc:943] OpKernel ('op: "TopNInsert" device_type: "CPU"') for unknown op: TopNInsert 
E c:\tf_jenkins\home\workspace\release-win\device\cpu\os\windows\tensorflow\core\framework\op_kernel.cc:943] OpKernel ('op: "TopNRemove" device_type: "CPU"') for unknown op: TopNRemove 
E c:\tf_jenkins\home\workspace\release-win\device\cpu\os\windows\tensorflow\core\framework\op_kernel.cc:943] OpKernel ('op: "TreePredictions" device_type: "CPU"') for unknown op: TreePredictions 
E c:\tf_jenkins\home\workspace\release-win\device\cpu\os\windows\tensorflow\core\framework\op_kernel.cc:943] OpKernel ('op: "UpdateFertileSlots" device_type: "CPU"') for unknown op: UpdateFertileSlots 
Model loaded. 
Traceback (most recent call last): 
    File "classifier_from_little_data_script_3.py", line 64, in <module> 
    top_model.add(Flatten(input_shape=model.output_shape[1:])) 
    File "C:\Python35\lib\site-packages\keras\models.py", line 430, in add 
    layer(x) 
    File "C:\Python35\lib\site-packages\keras\engine\topology.py", line 583, in __call__ 
    output_shape = self.compute_output_shape(input_shape) 
    File "C:\Python35\lib\site-packages\keras\layers\core.py", line 488, in compute_output_shape 
    '(got ' + str(input_shape[1:]) + '. ' 
ValueError: The shape of the input to "Flatten" is not fully defined (got (None, None, 512). Make sure to pass a complete "input_shape" or "batch_input_shape" argument to the first layer in your model. 

我怎样才能解决这个问题呢？

谢谢。

Answer 1

基于@ umutto的评论，那些是解决这一问题的变化：

input_tensor = Input(shape=(150,150,3)) 
# build the VGG16 network 
model = applications.VGG16(weights='imagenet', include_top=False, input_tensor=input_tensor) 

Answer 2

万一别人正面临着类似的问题，并想知道为什么有问题的错误被抛出，我会只是增加更多细节到@Simplicity's answer：

正如在keras documentation中所提到的，Keras在撰写本文时有两个后端Theano和Tensorflow。 Theano和Tensorflow数据/图像具有不同的维度排序。这个排序如下：

TensorFlow: [batch, width,height, channels]

Theano: [batch,channels, width, height]

如果您要使用的Tensorflow排序（如与OP的情况下），你要么必须：

1. 在您指定该keras.json配置文件（在Ubuntu中找到~/.keras/keras.json）。例如使用Theano，在keras.json配置文件运行时，你把下面几行：

   "image_dim_ordering": "th" 
   
   "backend": "theano" 
   

2. 指定要使用您的代码相关的后端，如：

   from keras import backend as K 
   K.set_image_dim_ordering('th') 
   

OP使用Tensorflow，因此他/她需要确保数据的格式为[batch, width, height, channels]，因此您必须将输入张量的定义更改为：

input_tensor = Input(shape=(150,150,3)) 

和模型为：

model = applications.VGG16(weights='imagenet', include_top=False, input_tensor=input_tensor) 

有OP一直使用Theano后端则输入张量将必须被定义为：

input_tensor = Input(shape=(3, 150, 150)) 

-Notice该信道是所述第一在这种情况下的论点。

和模型中定义的一样：

model = applications.VGG16(weights='imagenet', include_top=False, input_tensor=input_tensor) 

只是重申;我只是为了解他为什么/如何@ Simplicity的答案为他工作添加了一些清晰的内容。

我希望这可以帮助别人:)。

来源：

• https://github.com/fchollet/keras/issues/3850
• https://github.com/fchollet/keras/issues/5257
• https://keras.io/backend/