Keras TensorFlow importer: can't upload weights from .h5 file using importKerasNetwork.

Question

Ajpaezm 2019-2-7

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/443810-keras-tensorflow-importer-can-t-upload-weights-from-h5-file-using-importkerasnetwork

评论： Daniel Graham 2021-9-27

Hi, I have a .h5 file with a Keras TensorFlow model that was built using Sequential API. The model is carrying weights, and though Layers are being succesfully uploaded through importKerasNetwork() function, I can't seem to upload the weights with it.

What could I be doing wrong? Is there a way to debug this issue?

I tried this:

test_1=importKerasNetwork('myFile.h5')

And

test_2=importKerasNetwork('myFile.h5', 'WeightFile', 'myFile.h5')

No success whatsover.

Would it be recommendable to have the layers in an JSON file and the weights in a .h5 file?

Thanks in advance for all the help.

5 个评论
显示 3更早的评论隐藏 3更早的评论

darci taylor 2019-2-25

Don, I am having the same problem - I can't import my weights. If I use use importKerasNetwork, I get:

"Error using importKerasNetwork (line 93) Unable to import network because some network layers are not yet supported. To import layers and weights, call importKerasLayers with 'ImportWeights' set to true."

If I use "importKerasLayers(modelfile, 'ImportWeights', true)", I am able to see some of my layers, however there are a fair deal of layers that are "placeholder" layers, and I am not able to see the weghts at all. I get the message:

"Warning: Keras network takes vector inputs. Pass images with height=1 and channels=1. Warning: Loss function 'binary_crossentropy' is not yet supported. Warning: Unable to import some Keras layers, because they are not yet supported by the Deep Learning Toolbox. They have been replaced by placeholder layers. To find these layers, call the function findPlaceholderLayers on the returned object. "

Are the weights not importing because it's unable to identify the layers? (I have 12 layers, 8 of them have been returned as placeholders since Matlab doesn't suport 1dCNN , max, or average pooling...)

Don Mathis 2019-2-26

Darci, if you're using R2018b, you can download the latest version of the keras importer. There was an update in the last month or so. 'binary_crossentropy' is supported now. The placeholder layers should contain the weights, inside the KerasConfiguration field. Unfortunately, Conv1D is not yet supported by the importer.

José Luis Sandoval 2020-5-24

I have a similar problem:

>> detetor
Warning: File 'resnet50_pascal_cards_inference.h5' was saved in Keras version '2.3.1'. Import of Keras versions newer than
'2.2.4' is not yet supported. The imported model may not exactly match the model saved in the Keras file. 
Error using importKerasNetwork (line 94)
Unable to import network. Weight sharing is not yet supported.
Error in detetor (line 65)
net = importKerasNetwork(modelfile,'OutputLayerType','classification','ClassNames',classNames);

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Don Mathis 2019-2-8

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/443810-keras-tensorflow-importer-can-t-upload-weights-from-h5-file-using-importkerasnetwork#answer_360198

编辑：Don Mathis 2019-2-8

n.mat

It works for me when I use the latest R2018b update of the tensorflow-keras importer. What version of MATLAB are you using? And do you get an error message?

I get the attached network in MATLAB.

6 个评论
显示 4更早的评论隐藏 4更早的评论

Don Mathis 2019-2-8

importKerasNetwork returns the network. So you can look at it:

>> n = importKerasNetwork('OVO_LSTM_model-01.h5')
n =
  SeriesNetwork with properties:
    Layers: [10×1 nnet.cnn.layer.Layer]
    
>> n.Layers
ans = 
  10x1 Layer array with layers:
     1   'SequenceInputLayer'   Sequence Input      Sequence input with 26 dimensions
     2   'lstm_1'               LSTM                LSTM with 128 hidden units
     3   'dense_1'              Fully Connected     128 fully connected layer
     4   'dense_1_relu'         ReLU                ReLU
     5   'dense_2'              Fully Connected     128 fully connected layer
     6   'dense_2_relu'         ReLU                ReLU
     7   'dense_3'              Fully Connected     32 fully connected layer
     8   'dense_3_relu'         ReLU                ReLU
     9   'dense_4'              Fully Connected     4 fully connected layer
    10   'RegressionLayer'      Regression Output   mean-squared-error
>> n.Layers(5)
ans = 
  FullyConnectedLayer with properties:
          Name: 'dense_2'
   Hyperparameters
     InputSize: 128
    OutputSize: 128
   Learnable Parameters
       Weights: [128×128 single]
          Bias: [128×1 single]
  Show all properties