AttributeError:“节点"对象没有属性"output_masks" [英] AttributeError: 'Node' object has no attribute 'output_masks'

问题描述

我使用Keras预训练模型VGG16.问题在于，将tensorflow配置为使用GPU后，出现了使用CPU之前没有的错误.

I use Keras pretrained model VGG16. The problem is that after configuring tensorflow to use the GPU I get an error that I didn't have before when using the CPU.

错误如下:

    Traceback (most recent call last):
  File "/home/guillaume/Documents/Allianz/ConstatOrNotConstatv3/train_network.py",      line 109, in <module>
    model = LeNet.build(width=100, height=100, depth=3, classes=5)
  File "/home/guillaume/Documents/Allianz/ConstatOrNotConstatv3/lenet.py", line 39,    in build
    output = model(pretrainedOutput)
  File "/usr/local/lib/python3.6/dist-packages/keras/engine/base_layer.py", line 443, in __call__
    previous_mask = _collect_previous_mask(inputs)
  File "/usr/local/lib/python3.6/dist-packages/keras/engine/base_layer.py", line 1311, in _collect_previous_mask
mask = node.output_masks[tensor_index]
  AttributeError: 'Node' object has no attribute 'output_masks'

我在执行以下代码后得到了它:

I get it after executing this code :

    pretrained_model = VGG16(
        include_top=False,
        input_shape=(height, width, depth),
        weights='imagenet'
    )
    for layer in pretrained_model.layers:
        layer.trainable = False

    model = Sequential()
    # first (and only) set of FC => RELU layers
    model.add(Flatten())
    model.add(Dense(200, activation='relu'))
    model.add(Dropout(0.5))
    model.add(BatchNormalization())
    model.add(Dense(400, activation='relu'))
    model.add(Dropout(0.5))
    model.add(BatchNormalization())

    # softmax classifier
    model.add(Dense(classes,activation='softmax'))

    pretrainedInput = pretrained_model.input
    pretrainedOutput = pretrained_model.output
    output = model(pretrainedOutput)
    model = Model(pretrainedInput, output)

我有keras(2.2.2)和tensorflow(1.10.0rc1).我也尝试过keras 2.2.0和同样的错误.事实是，我使用的python环境可以在其他非预训练的NN上工作.

EDIT1 : I've got keras (2.2.2) and tensorflow(1.10.0rc1). I've also tried on keras 2.2.0 and same error. The thing is that the python environment I use works on others non-pretrained NN.

我可以连接两个自制模型.只有受过训练的人才有问题，而不仅仅是VGG16.

EDIT2 : I'm able to connect two homemade models. It's only whith the pretrained ones there is a problem and not only VGG16.

推荐答案

您可能会从tensorflow.keras导入tf.keras.layers或tf.keras.applications或其他keras模块，并将这些对象与基于版本等不兼容的纯" keras软件包.我建议您查看是否可以从纯" keras模块导入并运行所有内容；调试时不要使用tf.keras，因为它们不一定兼容.我遇到了同样的问题，并且此解决方案对我有用.

You're likely importing tf.keras.layers or tf.keras.applications or other keras modules from tensorflow.keras, and mixing these objects with objects from the "pure" keras package, which is not compatible, based upon version, etc. I recommend seeing if you can import and run everything from the "pure" keras modules; don't use tf.keras while debugging, as they're not necessarily compatible. I had the same problem, and this solution is working for me.

这篇关于AttributeError:“节点"对象没有属性"output_masks"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！