Question

我有一个使用Keras的Python代码。我没有发布代码，因为它有点长，问题似乎与代码本身无关。

这是我遇到的错误：

File "h5py\h5a.pyx", line 77, in h5py.h5a.open (D:\Build\h5py\h5py-2.7.0\h5py\h5a.c:2350)
KeyError: "Can't open attribute (Can't locate attribute: 'nb_layers')"

可能是什么问题？它与Keras有关吗？我该如何解决这个问题？

编辑1

错误似乎与这部分代码有关：

# load VGG16 weights
    f = h5py.File(weights_path)

    for k in range(f.attrs['nb_layers']):
        if k >= len(model.layers):
            break
        g = f['layer_{}'.format(k)]
        weights = [g['param_{}'.format(p)] for p in range(g.attrs['nb_params'])]
        model.layers[k].set_weights(weights)

    f.close()
    print('Model loaded.')

感谢。

Answer 1

使用https://github.com/fchollet/deep-learning-models/releases

中的权重文件vgg16_weights_th_dim_ordering_th_kernels.h5

此文件采用Keras 2格式。

Answer 2

显然，“ nb_layers”是指层数，因此您可以使用替代方法。在这种情况下：

f = h5py.File(filename, 'r')
nb_layers = len(f.attrs["layer_names"])

Answer 3

我有同样的问题。我通过添加此行来在需要的地方构建vgg16网络来解决它。

 Vmodel = applications.VGG16(weights='imagenet', include_top=False, input_shape=(3, img_width, img_height))
    print('Model loaded.')

    # build a classifier model to put on top of the convolutional model
    top_model = Sequential()
    top_model.add(Flatten(input_shape=Vmodel.output_shape[1:]))
    top_model.add(Dense(256, activation='relu'))
    top_model.add(Dropout(0.5))
    top_model.add(Dense(1, activation='sigmoid'))

    # note that it is necessary to start with a fully-trained
    # classifier, including the top classifier,
    # in order to successfully do fine-tuning
    top_model.load_weights(top_model_weights_path)

    # add the model on top of the convolutional base
    # model.add(top_model)
    model = Model(inputs=Vmodel.input, outputs=top_model(Vmodel.output))

因此，基本上不必创建自己的vgg16转换网并将vgg16权重加载到其中。我创建了vgg16模型，然后将最后一层添加到模型中。我希望这对您有用。

KeyError：＆＃34;无法打开属性（无法找到属性：＆＃39; nb_layers＆＃39;）＆＃34;

3 个答案: