1

我一直试图让一些开源代码运行，但可以摆脱这个错误。

mnist = input_data.read_data_sets('../../MNIST_data', one_hot=True)
X_train = mnist.train.images
y_train = mnist.train.labels

X = Input(batch_shape=(m, n_x))
cond = Input(batch_shape=(m, n_y))
merged = merge([X, cond], mode='concat', concat_axis=1)
inputs = merged  # I tried sub X instead of merged, then it works

...................
# middle layer code derives outputs, which is irrelevant to this error

vae = Model(inputs, outputs)

重要的是最后一行抱怨没有属性。

  File "cvae_keras.py", line 74, in <module>
    vae = Model(inputs, outputs)
  File "/Users/bruceho/anaconda/lib/python2.7/site-packages/keras/legacy/interfaces.py", line 88, in wrapper
    return func(*args, **kwargs)
  File "/Users/bruceho/anaconda/lib/python2.7/site-packages/keras/engine/topology.py", line 1566, in __init__
    if layer.is_placeholder:
AttributeError: 'Merge' object has no attribute 'is_placeholder'

但是合并和 X 都是 tensorflow.python.framework.ops.Tensor 类型，如果我将合并作为输入换出，并与 X 交换，则不会出现此类错误。

为什么语句不接受 Tensor 对象的合并版本？

4

1 回答 1

3

创建模型时不需要合并输入。

mnist = input_data.read_data_sets('../../MNIST_data', one_hot=True)
X_train = mnist.train.images
y_train = mnist.train.labels

X = Input(batch_shape=(m, n_x))
cond = Input(batch_shape=(m, n_y))

...................
# do whatever you want to create outputs from X and cond

vae = Model(inputs = [X, cond], outputs=outputs)

在Keras 模型文档中查看更多信息

于 2017-06-29T06:05:26.637 回答