Question

我一直试图让一些开源代码运行，但可以摆脱这一个错误。

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)

最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'

但是两者合并而且X都是tensorflow.python.framework.ops.Tensor类型，如果我换出合并为输入，而子换成X，则没有这样的错误。

为什么语句不接受Tensor对象的合并版本？

Answer 1

创建模型时无需合并输入。

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)

点击the Keras Model document

查看详情

keras merge AttributeError：'Merge'对象没有属性'is_placeholder'

1 个答案: