使用 Rstudio Keras 的暹罗网络

我正在尝试使用 Rstudio Keras 包实现暹罗网络。我尝试实现的网络与您可以在中看到的网络相同这个帖子 https://sorenbouma.github.io/blog/oneshot/.

因此，基本上，我将代码移植到 R 并使用 Rstudio Keras 实现。到目前为止我的代码如下所示：

    library(keras)

    inputShape <- c(105, 105, 1)
    leftInput <- layer_input(inputShape)
    rightInput <- layer_input(inputShape)

    model<- keras_model_sequential()

    model %>%
      layer_conv_2d(filter=64,
                    kernel_size=c(10,10),
                    activation = "relu",
                    input_shape=inputShape,
                    kernel_initializer = initializer_random_normal(0, 1e-2),
                    kernel_regularizer = regularizer_l2(2e-4)) %>%
      layer_max_pooling_2d() %>%

      layer_conv_2d(filter=128,
                    kernel_size=c(7,7),
                    activation = "relu",
                    kernel_initializer = initializer_random_normal(0, 1e-2),
                    kernel_regularizer = regularizer_l2(2e-4),
                    bias_initializer = initializer_random_normal(0.5, 1e-2)) %>%
      layer_max_pooling_2d() %>%

      layer_conv_2d(filter=128,
                    kernel_size=c(4,4),
                    activation = "relu",
                    kernel_initializer = initializer_random_normal(0, 1e-2),
                    kernel_regularizer = regularizer_l2(2e-4),
                    bias_initializer = initializer_random_normal(0.5, 1e-2)) %>%
      layer_max_pooling_2d() %>%

      layer_conv_2d(filter=256,
                    kernel_size=c(4,4),
                    activation = "relu",
                    kernel_initializer = initializer_random_normal(0, 1e-2),
                    kernel_regularizer = regularizer_l2(2e-4),
                    bias_initializer = initializer_random_normal(0.5, 1e-2)) %>%

      layer_flatten() %>%
      layer_dense(4096, 
                  activation = "sigmoid",
                  kernel_initializer = initializer_random_normal(0, 1e-2),
                  kernel_regularizer = regularizer_l2(1e-3),
                  bias_initializer = initializer_random_normal(0.5, 1e-2)) 

    encoded_left <- leftInput %>% model
    encoded_right <- rightInput %>% model

但是，当运行最后两行时，出现以下错误：

Error in py_call_impl(callable, dots$args, dots$keywords) : 
  AttributeError: 'Model' object has no attribute '_losses'

Detailed traceback: 
  File "/home/rstudio/.virtualenvs/r-tensorflow/lib/python2.7/site-packages/tensorflow/contrib/keras/python/keras/engine/topology.py", line 432, in __call__
    output = super(Layer, self).__call__(inputs, **kwargs)
  File "/home/rstudio/.virtualenvs/r-tensorflow/lib/python2.7/site-packages/tensorflow/python/layers/base.py", line 441, in __call__
    outputs = self.call(inputs, *args, **kwargs)
  File "/home/rstudio/.virtualenvs/r-tensorflow/lib/python2.7/site-packages/tensorflow/contrib/keras/python/keras/models.py", line 560, in call
    return self.model.call(inputs, mask)
  File "/home/rstudio/.virtualenvs/r-tensorflow/lib/python2.7/site-packages/tensorflow/contrib/keras/python/keras/engine/topology.py", line 1743, in call
    output_tensors, _, _ = self.run_internal_graph(inputs, masks)
  File "/home/rstudio/.virtualenvs/r-tensorflow/lib/python2.7/site-packages/tensorflow/contrib/keras/python

我一直在 StackOverflow 上寻找类似的实现和问题，但找不到解决方案。我想我可能会遗漏一些非常明显的东西。

有什么想法如何解决这个问题吗？

正如 Daniel Falbel 在评论中指出的那样，解决方案是更新 R-keras 软件包，然后更新 tensorflow 安装。

然而，R 中的tensorflow包没有安装最新的1.3版本的tensorflow（它正在重新安装1.2版本）。

要解决此问题，可以将正确版本的 URL 提供给 install_tensorflow 函数。可以找到不同实现的 URLhere https://pypi.python.org/pypi/tensorflow。在本例中我使用的是 Linux。运行此命令应该可以解决遇到相同问题的任何人的问题：

library(tensorflow)
install_tensorflow(package_url = "https://pypi.python.org/packages/b8/d6/af3d52dd52150ec4a6ceb7788bfeb2f62ecb6aa2d1172211c4db39b349a2/tensorflow-1.3.0rc0-cp27-cp27mu-manylinux1_x86_64.whl#md5=1cf77a2360ae2e38dd3578618eacc03b")