我在执行以下.prototxt时遇到错误，我完全不知道为什么会出现这个错误：

layer {    name: "conv"    type: "Convolution"    bottom: "image"    top: "conv"    convolution_param {        num_output: 2        kernel_size: 5        pad: 2        stride: 1        weight_filler {            type: "xavier"        }        bias_filler {            type: "constant"            value: 0        }    }}

这是错误输出。我在最新的caffe-master-branch中看到，应该可以使用5D-Blobs。

I1202 14:54:58.617269  2393 hdf5_data_layer.cpp:93] Number of HDF5 files: 9I1202 14:54:58.631134  2393 hdf5.cpp:35] Datatype class: H5T_INTEGERI1202 14:54:59.159739  2393 net.cpp:150] Setting up train-dataI1202 14:54:59.159760  2393 net.cpp:157] Top shape: 1 1 1 128 128 (16384)I1202 14:54:59.159765  2393 net.cpp:157] Top shape: 1 1 8 128 128 (131072)I1202 14:54:59.159766  2393 net.cpp:165] Memory required for data: 589824I1202 14:54:59.159773  2393 layer_factory.hpp:77] Creating layer down_level_0_convI1202 14:54:59.159790  2393 net.cpp:100] Creating Layer down_level_0_convI1202 14:54:59.159795  2393 net.cpp:434] down_level_0_conv <- imageI1202 14:54:59.159804  2393 net.cpp:408] down_level_0_conv -> down_level_0_convF1202 14:54:59.159915  2393 blob.hpp:140] Check failed: num_axes() <= 4 (5 vs. 4) Cannot use legacy accessors on Blobs with > 4 axes.

我需要切换到某个分支吗？我再次从caffe-master-branch拉取以确保是最新版本。然后我执行了make clean make all命令，但仍然不起作用。

回答：

据我所知，这个错误来自"Xavier"填充器：这个填充器计算输入和输出通道之间的比率。如果你用不同的填充器替换它，你应该可以使用ND blob。