如何在 caffe 中创建数据层？

Question

我有一个 Python 版本的 caffe 代码。 那个python代码有一个data layerlike

name: "hidden_seed"
type: "NumpyData"
top: "hidden_seed"

我喜欢在 c++ caffe 中装箱

layer{
    name: "hidden_seed"
    type: "Data"
    top: "hidden_seed"      
}

我的问题是如何创建一个大小为 300 x 250 且初始化为 0 值的数据层。

我查看了 caffe 中的数据层，可用的数据层是

Layers:

    Image Data - read raw images.
    Database - read data from LEVELDB or LMDB.
    HDF5 Input - read HDF5 data, allows data of arbitrary dimensions.
    HDF5 Output - write data as HDF5.
    Input - typically used for networks that are being deployed.
    Window Data - read window data file.
    Memory Data - read data directly from memory.
    Dummy Data - for static data and debugging.

哪一个适合我喜欢的Data层以及如何为每个单元格初始化0值？

Answer 1

似乎"DummyData" 层会为您完成这项工作：

layer {
  type: "DummyData"
  name: "hidden_seed"
  top: "hidden_seed"
  dummy_data_param {
    shape { dim: 300 dim: 250 }  # your desired data shape
    data_filler { type: "constant" value: 0 } # fill with all zeros
  }
}