我在Python版本中有一个caffe代码。
那个python代码有data layer
之类的
name: "hidden_seed"
type: "NumpyData"
top: "hidden_seed"
我喜欢用c ++ caffe作为
layer{
name: "hidden_seed"
type: "Data"
top: "hidden_seed"
}
我的查询是如何创建一个大小为300 x 250且初始化为0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数据层以及如何为每个单元格初始化0值?
答案 0 :(得分:2)
似乎"DummyData"
图层将为您完成这项工作:
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
}
}