I have a caffe code in Python version. That python code has a data layer
like
name: "hidden_seed"
type: "NumpyData"
top: "hidden_seed"
I like to crate in c++ caffe as
layer{
name: "hidden_seed"
type: "Data"
top: "hidden_seed"
}
My query is how to create a data layer with size 300 x 250 with 0 value initialized.
I looked at data layers in caffe and available data layers are
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.
Which one is suitable for the Data layer what I like to have and how to initialize 0 value for each cell?
It seems like "DummyData"
layer will do the job for you:
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
}
}
The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.