在测试阶段计算数据块的平均值
Compute the mean of a data blob during testing phase
我正在使用具有数据和标签的 hdf5 层。
layer {
name: "data"
type: "HDF5Data"
top: "data"
top: "label"
include {
phase: TEST
}
hdf5_data_param {
source: "./list.txt"
batch_size: 8
shuffle: true
}
}
在测试阶段,它将从测试集中加载 8 张图像并提供给网络。我想在测试阶段打印每张图像的平均值。可以在CAFFE中使用吗?我应该使用哪一层?
我认为您正在寻找 "Reduction"
图层
layer {
type: "Reduction"
name: "img_mean"
bottom: "data"
top: "img_mean"
reduction_param {
operation: MEAN
axis: 0 # to reduce the entire batch, or axis: 1 for per-image mean
}
}
我正在使用具有数据和标签的 hdf5 层。
layer {
name: "data"
type: "HDF5Data"
top: "data"
top: "label"
include {
phase: TEST
}
hdf5_data_param {
source: "./list.txt"
batch_size: 8
shuffle: true
}
}
在测试阶段,它将从测试集中加载 8 张图像并提供给网络。我想在测试阶段打印每张图像的平均值。可以在CAFFE中使用吗?我应该使用哪一层?
我认为您正在寻找 "Reduction"
图层
layer {
type: "Reduction"
name: "img_mean"
bottom: "data"
top: "img_mean"
reduction_param {
operation: MEAN
axis: 0 # to reduce the entire batch, or axis: 1 for per-image mean
}
}