【发布时间】:2019-02-21 15:44:09
【问题描述】:
这一层每边都有 4 个像素的填充,但在 tensorflow 中它只有“SAME”和“VALID”填充模式。如何在 tensorflow 中实现这一层?
layer {
name: "conv3"
type: "Deconvolution"
bottom: "conv26"
top: "conv3"
param {
lr_mult: 0.1
}
param {
lr_mult: 0.1
}
convolution_param {
num_output: 1
kernel_size: 9
stride: 3
pad: 4
weight_filler {
type: "gaussian"
std: 0.001
}
bias_filler {
type: "constant"
value: 0
}
}
}
【问题讨论】:
标签: tensorflow deep-learning caffe