Closed ghost closed 7 years ago
Hi,
Here, the deconv. layer is initialized to be a bilinear upsampler and works just like it.
As far as I know, 'reshape' lets us manipulate blob dimensions without increasing or reducing the amount of data. (e.g. 32x32x3 image blob => a vector with 3072 values) Therefore, it can't handle image or feature re-sizing.
Any corrections are welcome
@sanghoon Thanks,I forgot the "reshape" layer 's usuage. You are right!
good job!
layer { name: "upsample" type: "Deconvolution" bottom: "conv5_4" top: "upsample" param { lr_mult: 0 decay_mult: 0} convolution_param { num_output: 384 kernel_size: 4 pad: 1 stride: 2 group: 384 weight_filler: {type: "bilinear" } bias_term: false }
}
My question is why the layer's lr_mult is 0?
And If the lr_mult is 0, why not use "reshape" to get upsample.
thanks !