Resnet block from `ni` to `nh` with `stride`
ResBlock(
expansion,
ni,
nf,
stride = 1,
groups = 1,
reduction = NULL,
nh1 = NULL,
nh2 = NULL,
dw = FALSE,
g2 = 1,
sa = FALSE,
sym = FALSE,
norm_type = 1,
act_cls = nn$ReLU,
ndim = 2,
ks = 3,
pool = AvgPool(),
pool_first = TRUE,
padding = NULL,
bias = NULL,
bn_1st = TRUE,
transpose = FALSE,
init = "auto",
xtra = NULL,
bias_std = 0.01,
dilation = 1,
padding_mode = "zeros"
)
decoder
number of linear inputs
number of features
stride number
groups number
reduction
out channels 1
out channels 2
dw paramer
g2 block
sa parameter
symmetric
normalization type
activation
dimension number
kernel size
pooling type, Average, Max
pooling first
padding
bias
batch normalization 1st
transpose
initializer
xtra
bias standard deviation
dilation number
padding mode
Block object