class SqueezeExcite(nn.Module):
""" Squeeze-and-Excitation w/ specific features for EfficientNet/MobileNet family
Args:
in_chs (int): input channels to layer
rd_ratio (float): ratio of squeeze reduction
act_layer (nn.Module): activation layer of containing block
gate_layer (Callable): attention gate function
force_act_layer (nn.Module): override block's activation fn if this is set/bound
rd_round_fn (Callable): specify a fn to calculate rounding of reduced chs
"""
def __init__(
self,
in_chs: int,
rd_ratio: float = 0.25,
rd_channels: Optional[int] = None,
act_layer: LayerType = nn.ReLU,
gate_layer: LayerType = nn.Sigmoid,
force_act_layer: Optional[LayerType] = None,
rd_round_fn: Optional[Callable] = None,
):
super(SqueezeExcite, self).__init__()
if rd_channels is None:
rd_round_fn = rd_round_fn or round
rd_channels = rd_round_fn(in_chs * rd_ratio)
act_layer = force_act_layer or act_layer
self.conv_reduce = nn.Conv2d(in_chs, rd_channels, 1, bias=True)
self.act1 = create_act_layer(act_layer, inplace=True)
self.conv_expand = nn.Conv2d(rd_channels, in_chs, 1, bias=True)
self.gate = create_act_layer(gate_layer)
def forward(self, x):
x_se = x.mean((2, 3), keepdim=True)
x_se = self.conv_reduce(x_se)
x_se = self.act1(x_se)
x_se = self.conv_expand(x_se)
return x * self.gate(x_se)
class iRMB(nn.Module):
def __init__(self, dim_in, dim_out, norm_in=True, has_skip=True, exp_ratio=1.0, norm_layer='bn_2d',
act_layer='relu', v_proj=True, dw_ks=3, stride=1, dilation=1, se_ratio=0.0, dim_head=64, window_size=7,
attn_s=True, qkv_bias=False, attn_drop=0., drop=0., drop_path=0., v_group=False, attn_pre=False):
super().__init__()
self.norm = get_norm(norm_layer)(dim_in) if norm_in else nn.Identity()
dim_mid = int(dim_in * exp_ratio)
self.has_skip = (dim_in == dim_out and stride == 1) and has_skip
self.attn_s = attn_s
if self.attn_s:
assert dim_in % dim_head == 0, 'dim should be divisible by num_heads'
self.dim_head = dim_head
self.window_size = window_size
self.num_head = dim_in // dim_head
self.scale = self.dim_head ** -0.5
self.attn_pre = attn_pre
self.qk = ConvNormAct(dim_in, int(dim_in * 2), kernel_size=1, bias=qkv_bias, norm_layer='none',
act_layer='none')
self.v = ConvNormAct(dim_in, dim_mid, kernel_size=1, groups=self.num_head if v_group else 1, bias=qkv_bias,
norm_layer='none', act_layer=act_layer, inplace=inplace)
self.attn_drop = nn.Dropout(attn_drop)
else:
if v_proj:
self.v = ConvNormAct(dim_in, dim_mid, kernel_size=1, bias=qkv_bias, norm_layer='none',
act_layer=act_layer, inplace=inplace)
else:
self.v = nn.Identity()
self.conv_local = ConvNormAct(dim_mid, dim_mid, kernel_size=dw_ks, stride=stride, dilation=dilation,
groups=dim_mid, norm_layer='bn_2d', act_layer='silu', inplace=inplace)
self.se = SE(dim_mid, rd_ratio=se_ratio, act_layer=get_act(act_layer)) if se_ratio > 0.0 else nn.Identity()
self.proj_drop = nn.Dropout(drop)
self.proj = ConvNormAct(dim_mid, dim_out, kernel_size=1, norm_layer='none', act_layer='none', inplace=inplace)
self.drop_path = DropPath(drop_path) if drop_path else nn.Identity()
def forward(self, x):
shortcut = x
x = self.norm(x)
B, C, H, W = x.shape
if self.attn_s:
# padding
if self.window_size <= 0:
window_size_W, window_size_H = W, H
else:
window_size_W, window_size_H = self.window_size, self.window_size
pad_l, pad_t = 0, 0
pad_r = (window_size_W - W % window_size_W) % window_size_W
pad_b = (window_size_H - H % window_size_H) % window_size_H
x = F.pad(x, (pad_l, pad_r, pad_t, pad_b, 0, 0,))
n1, n2 = (H + pad_b) // window_size_H, (W + pad_r) // window_size_W
x = rearrange(x, 'b c (h1 n1) (w1 n2) -> (b n1 n2) c h1 w1', n1=n1, n2=n2).contiguous()
# attention
b, c, h, w = x.shape
qk = self.qk(x)
qk = rearrange(qk, 'b (qk heads dim_head) h w -> qk b heads (h w) dim_head', qk=2, heads=self.num_head,
dim_head=self.dim_head).contiguous()
q, k = qk[0], qk[1]
attn_spa = (q @ k.transpose(-2, -1)) * self.scale
attn_spa = attn_spa.softmax(dim=-1)
attn_spa = self.attn_drop(attn_spa)
if self.attn_pre:
x = rearrange(x, 'b (heads dim_head) h w -> b heads (h w) dim_head', heads=self.num_head).contiguous()
x_spa = attn_spa @ x
x_spa = rearrange(x_spa, 'b heads (h w) dim_head -> b (heads dim_head) h w', heads=self.num_head, h=h,
w=w).contiguous()
x_spa = self.v(x_spa)
else:
v = self.v(x)
v = rearrange(v, 'b (heads dim_head) h w -> b heads (h w) dim_head', heads=self.num_head).contiguous()
x_spa = attn_spa @ v
x_spa = rearrange(x_spa, 'b heads (h w) dim_head -> b (heads dim_head) h w', heads=self.num_head, h=h,
w=w).contiguous()
# unpadding
x = rearrange(x_spa, '(b n1 n2) c h1 w1 -> b c (h1 n1) (w1 n2)', n1=n1, n2=n2).contiguous()
if pad_r > 0 or pad_b > 0:
x = x[:, :, :H, :W].contiguous()
else:
x = self.v(x)
x = x + self.se(self.conv_local(x)) if self.has_skip else self.se(self.conv_local(x))
x = self.proj_drop(x)
x = self.proj(x)
x = (shortcut + self.drop_path(x)) if self.has_skip else x
return x
这是SE模块和iRMB的代码，请你根据代码帮我绘制详细的结构图
最新发布
扫一扫
1004
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
