|
- import torch
- import torch.nn as nn
- import torch.nn.functional as F
- from functools import partial
-
- from timm.models.layers import DropPath, to_2tuple, trunc_normal_
- from timm.models.registry import register_model
- from timm.models.vision_transformer import _cfg
- from timm.models.registry import register_model
-
- import math#数学库
-
-
- class Mlp(nn.Module):
- def __init__(self, in_features, hidden_features=None, out_features=None, act_layer=nn.GELU, drop=0.):
- super().__init__()
- out_features = out_features or in_features
- hidden_features = hidden_features or in_features
- self.fc1 = nn.Linear(in_features, hidden_features)
- self.dwconv = DWConv(hidden_features)
- self.act = act_layer()
- self.fc2 = nn.Linear(hidden_features, out_features)
- self.drop = nn.Dropout(drop)
-
- self.apply(self._init_weights)
-
- def _init_weights(self, m):
- if isinstance(m, nn.Linear):
- trunc_normal_(m.weight, std=.02)
- if isinstance(m, nn.Linear) and m.bias is not None:
- nn.init.constant_(m.bias, 0)
- elif isinstance(m, nn.LayerNorm):
- nn.init.constant_(m.bias, 0)
- nn.init.constant_(m.weight, 1.0)
- elif isinstance(m, nn.Conv2d):
- fan_out = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
- fan_out //= m.groups
- m.weight.data.normal_(0, math.sqrt(2.0 / fan_out))
- if m.bias is not None:
- m.bias.data.zero_()
-
- def forward(self, x, H, W):
- x = self.fc1(x)
- x = self.dwconv(x, H, W)
- x = self.act(x)
- x = self.drop(x)
- x = self.fc2(x)
- x = self.drop(x)
- return x
-
-
- class Attention(nn.Module):
- def __init__(self, dim, num_heads=8, qkv_bias=False, qk_scale=None, attn_drop=0., proj_drop=0., sr_ratio=1):
- super().__init__()
- assert dim % num_heads == 0, f"dim {dim} should be divided by num_heads {num_heads}."
-
- self.dim = dim
- self.num_heads = num_heads
- head_dim = dim // num_heads
- self.scale = qk_scale or head_dim ** -0.5
-
- self.q = nn.Linear(dim, dim, bias=qkv_bias)
- self.kv = nn.Linear(dim, dim * 2, bias=qkv_bias)
- self.attn_drop = nn.Dropout(attn_drop)
- self.proj = nn.Linear(dim, dim)
- self.proj_drop = nn.Dropout(proj_drop)
-
- self.sr_ratio = sr_ratio
- if sr_ratio > 1:
- self.sr = nn.Conv2d(dim, dim, kernel_size=sr_ratio, stride=sr_ratio)
- self.norm = nn.LayerNorm(dim)
-
- self.apply(self._init_weights)
-
- def _init_weights(self, m):
- if isinstance(m, nn.Linear):
- trunc_normal_(m.weight, std=.02)
- if isinstance(m, nn.Linear) and m.bias is not None:
- nn.init.constant_(m.bias, 0)
- elif isinstance(m, nn.LayerNorm):
- nn.init.constant_(m.bias, 0)
- nn.init.constant_(m.weight, 1.0)
- elif isinstance(m, nn.Conv2d):
- fan_out = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
- fan_out //= m.groups
- m.weight.data.normal_(0, math.sqrt(2.0 / fan_out))
- if m.bias is not None:
- m.bias.data.zero_()
-
- def forward(self, x, H, W):
- B, N, C = x.shape
- q = self.q(x).reshape(B, N, self.num_heads, C // self.num_heads).permute(0, 2, 1, 3)
-
- if self.sr_ratio > 1:
- x_ = x.permute(0, 2, 1).reshape(B, C, H, W)
- x_ = self.sr(x_).reshape(B, C, -1).permute(0, 2, 1)
- x_ = self.norm(x_)
- kv = self.kv(x_).reshape(B, -1, 2, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)
- else:
- kv = self.kv(x).reshape(B, -1, 2, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)
- k, v = kv[0], kv[1]
-
- attn = (q @ k.transpose(-2, -1)) * self.scale
- attn = attn.softmax(dim=-1)
- attn = self.attn_drop(attn)
-
- x = (attn @ v).transpose(1, 2).reshape(B, N, C)
- x = self.proj(x)
- x = self.proj_drop(x)
-
- return x
-
-
- class Block(nn.Module):
-
- def __init__(self, dim, num_heads, mlp_ratio=4., qkv_bias=False, qk_scale=None, drop=0., attn_drop=0.,
- drop_path=0., act_layer=nn.GELU, norm_layer=nn.LayerNorm, sr_ratio=1):
- super().__init__()
- self.norm1 = norm_layer(dim)
- self.attn = Attention(
- dim,
- num_heads=num_heads, qkv_bias=qkv_bias, qk_scale=qk_scale,
- attn_drop=attn_drop, proj_drop=drop, sr_ratio=sr_ratio)
- # NOTE: drop path for stochastic depth, we shall see if this is better than dropout here
- self.drop_path = DropPath(drop_path) if drop_path > 0. else nn.Identity()
- self.norm2 = norm_layer(dim)
- mlp_hidden_dim = int(dim * mlp_ratio)
- self.mlp = Mlp(in_features=dim, hidden_features=mlp_hidden_dim, act_layer=act_layer, drop=drop)
-
- self.apply(self._init_weights)
-
- def _init_weights(self, m):
- if isinstance(m, nn.Linear):
- trunc_normal_(m.weight, std=.02)
- if isinstance(m, nn.Linear) and m.bias is not None:
- nn.init.constant_(m.bias, 0)
- elif isinstance(m, nn.LayerNorm):
- nn.init.constant_(m.bias, 0)
- nn.init.constant_(m.weight, 1.0)
- elif isinstance(m, nn.Conv2d):
- fan_out = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
- fan_out //= m.groups
- m.weight.data.normal_(0, math.sqrt(2.0 / fan_out))
- if m.bias is not None:
- m.bias.data.zero_()
-
- def forward(self, x, H, W):
- x = x + self.drop_path(self.attn(self.norm1(x), H, W))
- x = x + self.drop_path(self.mlp(self.norm2(x), H, W))
-
- return x
-
-
- class OverlapPatchEmbed(nn.Module):
- """ Image to Patch Embedding
- """
-
- def __init__(self, img_size=224, patch_size=7, stride=4, in_chans=3, embed_dim=768):
- super().__init__()
- img_size = to_2tuple(img_size)
- patch_size = to_2tuple(patch_size)
-
- self.img_size = img_size
- self.patch_size = patch_size
- self.H, self.W = img_size[0] // patch_size[0], img_size[1] // patch_size[1]
- self.num_patches = self.H * self.W
- self.proj = nn.Conv2d(in_chans, embed_dim, kernel_size=patch_size, stride=stride,
- padding=(patch_size[0] // 2, patch_size[1] // 2))
- self.norm = nn.LayerNorm(embed_dim)
-
- self.apply(self._init_weights)
-
- def _init_weights(self, m):
- if isinstance(m, nn.Linear):
- trunc_normal_(m.weight, std=.02)
- if isinstance(m, nn.Linear) and m.bias is not None:
- nn.init.constant_(m.bias, 0)
- elif isinstance(m, nn.LayerNorm):
- nn.init.constant_(m.bias, 0)
- nn.init.constant_(m.weight, 1.0)
- elif isinstance(m, nn.Conv2d):
- fan_out = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
- fan_out //= m.groups
- m.weight.data.normal_(0, math.sqrt(2.0 / fan_out))
- if m.bias is not None:
- m.bias.data.zero_()
-
- def forward(self, x):
- x = self.proj(x)
- _, _, H, W = x.shape
- x = x.flatten(2).transpose(1, 2)
- x = self.norm(x)
-
- return x, H, W
-
-
- class PyramidVisionTransformerImpr(nn.Module):
- def __init__(self, img_size=224, patch_size=16, in_chans=3, num_classes=1000, embed_dims=[64, 128, 256, 512],
- num_heads=[1, 2, 4, 8], mlp_ratios=[4, 4, 4, 4], qkv_bias=False, qk_scale=None, drop_rate=0.,
- attn_drop_rate=0., drop_path_rate=0., norm_layer=nn.LayerNorm,
- depths=[3, 4, 6, 3], sr_ratios=[8, 4, 2, 1]):
- super().__init__()
- self.num_classes = num_classes
- self.depths = depths
-
- # patch_embed
- self.patch_embed1 = OverlapPatchEmbed(img_size=img_size, patch_size=7, stride=4, in_chans=in_chans,
- embed_dim=embed_dims[0])
- self.patch_embed2 = OverlapPatchEmbed(img_size=img_size // 4, patch_size=3, stride=2, in_chans=embed_dims[0],
- embed_dim=embed_dims[1])
- self.patch_embed3 = OverlapPatchEmbed(img_size=img_size // 8, patch_size=3, stride=2, in_chans=embed_dims[1],
- embed_dim=embed_dims[2])
- self.patch_embed4 = OverlapPatchEmbed(img_size=img_size // 16, patch_size=3, stride=2, in_chans=embed_dims[2],
- embed_dim=embed_dims[3])
-
- # transformer encoder
- dpr = [x.item() for x in torch.linspace(0, drop_path_rate, sum(depths))] # stochastic depth decay rule
- cur = 0
- self.block1 = nn.ModuleList([Block(
- dim=embed_dims[0], num_heads=num_heads[0], mlp_ratio=mlp_ratios[0], qkv_bias=qkv_bias, qk_scale=qk_scale,
- drop=drop_rate, attn_drop=attn_drop_rate, drop_path=dpr[cur + i], norm_layer=norm_layer,
- sr_ratio=sr_ratios[0])
- for i in range(depths[0])])
- self.norm1 = norm_layer(embed_dims[0])
-
- cur += depths[0]
- self.block2 = nn.ModuleList([Block(
- dim=embed_dims[1], num_heads=num_heads[1], mlp_ratio=mlp_ratios[1], qkv_bias=qkv_bias, qk_scale=qk_scale,
- drop=drop_rate, attn_drop=attn_drop_rate, drop_path=dpr[cur + i], norm_layer=norm_layer,
- sr_ratio=sr_ratios[1])
- for i in range(depths[1])])
- self.norm2 = norm_layer(embed_dims[1])
-
- cur += depths[1]
- self.block3 = nn.ModuleList([Block(
- dim=embed_dims[2], num_heads=num_heads[2], mlp_ratio=mlp_ratios[2], qkv_bias=qkv_bias, qk_scale=qk_scale,
- drop=drop_rate, attn_drop=attn_drop_rate, drop_path=dpr[cur + i], norm_layer=norm_layer,
- sr_ratio=sr_ratios[2])
- for i in range(depths[2])])
- self.norm3 = norm_layer(embed_dims[2])
-
- cur += depths[2]
- self.block4 = nn.ModuleList([Block(
- dim=embed_dims[3], num_heads=num_heads[3], mlp_ratio=mlp_ratios[3], qkv_bias=qkv_bias, qk_scale=qk_scale,
- drop=drop_rate, attn_drop=attn_drop_rate, drop_path=dpr[cur + i], norm_layer=norm_layer,
- sr_ratio=sr_ratios[3])
- for i in range(depths[3])])
- self.norm4 = norm_layer(embed_dims[3])
-
- # classification head
- # self.head = nn.Linear(embed_dims[3], num_classes) if num_classes > 0 else nn.Identity()
-
- self.apply(self._init_weights)
-
- def _init_weights(self, m):
- if isinstance(m, nn.Linear):
- trunc_normal_(m.weight, std=.02)
- if isinstance(m, nn.Linear) and m.bias is not None:
- nn.init.constant_(m.bias, 0)
- elif isinstance(m, nn.LayerNorm):
- nn.init.constant_(m.bias, 0)
- nn.init.constant_(m.weight, 1.0)
- elif isinstance(m, nn.Conv2d):
- fan_out = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
- fan_out //= m.groups
- m.weight.data.normal_(0, math.sqrt(2.0 / fan_out))
- if m.bias is not None:
- m.bias.data.zero_()
-
- def init_weights(self, pretrained=None):
- if isinstance(pretrained, str):
- logger = 1
- #load_checkpoint(self, pretrained, map_location='cpu', strict=False, logger=logger)
-
- def reset_drop_path(self, drop_path_rate):
- dpr = [x.item() for x in torch.linspace(0, drop_path_rate, sum(self.depths))]
- cur = 0
- for i in range(self.depths[0]):
- self.block1[i].drop_path.drop_prob = dpr[cur + i]
-
- cur += self.depths[0]
- for i in range(self.depths[1]):
- self.block2[i].drop_path.drop_prob = dpr[cur + i]
-
- cur += self.depths[1]
- for i in range(self.depths[2]):
- self.block3[i].drop_path.drop_prob = dpr[cur + i]
-
- cur += self.depths[2]
- for i in range(self.depths[3]):
- self.block4[i].drop_path.drop_prob = dpr[cur + i]
-
- def freeze_patch_emb(self):
- self.patch_embed1.requires_grad = False
-
- @torch.jit.ignore
- def no_weight_decay(self):
- return {'pos_embed1', 'pos_embed2', 'pos_embed3', 'pos_embed4', 'cls_token'} # has pos_embed may be better
-
- def get_classifier(self):
- return self.head
-
- def reset_classifier(self, num_classes, global_pool=''):
- self.num_classes = num_classes
- self.head = nn.Linear(self.embed_dim, num_classes) if num_classes > 0 else nn.Identity()
-
- # def _get_pos_embed(self, pos_embed, patch_embed, H, W):
- # if H * W == self.patch_embed1.num_patches:
- # return pos_embed
- # else:
- # return F.interpolate(
- # pos_embed.reshape(1, patch_embed.H, patch_embed.W, -1).permute(0, 3, 1, 2),
- # size=(H, W), mode="bilinear").reshape(1, -1, H * W).permute(0, 2, 1)
-
- def forward_features(self, x):
- B = x.shape[0]
- outs = []
-
- # stage 1
- x, H, W = self.patch_embed1(x)
- for i, blk in enumerate(self.block1):
- x = blk(x, H, W)
- x = self.norm1(x)
- x = x.reshape(B, H, W, -1).permute(0, 3, 1, 2).contiguous()
- outs.append(x)
-
- # stage 2
- x, H, W = self.patch_embed2(x)
- for i, blk in enumerate(self.block2):
- x = blk(x, H, W)
- x = self.norm2(x)
- x = x.reshape(B, H, W, -1).permute(0, 3, 1, 2).contiguous()
- outs.append(x)
-
- # stage 3
- x, H, W = self.patch_embed3(x)
- for i, blk in enumerate(self.block3):
- x = blk(x, H, W)
- x = self.norm3(x)
- x = x.reshape(B, H, W, -1).permute(0, 3, 1, 2).contiguous()
- outs.append(x)
-
- # stage 4
- x, H, W = self.patch_embed4(x)
- for i, blk in enumerate(self.block4):
- x = blk(x, H, W)
- x = self.norm4(x)
- x = x.reshape(B, H, W, -1).permute(0, 3, 1, 2).contiguous()
- outs.append(x)
-
- return outs
-
- # return x.mean(dim=1)
-
- def forward(self, x):
- x = self.forward_features(x)
- # x = self.head(x)
-
- return x
-
-
- class DWConv(nn.Module):
- def __init__(self, dim=768):
- super(DWConv, self).__init__()
- self.dwconv = nn.Conv2d(dim, dim, 3, 1, 1, bias=True, groups=dim)
-
- def forward(self, x, H, W):
- B, N, C = x.shape
- x = x.transpose(1, 2).view(B, C, H, W)
- x = self.dwconv(x)
- x = x.flatten(2).transpose(1, 2)
-
- return x
-
-
- def _conv_filter(state_dict, patch_size=16):
- """ convert patch embedding weight from manual patchify + linear proj to conv"""
- out_dict = {}
- for k, v in state_dict.items():
- if 'patch_embed.proj.weight' in k:
- v = v.reshape((v.shape[0], 3, patch_size, patch_size))
- out_dict[k] = v
-
- return out_dict
-
-
- @register_model
- class pvt_v2_b0(PyramidVisionTransformerImpr):
- def __init__(self, **kwargs):
- super(pvt_v2_b0, self).__init__(
- patch_size=4, embed_dims=[32, 64, 160, 256], num_heads=[1, 2, 5, 8], mlp_ratios=[8, 8, 4, 4],
- qkv_bias=True, norm_layer=partial(nn.LayerNorm, eps=1e-6), depths=[2, 2, 2, 2], sr_ratios=[8, 4, 2, 1],
- drop_rate=0.0, drop_path_rate=0.1)
-
-
-
- @register_model
- class pvt_v2_b1(PyramidVisionTransformerImpr):
- def __init__(self, **kwargs):
- super(pvt_v2_b1, self).__init__(
- patch_size=4, embed_dims=[64, 128, 320, 512], num_heads=[1, 2, 5, 8], mlp_ratios=[8, 8, 4, 4],
- qkv_bias=True, norm_layer=partial(nn.LayerNorm, eps=1e-6), depths=[2, 2, 2, 2], sr_ratios=[8, 4, 2, 1],
- drop_rate=0.0, drop_path_rate=0.1)
-
- @register_model
- class pvt_v2_b2(PyramidVisionTransformerImpr):
- def __init__(self, **kwargs):
- super(pvt_v2_b2, self).__init__(
- patch_size=4, embed_dims=[64, 128, 320, 512], num_heads=[1, 2, 5, 8], mlp_ratios=[8, 8, 4, 4],
- qkv_bias=True, norm_layer=partial(nn.LayerNorm, eps=1e-6), depths=[3, 4, 6, 3], sr_ratios=[8, 4, 2, 1],
- drop_rate=0.0, drop_path_rate=0.1)
-
- @register_model
- class pvt_v2_b3(PyramidVisionTransformerImpr):
- def __init__(self, **kwargs):
- super(pvt_v2_b3, self).__init__(
- patch_size=4, embed_dims=[64, 128, 320, 512], num_heads=[1, 2, 5, 8], mlp_ratios=[8, 8, 4, 4],
- qkv_bias=True, norm_layer=partial(nn.LayerNorm, eps=1e-6), depths=[3, 4, 18, 3], sr_ratios=[8, 4, 2, 1],
- drop_rate=0.0, drop_path_rate=0.1)
-
- @register_model
- class pvt_v2_b4(PyramidVisionTransformerImpr):
- def __init__(self, **kwargs):
- super(pvt_v2_b4, self).__init__(
- patch_size=4, embed_dims=[64, 128, 320, 512], num_heads=[1, 2, 5, 8], mlp_ratios=[8, 8, 4, 4],
- qkv_bias=True, norm_layer=partial(nn.LayerNorm, eps=1e-6), depths=[3, 8, 27, 3], sr_ratios=[8, 4, 2, 1],
- drop_rate=0.0, drop_path_rate=0.1)
-
-
- @register_model
- class pvt_v2_b5(PyramidVisionTransformerImpr):
- def __init__(self, **kwargs):
- super(pvt_v2_b5, self).__init__(
- patch_size=4, embed_dims=[64, 128, 320, 512], num_heads=[1, 2, 5, 8], mlp_ratios=[4, 4, 4, 4],
- qkv_bias=True, norm_layer=partial(nn.LayerNorm, eps=1e-6), depths=[3, 6, 40, 3], sr_ratios=[8, 4, 2, 1],
- drop_rate=0.0, drop_path_rate=0.1)
-
- import torch
- import torch.nn as nn
- import torch.nn.functional as F
- import os
- import torch
- import torch.nn as nn
- import torch.nn.functional as F
-
-
- class BasicConv2d(nn.Module):
- def __init__(self, in_planes, out_planes, kernel_size, stride=1, padding=0, dilation=1):
- super(BasicConv2d, self).__init__()
-
- self.conv = nn.Conv2d(in_planes, out_planes,
- kernel_size=kernel_size, stride=stride,
- padding=padding, dilation=dilation, bias=False)
- self.bn = nn.BatchNorm2d(out_planes)
- self.relu = nn.ReLU(inplace=True)
-
- def forward(self, x):
- x = self.conv(x)
- x = self.bn(x)
- return x
-
-
- class CFM(nn.Module):
- def __init__(self, channel):
- super(CFM, self).__init__()
- self.relu = nn.ReLU(True)
-
- self.upsample = nn.Upsample(scale_factor=2, mode='bilinear', align_corners=True)
- self.conv_upsample1 = BasicConv2d(channel, channel, 3, padding=1)
- self.conv_upsample2 = BasicConv2d(channel, channel, 3, padding=1)
- self.conv_upsample3 = BasicConv2d(channel, channel, 3, padding=1)
- self.conv_upsample4 = BasicConv2d(channel, channel, 3, padding=1)
- self.conv_upsample5 = BasicConv2d(2 * channel, 2 * channel, 3, padding=1)
-
- self.conv_concat2 = BasicConv2d(2 * channel, 2 * channel, 3, padding=1)
- self.conv_concat3 = BasicConv2d(3 * channel, 3 * channel, 3, padding=1)
- self.conv4 = BasicConv2d(3 * channel, channel, 3, padding=1)
-
- def forward(self, x1, x2, x3):
- x1_1 = x1
- x2_1 = self.conv_upsample1(self.upsample(x1)) * x2
- x3_1 = self.conv_upsample2(self.upsample(self.upsample(x1))) \
- * self.conv_upsample3(self.upsample(x2)) * x3
-
- x2_2 = torch.cat((x2_1, self.conv_upsample4(self.upsample(x1_1))), 1)
- x2_2 = self.conv_concat2(x2_2)
-
- x3_2 = torch.cat((x3_1, self.conv_upsample5(self.upsample(x2_2))), 1)
- x3_2 = self.conv_concat3(x3_2)
-
- x1 = self.conv4(x3_2)
-
- return x1
-
-
-
-
- class GCN(nn.Module):
- def __init__(self, num_state, num_node, bias=False):
- super(GCN, self).__init__()
- self.conv1 = nn.Conv1d(num_node, num_node, kernel_size=1)
- self.relu = nn.ReLU(inplace=True)
- self.conv2 = nn.Conv1d(num_state, num_state, kernel_size=1, bias=bias)
-
- def forward(self, x):
- h = self.conv1(x.permute(0, 2, 1)).permute(0, 2, 1)
- h = h - x
- h = self.relu(self.conv2(h))
- return h
-
-
- class SAM(nn.Module):
- def __init__(self, num_in=32, plane_mid=16, mids=4, normalize=False):
- super(SAM, self).__init__()
-
- self.normalize = normalize
- self.num_s = int(plane_mid)
- self.num_n = (mids) * (mids)
- self.priors = nn.AdaptiveAvgPool2d(output_size=(mids + 2, mids + 2))
-
- self.conv_state = nn.Conv2d(num_in, self.num_s, kernel_size=1)
- self.conv_proj = nn.Conv2d(num_in, self.num_s, kernel_size=1)
- self.gcn = GCN(num_state=self.num_s, num_node=self.num_n)
- self.conv_extend = nn.Conv2d(self.num_s, num_in, kernel_size=1, bias=False)
-
- def forward(self, x, edge):
- edge = F.upsample(edge, (x.size()[-2], x.size()[-1]))
-
- n, c, h, w = x.size()
- edge = torch.nn.functional.softmax(edge, dim=1)[:, 1, :, :].unsqueeze(1)
-
- x_state_reshaped = self.conv_state(x).view(n, self.num_s, -1)
- x_proj = self.conv_proj(x)
- x_mask = x_proj * edge
-
- x_anchor1 = self.priors(x_mask)
- x_anchor2 = self.priors(x_mask)[:, :, 1:-1, 1:-1].reshape(n, self.num_s, -1)
- x_anchor = self.priors(x_mask)[:, :, 1:-1, 1:-1].reshape(n, self.num_s, -1)
-
- x_proj_reshaped = torch.matmul(x_anchor.permute(0, 2, 1), x_proj.reshape(n, self.num_s, -1))
- x_proj_reshaped = torch.nn.functional.softmax(x_proj_reshaped, dim=1)
-
- x_rproj_reshaped = x_proj_reshaped
-
- x_n_state = torch.matmul(x_state_reshaped, x_proj_reshaped.permute(0, 2, 1))
- if self.normalize:
- x_n_state = x_n_state * (1. / x_state_reshaped.size(2))
- x_n_rel = self.gcn(x_n_state)
-
- x_state_reshaped = torch.matmul(x_n_rel, x_rproj_reshaped)
- x_state = x_state_reshaped.view(n, self.num_s, *x.size()[2:])
- out = x + (self.conv_extend(x_state))
-
- return out
-
-
- class ChannelAttention(nn.Module):
- def __init__(self, in_planes, ratio=16):
- super(ChannelAttention, self).__init__()
- self.avg_pool = nn.AdaptiveAvgPool2d(1)
- self.max_pool = nn.AdaptiveMaxPool2d(1)
-
- self.fc1 = nn.Conv2d(in_planes, in_planes // 16, 1, bias=False)
- self.relu1 = nn.ReLU()
- self.fc2 = nn.Conv2d(in_planes // 16, in_planes, 1, bias=False)
-
- self.sigmoid = nn.Sigmoid()
-
- def forward(self, x):
- avg_out = self.fc2(self.relu1(self.fc1(self.avg_pool(x))))
- max_out = self.fc2(self.relu1(self.fc1(self.max_pool(x))))
- out = avg_out + max_out
- return self.sigmoid(out)
-
-
- class SpatialAttention(nn.Module):
- def __init__(self, kernel_size=7):
- super(SpatialAttention, self).__init__()
-
- assert kernel_size in (3, 7), 'kernel size must be 3 or 7'
- padding = 3 if kernel_size == 7 else 1
-
- self.conv1 = nn.Conv2d(2, 1, kernel_size, padding=padding, bias=False)
- self.sigmoid = nn.Sigmoid()
-
- def forward(self, x):
- avg_out = torch.mean(x, dim=1, keepdim=True)
- max_out, _ = torch.max(x, dim=1, keepdim=True)
- x = torch.cat([avg_out, max_out], dim=1)
- x = self.conv1(x)
- return self.sigmoid(x)
-
-
- class pvt_PPD(nn.Module):
- def __init__(self, channel=32, class_num=1):
- super(pvt_PPD, self).__init__()
-
- self.backbone = pvt_v2_b2() # [64, 128, 320, 512]
- # path = './pretrained_pth/pvt_v2_b2.pth'
- # save_model = torch.load(path)
- # model_dict = self.backbone.state_dict()
- # state_dict = {k: v for k, v in save_model.items() if k in model_dict.keys()}
- # model_dict.update(state_dict)
- # self.backbone.load_state_dict(model_dict)
-
- self.Translayer2_0 = BasicConv2d(64, channel, 1)
- self.Translayer2_1 = BasicConv2d(128, channel, 1)
- self.Translayer3_1 = BasicConv2d(320, channel, 1)
- self.Translayer4_1 = BasicConv2d(512, channel, 1)
-
- self.CFM = CFM(channel)
- self.ca = ChannelAttention(64)
- self.sa = SpatialAttention()
- self.SAM = SAM()
-
- self.down05 = nn.Upsample(scale_factor=0.5, mode='bilinear', align_corners=True)
- self.out_SAM = nn.Conv2d(channel, 1, 1)
- self.out_CFM = nn.Conv2d(channel, 1, 1)
-
-
- def forward(self, x):
-
- # backbone
- pvt = self.backbone(x)
- x1 = pvt[0]
- x2 = pvt[1]
- x3 = pvt[2]
- x4 = pvt[3]
-
- # CIM
- x1 = self.ca(x1) * x1 # channel attention
- cim_feature = self.sa(x1) * x1 # spatial attention
-
-
- # CFM
- x2_t = self.Translayer2_1(x2)
- x3_t = self.Translayer3_1(x3)
- x4_t = self.Translayer4_1(x4)
- cfm_feature = self.CFM(x4_t, x3_t, x2_t)
-
- # SAM
- T2 = self.Translayer2_0(cim_feature)
- T2 = self.down05(T2)
- sam_feature = self.SAM(cfm_feature, T2)
-
- prediction1 = self.out_CFM(cfm_feature)
- prediction2 = self.out_SAM(sam_feature)
-
- prediction1_8 = F.interpolate(prediction1, scale_factor=8, mode='bilinear')
- prediction2_8 = F.interpolate(prediction2, scale_factor=8, mode='bilinear')
- return prediction1_8, prediction2_8
-
-
- if __name__ == '__main__':
- model = pvt_PPD()
- model = model.to('cuda')
- from torchinfo import summary
- summary(model, (1, 3, 512, 512))
- from thop import profile
- import torch
- input = torch.randn(1, 3, 352, 352).to('cuda')
- macs, params = profile(model, inputs=(input, ))
- print('macs:',macs/1000000000)
- print('params:',params/1000000)
-
-
|