目标检测算法改进系列之Backbone替换为FocalNet

FocalNet

近些年，Transformers在自然语言处理、图像分类、目标检测和图像分割上均取得了较大的成功，归根结底是自注意力（SA ：self-attention）起到了关键性的作用，因此能够支持输入信息的全局交互。但是由于视觉tokens的大量存在，自注意力的计算复杂度高，尤其是在高分辨的输入时，因此针对该缺陷，论文《Focal Modulation Networks》提出了FocalNet网络。

论文地址：Focal Modulation Networks

原理：使用新提出的Focal Modulation替代之前的SA自注意力模块，解耦聚合和单个查询过程，先将查询周围的上下文信息进行聚合，再根据聚合信息获取查询结果。如下图所示，图中红色表示query token。对比来看，Window-wise Self-Attention (SA)利用周围的token（橙色）来捕获空间上下文信息；在此基础上，Focal Attention扩大了感受野，还可以使用更远的summarized tokens（蓝色）；而Focal Modulation更为强大，先利用诸如depth-wise convolution的方式将不同粒度级别的空间上下文编码为summarized tokens （橙色、绿色和蓝色），再根据查询内容，选择性的将这些summarized tokens融合为query token。而本文新提出的方式便是进行轻量化，将聚合和单个查询进行解耦，减少计算量。

在前两者中，绿色和紫色箭头分别代表注意力交互和基于查询的聚合，但是都存在一个缺陷，即：均需要涉及大量的交互和聚合操作。而Focal Modulation计算过程得到大量简化。
原理图

FocalNet代码实现

# --------------------------------------------------------
# FocalNets -- Focal Modulation Networks
# Copyright (c) 2022 Microsoft
# Licensed under The MIT License [see LICENSE for details]
# Written by Jianwei Yang (jianwyan@microsoft.com)
# --------------------------------------------------------import numpy as np
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.utils.checkpoint as checkpoint
from timm.models.layers import DropPath, to_2tuple, trunc_normal___all__ = ['focalnet_tiny_srf', 'focalnet_tiny_lrf', 'focalnet_small_srf', 'focalnet_small_lrf', 'focalnet_base_srf', 'focalnet_base_lrf', 'focalnet_large_fl3', 'focalnet_large_fl4', 'focalnet_xlarge_fl3', 'focalnet_xlarge_fl4', 'focalnet_huge_fl3', 'focalnet_huge_fl4']def update_weight(model_dict, weight_dict):idx, temp_dict = 0, {}for k, v in weight_dict.items():if k in model_dict.keys() and np.shape(model_dict[k]) == np.shape(v):temp_dict[k] = vidx += 1model_dict.update(temp_dict)print(f'loading weights... {idx}/{len(model_dict)} items')return model_dictclass 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_featureshidden_features = hidden_features or in_featuresself.fc1 = nn.Linear(in_features, hidden_features)self.act = act_layer()self.fc2 = nn.Linear(hidden_features, out_features)self.drop = nn.Dropout(drop)def forward(self, x):x = self.fc1(x)     x = self.act(x)x = self.drop(x)x = self.fc2(x)x = self.drop(x)return xclass FocalModulation(nn.Module):def __init__(self, dim, focal_window, focal_level, focal_factor=2, bias=True, proj_drop=0., use_postln_in_modulation=False, normalize_modulator=False):super().__init__()self.dim = dimself.focal_window = focal_windowself.focal_level = focal_levelself.focal_factor = focal_factorself.use_postln_in_modulation = use_postln_in_modulationself.normalize_modulator = normalize_modulatorself.f = nn.Linear(dim, 2*dim + (self.focal_level+1), bias=bias)self.h = nn.Conv2d(dim, dim, kernel_size=1, stride=1, bias=bias)self.act = nn.GELU()self.proj = nn.Linear(dim, dim)self.proj_drop = nn.Dropout(proj_drop)self.focal_layers = nn.ModuleList()self.kernel_sizes = []for k in range(self.focal_level):kernel_size = self.focal_factor*k + self.focal_windowself.focal_layers.append(nn.Sequential(nn.Conv2d(dim, dim, kernel_size=kernel_size, stride=1, groups=dim, padding=kernel_size//2, bias=False),nn.GELU(),))              self.kernel_sizes.append(kernel_size)          if self.use_postln_in_modulation:self.ln = nn.LayerNorm(dim)def forward(self, x):"""Args:x: input features with shape of (B, H, W, C)"""C = x.shape[-1]# pre linear projectionx = self.f(x).permute(0, 3, 1, 2).contiguous()q, ctx, gates = torch.split(x, (C, C, self.focal_level+1), 1)# context aggreationctx_all = 0 for l in range(self.focal_level):         ctx = self.focal_layers[l](ctx)ctx_all = ctx_all + ctx * gates[:, l:l+1]ctx_global = self.act(ctx.mean(2, keepdim=True).mean(3, keepdim=True))ctx_all = ctx_all + ctx_global * gates[:,self.focal_level:]# normalize contextif self.normalize_modulator:ctx_all = ctx_all / (self.focal_level+1)# focal modulationmodulator = self.h(ctx_all)x_out = q * modulatorx_out = x_out.permute(0, 2, 3, 1).contiguous()if self.use_postln_in_modulation:x_out = self.ln(x_out)# post linear porjectionx_out = self.proj(x_out)x_out = self.proj_drop(x_out)return x_outdef extra_repr(self) -> str:return f'dim={self.dim}'def flops(self, N):# calculate flops for 1 window with token length of Nflops = 0flops += N * self.dim * (self.dim * 2 + (self.focal_level+1))# focal convolutionfor k in range(self.focal_level):flops += N * (self.kernel_sizes[k]**2+1) * self.dim# global gatingflops += N * 1 * self.dim #  self.linearflops += N * self.dim * (self.dim + 1)# x = self.proj(x)flops += N * self.dim * self.dimreturn flopsclass FocalNetBlock(nn.Module):r""" Focal Modulation Network Block.Args:dim (int): Number of input channels.input_resolution (tuple[int]): Input resulotion.mlp_ratio (float): Ratio of mlp hidden dim to embedding dim.drop (float, optional): Dropout rate. Default: 0.0drop_path (float, optional): Stochastic depth rate. Default: 0.0act_layer (nn.Module, optional): Activation layer. Default: nn.GELUnorm_layer (nn.Module, optional): Normalization layer.  Default: nn.LayerNormfocal_level (int): Number of focal levels. focal_window (int): Focal window size at first focal leveluse_layerscale (bool): Whether use layerscalelayerscale_value (float): Initial layerscale valueuse_postln (bool): Whether use layernorm after modulation"""def __init__(self, dim, input_resolution, mlp_ratio=4., drop=0., drop_path=0., act_layer=nn.GELU, norm_layer=nn.LayerNorm,focal_level=1, focal_window=3,use_layerscale=False, layerscale_value=1e-4, use_postln=False, use_postln_in_modulation=False, normalize_modulator=False):super().__init__()self.dim = dimself.input_resolution = input_resolutionself.mlp_ratio = mlp_ratioself.focal_window = focal_windowself.focal_level = focal_levelself.use_postln = use_postlnself.norm1 = norm_layer(dim)self.modulation = FocalModulation(dim, proj_drop=drop, focal_window=focal_window, focal_level=self.focal_level, use_postln_in_modulation=use_postln_in_modulation, normalize_modulator=normalize_modulator)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.gamma_1 = 1.0self.gamma_2 = 1.0    if use_layerscale:self.gamma_1 = nn.Parameter(layerscale_value * torch.ones((dim)), requires_grad=True)self.gamma_2 = nn.Parameter(layerscale_value * torch.ones((dim)), requires_grad=True)self.H = Noneself.W = Nonedef forward(self, x):H, W = self.H, self.WB, L, C = x.shapeshortcut = x# Focal Modulationx = x if self.use_postln else self.norm1(x)x = x.view(B, H, W, C)x = self.modulation(x).view(B, H * W, C)x = x if not self.use_postln else self.norm1(x)# FFNx = shortcut + self.drop_path(self.gamma_1 * x)x = x + self.drop_path(self.gamma_2 * (self.norm2(self.mlp(x)) if self.use_postln else self.mlp(self.norm2(x))))return xdef extra_repr(self) -> str:return f"dim={self.dim}, input_resolution={self.input_resolution}, " \f"mlp_ratio={self.mlp_ratio}"def flops(self):flops = 0H, W = self.input_resolution# norm1flops += self.dim * H * W# W-MSA/SW-MSAflops += self.modulation.flops(H*W)# mlpflops += 2 * H * W * self.dim * self.dim * self.mlp_ratio# norm2flops += self.dim * H * Wreturn flopsclass BasicLayer(nn.Module):""" A basic Focal Transformer layer for one stage.Args:dim (int): Number of input channels.input_resolution (tuple[int]): Input resolution.depth (int): Number of blocks.window_size (int): Local window size.mlp_ratio (float): Ratio of mlp hidden dim to embedding dim.qkv_bias (bool, optional): If True, add a learnable bias to query, key, value. Default: Trueqk_scale (float | None, optional): Override default qk scale of head_dim ** -0.5 if set.drop (float, optional): Dropout rate. Default: 0.0drop_path (float | tuple[float], optional): Stochastic depth rate. Default: 0.0norm_layer (nn.Module, optional): Normalization layer. Default: nn.LayerNormdownsample (nn.Module | None, optional): Downsample layer at the end of the layer. Default: Noneuse_checkpoint (bool): Whether to use checkpointing to save memory. Default: False.focal_level (int): Number of focal levelsfocal_window (int): Focal window size at first focal leveluse_layerscale (bool): Whether use layerscalelayerscale_value (float): Initial layerscale valueuse_postln (bool): Whether use layernorm after modulation"""def __init__(self, dim, out_dim, input_resolution, depth,mlp_ratio=4., drop=0., drop_path=0., norm_layer=nn.LayerNorm, downsample=None, use_checkpoint=False, focal_level=1, focal_window=1, use_conv_embed=False, use_layerscale=False, layerscale_value=1e-4, use_postln=False, use_postln_in_modulation=False, normalize_modulator=False):super().__init__()self.dim = dimself.input_resolution = input_resolutionself.depth = depthself.use_checkpoint = use_checkpoint# build blocksself.blocks = nn.ModuleList([FocalNetBlock(dim=dim, input_resolution=input_resolution,mlp_ratio=mlp_ratio, drop=drop, drop_path=drop_path[i] if isinstance(drop_path, list) else drop_path,norm_layer=norm_layer,focal_level=focal_level,focal_window=focal_window, use_layerscale=use_layerscale, layerscale_value=layerscale_value,use_postln=use_postln, use_postln_in_modulation=use_postln_in_modulation, normalize_modulator=normalize_modulator, )for i in range(depth)])if downsample is not None:self.downsample = downsample(img_size=input_resolution, patch_size=2, in_chans=dim, embed_dim=out_dim, use_conv_embed=use_conv_embed, norm_layer=norm_layer, is_stem=False)else:self.downsample = Nonedef forward(self, x, H, W):for blk in self.blocks:blk.H, blk.W = H, Wif self.use_checkpoint:x = checkpoint.checkpoint(blk, x)else:x = blk(x)if self.downsample is not None:x = x.transpose(1, 2).reshape(x.shape[0], -1, H, W)x, Ho, Wo = self.downsample(x)else:Ho, Wo = H, W        return x, Ho, Wodef extra_repr(self) -> str:return f"dim={self.dim}, input_resolution={self.input_resolution}, depth={self.depth}"def flops(self):flops = 0for blk in self.blocks:flops += blk.flops()if self.downsample is not None:flops += self.downsample.flops()return flopsclass PatchEmbed(nn.Module):r""" Image to Patch EmbeddingArgs:img_size (int): Image size.  Default: 224.patch_size (int): Patch token size. Default: 4.in_chans (int): Number of input image channels. Default: 3.embed_dim (int): Number of linear projection output channels. Default: 96.norm_layer (nn.Module, optional): Normalization layer. Default: None"""def __init__(self, img_size=(224, 224), patch_size=4, in_chans=3, embed_dim=96, use_conv_embed=False, norm_layer=None, is_stem=False):super().__init__()patch_size = to_2tuple(patch_size)patches_resolution = [img_size[0] // patch_size[0], img_size[1] // patch_size[1]]self.img_size = img_sizeself.patch_size = patch_sizeself.patches_resolution = patches_resolutionself.num_patches = patches_resolution[0] * patches_resolution[1]self.in_chans = in_chansself.embed_dim = embed_dimif use_conv_embed:# if we choose to use conv embedding, then we treat the stem and non-stem differentlyif is_stem:kernel_size = 7; padding = 2; stride = 4else:kernel_size = 3; padding = 1; stride = 2self.proj = nn.Conv2d(in_chans, embed_dim, kernel_size=kernel_size, stride=stride, padding=padding)else:self.proj = nn.Conv2d(in_chans, embed_dim, kernel_size=patch_size, stride=patch_size)if norm_layer is not None:self.norm = norm_layer(embed_dim)else:self.norm = Nonedef forward(self, x):B, C, H, W = x.shapex = self.proj(x)        H, W = x.shape[2:]x = x.flatten(2).transpose(1, 2)  # B Ph*Pw Cif self.norm is not None:x = self.norm(x)return x, H, Wdef flops(self):Ho, Wo = self.patches_resolutionflops = Ho * Wo * self.embed_dim * self.in_chans * (self.patch_size[0] * self.patch_size[1])if self.norm is not None:flops += Ho * Wo * self.embed_dimreturn flopsclass FocalNet(nn.Module):r""" Focal Modulation Networks (FocalNets)Args:img_size (int | tuple(int)): Input image size. Default 224patch_size (int | tuple(int)): Patch size. Default: 4in_chans (int): Number of input image channels. Default: 3num_classes (int): Number of classes for classification head. Default: 1000embed_dim (int): Patch embedding dimension. Default: 96depths (tuple(int)): Depth of each Focal Transformer layer.mlp_ratio (float): Ratio of mlp hidden dim to embedding dim. Default: 4drop_rate (float): Dropout rate. Default: 0drop_path_rate (float): Stochastic depth rate. Default: 0.1norm_layer (nn.Module): Normalization layer. Default: nn.LayerNorm.patch_norm (bool): If True, add normalization after patch embedding. Default: Trueuse_checkpoint (bool): Whether to use checkpointing to save memory. Default: False focal_levels (list): How many focal levels at all stages. Note that this excludes the finest-grain level. Default: [1, 1, 1, 1] focal_windows (list): The focal window size at all stages. Default: [7, 5, 3, 1] use_conv_embed (bool): Whether use convolutional embedding. We noted that using convolutional embedding usually improve the performance, but we do not use it by default. Default: False use_layerscale (bool): Whether use layerscale proposed in CaiT. Default: False layerscale_value (float): Value for layer scale. Default: 1e-4 use_postln (bool): Whether use layernorm after modulation (it helps stablize training of large models)"""def __init__(self, img_size=224, patch_size=4, in_chans=3, num_classes=1000,embed_dim=96, depths=[2, 2, 6, 2], mlp_ratio=4., drop_rate=0., drop_path_rate=0.1,norm_layer=nn.LayerNorm, patch_norm=True,use_checkpoint=False,                 focal_levels=[2, 2, 2, 2], focal_windows=[3, 3, 3, 3], use_conv_embed=False, use_layerscale=False, layerscale_value=1e-4, use_postln=False, use_postln_in_modulation=False, normalize_modulator=False, **kwargs):super().__init__()self.num_layers = len(depths)embed_dim = [embed_dim * (2 ** i) for i in range(self.num_layers)]self.num_classes = num_classesself.embed_dim = embed_dimself.patch_norm = patch_normself.num_features = embed_dim[-1]self.mlp_ratio = mlp_ratio# split image into patches using either non-overlapped embedding or overlapped embeddingself.patch_embed = PatchEmbed(img_size=to_2tuple(img_size), patch_size=patch_size, in_chans=in_chans, embed_dim=embed_dim[0], use_conv_embed=use_conv_embed, norm_layer=norm_layer if self.patch_norm else None, is_stem=True)num_patches = self.patch_embed.num_patchespatches_resolution = self.patch_embed.patches_resolutionself.patches_resolution = patches_resolutionself.pos_drop = nn.Dropout(p=drop_rate)# stochastic depthdpr = [x.item() for x in torch.linspace(0, drop_path_rate, sum(depths))]  # stochastic depth decay rule# build layersself.layers = nn.ModuleList()for i_layer in range(self.num_layers):layer = BasicLayer(dim=embed_dim[i_layer], out_dim=embed_dim[i_layer+1] if (i_layer < self.num_layers - 1) else None,  input_resolution=(patches_resolution[0] // (2 ** i_layer),patches_resolution[1] // (2 ** i_layer)),depth=depths[i_layer],mlp_ratio=self.mlp_ratio,drop=drop_rate, drop_path=dpr[sum(depths[:i_layer]):sum(depths[:i_layer + 1])],norm_layer=norm_layer, downsample=PatchEmbed if (i_layer < self.num_layers - 1) else None,focal_level=focal_levels[i_layer], focal_window=focal_windows[i_layer], use_conv_embed=use_conv_embed,use_checkpoint=use_checkpoint, use_layerscale=use_layerscale, layerscale_value=layerscale_value, use_postln=use_postln,use_postln_in_modulation=use_postln_in_modulation, normalize_modulator=normalize_modulator)self.layers.append(layer)self.norm = norm_layer(self.num_features)self.apply(self._init_weights)self.channel = [i.size(1) for i in self.forward(torch.randn(1, 3, 640, 640))]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)@torch.jit.ignoredef no_weight_decay(self):return {''}@torch.jit.ignoredef no_weight_decay_keywords(self):return {''}def forward(self, x):input_size = x.size(2)scale = [4, 8, 16, 32]x, H, W = self.patch_embed(x)x = self.pos_drop(x)features = [x, None, None, None]for layer in self.layers:x, H, W = layer(x, H, W)if input_size // H in scale:features[scale.index(input_size // H)] = x# features[-1] = self.norm(features[-1])  # B L Cfor i in range(len(features)):features[i] = torch.transpose(features[i], dim0=2, dim1=1).view(-1,features[i].size(2), int(features[i].size(1) ** 0.5), int(features[i].size(1) ** 0.5))return featuresdef flops(self):flops = 0flops += self.patch_embed.flops()for i, layer in enumerate(self.layers):flops += layer.flops()flops += self.num_features * self.patches_resolution[0] * self.patches_resolution[1] // (2 ** self.num_layers)flops += self.num_features * self.num_classesreturn flopsmodel_urls = {"focalnet_tiny_srf": "https://projects4jw.blob.core.windows.net/focalnet/release/classification/focalnet_tiny_srf.pth","focalnet_tiny_lrf": "https://projects4jw.blob.core.windows.net/focalnet/release/classification/focalnet_tiny_lrf.pth","focalnet_small_srf": "https://projects4jw.blob.core.windows.net/focalnet/release/classification/focalnet_small_srf.pth","focalnet_small_lrf": "https://projects4jw.blob.core.windows.net/focalnet/release/classification/focalnet_small_lrf.pth","focalnet_base_srf": "https://projects4jw.blob.core.windows.net/focalnet/release/classification/focalnet_base_srf.pth","focalnet_base_lrf": "https://projects4jw.blob.core.windows.net/focalnet/release/classification/focalnet_base_lrf.pth",    "focalnet_large_fl3": "https://projects4jw.blob.core.windows.net/focalnet/release/classification/focalnet_large_lrf_384.pth", "focalnet_large_fl4": "https://projects4jw.blob.core.windows.net/focalnet/release/classification/focalnet_large_lrf_384_fl4.pth", "focalnet_xlarge_fl3": "https://projects4jw.blob.core.windows.net/focalnet/release/classification/focalnet_xlarge_lrf_384.pth", "focalnet_xlarge_fl4": "https://projects4jw.blob.core.windows.net/focalnet/release/classification/focalnet_xlarge_lrf_384_fl4.pth", "focalnet_huge_fl3": "https://projects4jw.blob.core.windows.net/focalnet/release/classification/focalnet_huge_lrf_224.pth", "focalnet_huge_fl4": "https://projects4jw.blob.core.windows.net/focalnet/release/classification/focalnet_huge_lrf_224_fl4.pth", 
}def focalnet_tiny_srf(pretrained=False, **kwargs):model = FocalNet(depths=[2, 2, 6, 2], embed_dim=96, **kwargs)if pretrained:url = model_urls['focalnet_tiny_srf']checkpoint = torch.hub.load_state_dict_from_url(url=url, map_location="cpu", check_hash=True)model.load_state_dict(update_weight(model.state_dict(), checkpoint["model"]))return modeldef focalnet_small_srf(pretrained=False, **kwargs):model = FocalNet(depths=[2, 2, 18, 2], embed_dim=96, **kwargs)if pretrained:url = model_urls['focalnet_small_srf']checkpoint = torch.hub.load_state_dict_from_url(url=url, map_location="cpu")model.load_state_dict(update_weight(model.state_dict(), checkpoint["model"]))return modeldef focalnet_base_srf(pretrained=False, **kwargs):model = FocalNet(depths=[2, 2, 18, 2], embed_dim=128, **kwargs)if pretrained:url = model_urls['focalnet_base_srf']checkpoint = torch.hub.load_state_dict_from_url(url=url, map_location="cpu")model.load_state_dict(update_weight(model.state_dict(), checkpoint["model"]))return modeldef focalnet_tiny_lrf(pretrained=False, **kwargs):model = FocalNet(depths=[2, 2, 6, 2], embed_dim=96, **kwargs)if pretrained:url = model_urls['focalnet_tiny_lrf']checkpoint = torch.hub.load_state_dict_from_url(url=url, map_location="cpu", check_hash=True)model.load_state_dict(update_weight(model.state_dict(), checkpoint["model"]))return modeldef focalnet_small_lrf(pretrained=False, **kwargs):model = FocalNet(depths=[2, 2, 18, 2], embed_dim=96, **kwargs)if pretrained:url = model_urls['focalnet_small_lrf']checkpoint = torch.hub.load_state_dict_from_url(url=url, map_location="cpu")model.load_state_dict(update_weight(model.state_dict(), checkpoint["model"]))return modeldef focalnet_base_lrf(pretrained=False, **kwargs):model = FocalNet(depths=[2, 2, 18, 2], embed_dim=128, **kwargs)if pretrained:url = model_urls['focalnet_base_lrf']checkpoint = torch.hub.load_state_dict_from_url(url=url, map_location="cpu")model.load_state_dict(update_weight(model.state_dict(), checkpoint["model"]))return modeldef focalnet_tiny_iso(pretrained=False, **kwargs):model = FocalNet(depths=[12], patch_size=16, embed_dim=192, **kwargs)if pretrained:url = model_urls['focalnet_tiny_iso']checkpoint = torch.hub.load_state_dict_from_url(url=url, map_location="cpu", check_hash=True)model.load_state_dict(update_weight(model.state_dict(), checkpoint["model"]))return modeldef focalnet_small_iso(pretrained=False, **kwargs):model = FocalNet(depths=[12], patch_size=16, embed_dim=384, **kwargs)if pretrained:url = model_urls['focalnet_small_iso']checkpoint = torch.hub.load_state_dict_from_url(url=url, map_location="cpu")model.load_state_dict(update_weight(model.state_dict(), checkpoint["model"]))return modeldef focalnet_base_iso(pretrained=False, **kwargs):model = FocalNet(depths=[12], patch_size=16, embed_dim=768, focal_levels=[3], focal_windows=[3], use_layerscale=True, use_postln=True, **kwargs)if pretrained:url = model_urls['focalnet_base_iso']checkpoint = torch.hub.load_state_dict_from_url(url=url, map_location="cpu")model.load_state_dict(update_weight(model.state_dict(), checkpoint["model"]))return model# FocalNet large+ models 
def focalnet_large_fl3(pretrained=False, **kwargs):model = FocalNet(depths=[2, 2, 18, 2], embed_dim=192, **kwargs)if pretrained:url = model_urls['focalnet_large_fl3']checkpoint = torch.hub.load_state_dict_from_url(url=url, map_location="cpu")model.load_state_dict(update_weight(model.state_dict(), checkpoint["model"]))return modeldef focalnet_large_fl4(pretrained=False, **kwargs):model = FocalNet(depths=[2, 2, 18, 2], embed_dim=192, **kwargs)if pretrained:url = model_urls['focalnet_large_fl4']checkpoint = torch.hub.load_state_dict_from_url(url=url, map_location="cpu")model.load_state_dict(update_weight(model.state_dict(), checkpoint["model"]))return modeldef focalnet_xlarge_fl3(pretrained=False, **kwargs):model = FocalNet(depths=[2, 2, 18, 2], embed_dim=256, **kwargs)if pretrained:url = model_urls['focalnet_xlarge_fl3']checkpoint = torch.hub.load_state_dict_from_url(url=url, map_location="cpu")model.load_state_dict(update_weight(model.state_dict(), checkpoint["model"]))return modeldef focalnet_xlarge_fl4(pretrained=False, **kwargs):model = FocalNet(depths=[2, 2, 18, 2], embed_dim=256, **kwargs)if pretrained:url = model_urls['focalnet_xlarge_fl4']checkpoint = torch.hub.load_state_dict_from_url(url=url, map_location="cpu")model.load_state_dict(update_weight(model.state_dict(), checkpoint["model"]))return modeldef focalnet_huge_fl3(pretrained=False, **kwargs):model = FocalNet(depths=[2, 2, 18, 2], embed_dim=352, **kwargs)if pretrained:url = model_urls['focalnet_huge_fl3']checkpoint = torch.hub.load_state_dict_from_url(url=url, map_location="cpu")model.load_state_dict(update_weight(model.state_dict(), checkpoint["model"]))return modeldef focalnet_huge_fl4(pretrained=False, **kwargs):model = FocalNet(depths=[2, 2, 18, 2], embed_dim=352, **kwargs)if pretrained:url = model_urls['focalnet_huge_fl4']checkpoint = torch.hub.load_state_dict_from_url(url=url, map_location="cpu")model.load_state_dict(update_weight(model.state_dict(), checkpoint["model"]))return modelif __name__ == '__main__':from copy import deepcopyimg_size = 640x = torch.rand(16, 3, img_size, img_size).cuda()model = focalnet_tiny_srf(pretrained=True).cuda()# model_copy = deepcopy(model)for i in model(x):print(i.size())flops = model.flops()print(f"number of GFLOPs: {flops / 1e9}")n_parameters = sum(p.numel() for p in model.parameters() if p.requires_grad)print(f"number of params: {n_parameters}")print(list(model_urls.keys()))

Backbone替换

yolo.py修改

def parse_model函数

def parse_model(d, ch):  # model_dict, input_channels(3)# Parse a YOLOv5 model.yaml dictionaryLOGGER.info(f"\n{'':>3}{'from':>18}{'n':>3}{'params':>10}  {'module':<40}{'arguments':<30}")anchors, nc, gd, gw, act = d['anchors'], d['nc'], d['depth_multiple'], d['width_multiple'], d.get('activation')if act:Conv.default_act = eval(act)  # redefine default activation, i.e. Conv.default_act = nn.SiLU()LOGGER.info(f"{colorstr('activation:')} {act}")  # printna = (len(anchors[0]) // 2) if isinstance(anchors, list) else anchors  # number of anchorsno = na * (nc + 5)  # number of outputs = anchors * (classes + 5)is_backbone = Falselayers, save, c2 = [], [], ch[-1]  # layers, savelist, ch outfor i, (f, n, m, args) in enumerate(d['backbone'] + d['head']):  # from, number, module, argstry:t = mm = eval(m) if isinstance(m, str) else m  # eval stringsexcept:passfor j, a in enumerate(args):with contextlib.suppress(NameError):try:args[j] = eval(a) if isinstance(a, str) else a  # eval stringsexcept:args[j] = an = n_ = max(round(n * gd), 1) if n > 1 else n  # depth gainif m in {Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv,BottleneckCSP, C3, C3TR, C3SPP, C3Ghost, nn.ConvTranspose2d, DWConvTranspose2d, C3x}:c1, c2 = ch[f], args[0]if c2 != no:  # if not outputc2 = make_divisible(c2 * gw, 8)args = [c1, c2, *args[1:]]if m in {BottleneckCSP, C3, C3TR, C3Ghost, C3x}:args.insert(2, n)  # number of repeatsn = 1elif m is nn.BatchNorm2d:args = [ch[f]]elif m is Concat:c2 = sum(ch[x] for x in f)# TODO: channel, gw, gdelif m in {Detect, Segment}:args.append([ch[x] for x in f])if isinstance(args[1], int):  # number of anchorsargs[1] = [list(range(args[1] * 2))] * len(f)if m is Segment:args[3] = make_divisible(args[3] * gw, 8)elif m is Contract:c2 = ch[f] * args[0] ** 2elif m is Expand:c2 = ch[f] // args[0] ** 2elif isinstance(m, str):t = mm = timm.create_model(m, pretrained=args[0], features_only=True)c2 = m.feature_info.channels()elif m in {focalnet_tiny_srf}: #可添加更多Backbonem = m(*args)c2 = m.channelelse:c2 = ch[f]if isinstance(c2, list):is_backbone = Truem_ = mm_.backbone = Trueelse:m_ = nn.Sequential(*(m(*args) for _ in range(n))) if n > 1 else m(*args)  # modulet = str(m)[8:-2].replace('__main__.', '')  # module typenp = sum(x.numel() for x in m_.parameters())  # number paramsm_.i, m_.f, m_.type, m_.np = i + 4 if is_backbone else i, f, t, np  # attach index, 'from' index, type, number paramsLOGGER.info(f'{i:>3}{str(f):>18}{n_:>3}{np:10.0f}  {t:<40}{str(args):<30}')  # printsave.extend(x % (i + 4 if is_backbone else i) for x in ([f] if isinstance(f, int) else f) if x != -1)  # append to savelistlayers.append(m_)if i == 0:ch = []if isinstance(c2, list):ch.extend(c2)for _ in range(5 - len(ch)):ch.insert(0, 0)else:ch.append(c2)return nn.Sequential(*layers), sorted(save)

def _forward_once函数

def _forward_once(self, x, profile=False, visualize=False):y, dt = [], []  # outputsfor m in self.model:if m.f != -1:  # if not from previous layerx = y[m.f] if isinstance(m.f, int) else [x if j == -1 else y[j] for j in m.f]  # from earlier layersif profile:self._profile_one_layer(m, x, dt)if hasattr(m, 'backbone'):x = m(x)for _ in range(5 - len(x)):x.insert(0, None)for i_idx, i in enumerate(x):if i_idx in self.save:y.append(i)else:y.append(None)x = x[-1]else:x = m(x)  # runy.append(x if m.i in self.save else None)  # save outputif visualize:feature_visualization(x, m.type, m.i, save_dir=visualize)return x

创建新的.yaml配置文件

# YOLOv5 🚀 by Ultralytics, GPL-3.0 license# Parameters
nc: 80  # number of classes
depth_multiple: 0.33  # model depth multiple
width_multiple: 0.25  # layer channel multiple
anchors:- [10,13, 16,30, 33,23]  # P3/8- [30,61, 62,45, 59,119]  # P4/16- [116,90, 156,198, 373,326]  # P5/32# 0-P1/2
# 1-P2/4
# 2-P3/8
# 3-P4/16
# 4-P5/32# YOLOv5 v6.0 backbone
backbone:# [from, number, module, args][[-1, 1, focalnet_tiny_srf, [False]], # 4[-1, 1, SPPF, [1024, 5]],  # 5]# YOLOv5 v6.0 head
head:[[-1, 1, Conv, [512, 1, 1]], # 6[-1, 1, nn.Upsample, [None, 2, 'nearest']], # 7[[-1, 3], 1, Concat, [1]],  # cat backbone P4 8[-1, 3, C3, [512, False]],  # 9[-1, 1, Conv, [256, 1, 1]], # 10[-1, 1, nn.Upsample, [None, 2, 'nearest']], # 11[[-1, 2], 1, Concat, [1]],  # cat backbone P3 12[-1, 3, C3, [256, False]],  # 13 (P3/8-small)[-1, 1, Conv, [256, 3, 2]], # 14[[-1, 10], 1, Concat, [1]],  # cat head P4 15[-1, 3, C3, [512, False]],  # 16 (P4/16-medium)[-1, 1, Conv, [512, 3, 2]], # 17[[-1, 5], 1, Concat, [1]],  # cat head P5 18[-1, 3, C3, [1024, False]],  # 19 (P5/32-large)[[13, 16, 19], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)]

本文来自互联网用户投稿，该文观点仅代表作者本人，不代表本站立场。本站仅提供信息存储空间服务，不拥有所有权，不承担相关法律责任。如若转载，请注明出处：http://www.mzph.cn/news/95804.shtml

如若内容造成侵权/违法违规/事实不符，请联系多彩编程网进行投诉反馈email:809451989@qq.com，一经查实，立即删除！

相关文章

计算机网络——计算机网络的性能指标（上）-速率、带宽、吞吐量、时延

计算机网络——计算机网络的性能指标（上）-速率、带宽、吞吐量、时延

目录 速率 比特 速率 例1 带宽 带宽在模拟信号系统中的意义 带宽在计算机网络中的意义 吞吐量 时延 发送时延 传播时延 处理时延 例2 例3 速率 了解速率之前&#xff0c;先详细了解一下比特&#xff1a; 比特 计算机中数据量的单位&#xff0c;也是信息论中信…
阅读更多...
剑指offer——JZ26 树的子结构 解题思路与具体代码【C++】

剑指offer——JZ26 树的子结构 解题思路与具体代码【C++】

一、题目描述与要求 树的子结构_牛客题霸_牛客网 (nowcoder.com) 题目描述 输入两棵二叉树A&#xff0c;B&#xff0c;判断B是不是A的子结构。&#xff08;我们约定空树不是任意一个树的子结构&#xff09; 假如给定A为{8,8,7,9,2,#,#,#,#,4,7}&#xff0c;B为{8,9,2}&…
阅读更多...
cad图纸如何防止盗图（一个的制造设计型企业如何保护设计图纸文件）

cad图纸如何防止盗图（一个的制造设计型企业如何保护设计图纸文件）

在现代企业中&#xff0c;设计图纸是公司的重要知识产权&#xff0c;关系到公司的核心竞争力。然而&#xff0c;随着技术的发展&#xff0c;员工获取和传播设计图纸的途径越来越多样化&#xff0c;如何有效地防止员工复制设计图纸成为了企业管理的一大挑战。本文将从技术、管理…
阅读更多...
计算机竞赛 题目：基于python的验证码识别 - 机器视觉 验证码识别

计算机竞赛 题目：基于python的验证码识别 - 机器视觉 验证码识别

文章目录 0 前言1 项目简介2 验证码识别步骤2.1 灰度处理&二值化2.2 去除边框2.3 图像降噪2.4 字符切割2.5 识别 3 基于tensorflow的验证码识别3.1 数据集3.2 基于tf的神经网络训练代码 4 最后 0 前言 &#x1f525; 优质竞赛项目系列&#xff0c;今天要分享的是 基于pyt…
阅读更多...
NEFU数字图像处理（1）绪论

NEFU数字图像处理（1）绪论

一、简介 1.1什么是数字图像 图像是三维场景在二维平面上的影像。根据其存储方式和表现形式&#xff0c;可以将图像分为模拟图像和数字图像两大类 图像处理方法&#xff1a;光学方法、电子学方法 模拟图像&#xff1a;连续的图像数字图像&#xff1a;通过对时间上和数值上连续…
阅读更多...
阿里云ECS和轻量服务器有什么区别？

阿里云ECS和轻量服务器有什么区别？

阿里云服务器ECS和轻量应用服务器有什么区别&#xff1f;轻量和ECS优缺点对比&#xff0c;云服务器ECS是明星级云产品&#xff0c;适合企业专业级的使用场景&#xff0c;轻量应用服务器是在ECS的基础上推出的轻量级云服务器&#xff0c;适合个人开发者单机应用访问量不高的网站…
阅读更多...
二叉树的初步认识

二叉树的初步认识

二叉树是这么一种树状结构&#xff1a;每个节点最多有两个孩子&#xff0c;左孩子和右孩子 重要的二叉树结构 完全二叉树&#xff08;complete binary tree&#xff09;是一种二叉树结构&#xff0c;除最后一层以外&#xff0c;每一层都必须填满&#xff0c;填充时要遵从先左后…
阅读更多...
[Spring] @Bean 修饰方法时如何注入参数

[Spring] @Bean 修饰方法时如何注入参数

目录 一、Bean 的简单使用 1、正常情况 2、问题提出 二、解决方案 1、Qualifier 2、直接写方法名 三、特殊情况 1、DataSource 一、Bean 的简单使用 在开发中&#xff0c;基于 XML 文件配置 Bean 对象的做法非常繁琐且不好维护&#xff0c;因此绝大部分情况下都是使用…
阅读更多...
【新的小主机】向日葵远程控制ubuntu

【新的小主机】向日葵远程控制ubuntu

向日葵远程控制ubuntu 一、简介二、问题及解决方法2.1 向日葵远程连接Ubuntu22主机黑屏&#xff1f;2.2 Ubuntu如何向日葵开机自启&#xff1f;2.3 无显示器情况下&#xff0c;windows远程桌面连接Ubuntu? 三、美化桌面3.1 安装/解压3.2 设置3.3 右上角显示实时网速 四、安装d…
阅读更多...
运营人必备这个微信运营工具

运营人必备这个微信运营工具

微信管理系统CRM在各行各业都有应用的场景---IT互联网、制造业、商业服务、金融投资、教育培训、房产家装、电商、政务等20行业领域均得到广泛应用。 微信CRM管理系统的主要功能&#xff1a; 多个微信号聚合聊天&#xff1a;解决多个微信来回切换&#xff0c;换着手着手机的麻烦…
阅读更多...
Spring MVC程序开发（JavaEE进阶系列3）

Spring MVC程序开发（JavaEE进阶系列3）

目录 前言&#xff1a; 1.什么是Spring MVC 1.1MVC的定义 1.2MVC和Spring MVC的关系 1.3为什么要学习Spring MVC 2.Spring MVC项目的创建 3.Spring MVC框架的使用 3.1连接的功能 3.1.1RequestMapping 3.1.2GetMapping 3.1.3PostMapping 3.2获取参数的功能 3.2.1获…
阅读更多...
高通camx开源部分学习简介

高通camx开源部分学习简介

camera整体框架 sensor 上电&#xff0c;通过 MIPI协议传输&#xff0c;得到RAW图像数据。RAW图像数据经过ISP处理&#xff0c;得到YUV图像数据。YUV图像数据再经过DMA传输到DDR内存中&#xff0c;DDR内存也就是上图中标识的HOST。每个厂家的 ISP原理和功能大致相同&#xff0c…
阅读更多...
【亲测有效】C盘容量满了，给C盘扩容！！！

【亲测有效】C盘容量满了，给C盘扩容！！！

前言 相信有很多小伙伴用自己电脑的时候明明不往C盘装东西&#xff0c;但是C盘还是慢慢的变红了&#xff0c;我也是因为C盘满了而备受困扰。又不知道如何解决或者怕自己鼓捣着磁盘数据没了。闲来无事&#xff0c;我查了一些资料&#xff0c;终于将我的C盘容量扩充了且数据保存…
阅读更多...
Hive 【Hive（七）窗口函数练习】

Hive 【Hive（七）窗口函数练习】

窗口函数案例 数据准备 1&#xff09;建表语句 create table order_info (order_id string, --订单iduser_id string, -- 用户iduser_name string, -- 用户姓名order_date string, -- 下单日期order_amount int -- 订单金额 ); 2&#xff09;装载语句 i…
阅读更多...
一文搞懂APT攻击

一文搞懂APT攻击

APT攻击 1. 基本概念2. APT的攻击阶段3. APT的典型案例参考 1. 基本概念 高级持续性威胁&#xff08;APT&#xff0c;Advanced Persistent Threat&#xff09;&#xff0c;又叫高级长期威胁&#xff0c;是一种复杂的、持续的网络攻击&#xff0c;包含高级、长期、威胁三个要素…
阅读更多...
超声波气象站——环境监测领域强大助手

超声波气象站——环境监测领域强大助手

超声波气象站是环境监测领域的一位强大助手&#xff0c;超声波气象站是一种综合型的气象设备&#xff0c;精巧而全面&#xff0c;满足人们对环境状况的深入了解和精准把握。 首先&#xff0c;超声波气象站的传感器部分&#xff0c;是它的核心组成部分&#xff0c;这位“感知者”…
阅读更多...
PHP 行事准则：allow_url_fopen 与 allow_url_include

PHP 行事准则：allow_url_fopen 与 allow_url_include

文章目录 参考环境allow_url_fopenallow_url_fopen 配置项操作远程文件file 协议 allow_url_includeallow_url_include 配置项 allow_url_include 与 allow_url_fopen区别联系默认配置配置项关闭所导致异常运行时配置ini_set()限制 参考 项目描述搜索引擎Bing、GoogleAI 大模型…
阅读更多...
Elasticsearch数据操作原理

Elasticsearch数据操作原理

Elasticsearch 是一个开源的、基于 Lucene 的分布式搜索和分析引擎&#xff0c;设计用于云计算环境中&#xff0c;能够实现实时的、可扩展的搜索、分析和探索全文和结构化数据。它具有高度的可扩展性&#xff0c;可以在短时间内搜索和分析大量数据。 Elasticsearch 不仅仅是一个…
阅读更多...
Linux 本地 Docker Registry本地镜像仓库远程连接

Linux 本地 Docker Registry本地镜像仓库远程连接

Linux 本地 Docker Registry本地镜像仓库远程连接 Docker Registry 本地镜像仓库,简单几步结合cpolar内网穿透工具实现远程pull or push (拉取和推送)镜像,不受本地局域网限制&#xff01; 1. 部署Docker Registry 使用官网安装方式,docker命令一键启动,该命令启动一个regis…
阅读更多...
JVM-满老师

JVM-满老师

JVM 前言程序计数器&#xff0c;栈&#xff0c;虚拟机栈&#xff1a;本地方法栈&#xff1a;堆&#xff0c;方法区&#xff1a;堆内存溢出方法区运行时常量池 垃圾回收垃圾回收算法分代回收 前言 JVM 可以理解的代码就叫做字节码&#xff08;即扩展名为 .class 的文件&#xff…
阅读更多...
推荐文章
最新文章

Copyright @ 2022~2023