爆改yolov8|AIFI (尺度内特征交互）助力YOLOv8 ,轻量化模型

不想敲代码！！！

已于 2024-08-29 09:47:11 修改

阅读量177

点赞数 1

分类专栏：爆改yolov8，即插即用文章标签： YOLO yolov8 目标检测 python pytorch

于 2024-08-29 09:44:58 首次发布

本文链接：https://blog.csdn.net/weixin_43986124/article/details/141668659

版权

爆改yolov8，即插即用专栏收录该内容

26 篇文章 2 订阅

订阅专栏

1，本文介绍

AIFI模块（Adaptive Information Fusion Integration Module）是一种旨在提升神经网络处理复杂任务能力的技术模块。其主要目的是通过灵活的特征融合方法来优化信息处理和任务表现。

核心特点：

自适应信息融合：AIFI模块能够根据输入数据和任务需求，动态调整特征融合的策略。这种自适应机制使得网络能够更有效地结合来自不同来源的信息，改善对复杂数据的理解和处理能力。
多模态融合：该模块设计用于处理多模态数据，通过有效融合来自不同模态的信息（如图像、文本、音频），提升模型对多种类型数据的综合处理能力。
增强模型表现：通过优化特征融合方式，AIFI模块能够显著提升模型在各种任务中的表现，包括分类、检测、生成等。

应用场景：

计算机视觉：在多模态图像分析和多任务学习中，AIFI模块可以有效融合来自不同传感器或图像来源的信息。
自然语言处理：在处理结合文本和图像的任务时（如图文检索和视觉问答），AIFI模块能够提供更加丰富和准确的信息融合。
多模态学习：适用于需要整合不同类型数据（如视频分析结合音频和文本）的应用。

总的来说，AIFI模块通过自适应的信息融合方法，增强了模型的综合处理能力，使其在处理复杂和多模态数据时表现更加出色。

关于AIFI的详细介绍可以看论文：http://file///C:/Users/shaoqi.sun/Desktop/RT-DETR.pdf

本文将讲解如何将AIFI融合进yolov8

话不多说，上代码！

2，将AIFI融合进yolov8

2.1 步骤一

最新版本的yolov8已更新，AIFI在源码中位置为ultralytics/nn/modules/transformer.py，不用复制添加，

只需要复制下面的yaml文件运行即可


import torch
import torch.nn as nn
 
class TransformerEncoderLayer(nn.Module):
    """Defines a single layer of the transformer encoder."""
 
    def __init__(self, c1, cm=2048, num_heads=8, dropout=0.0, act=nn.GELU(), normalize_before=False):
        """Initialize the TransformerEncoderLayer with specified parameters."""
        super().__init__()
 
        self.ma = nn.MultiheadAttention(c1, num_heads, dropout=dropout, batch_first=True)
        # Implementation of Feedforward model
        self.fc1 = nn.Linear(c1, cm)
        self.fc2 = nn.Linear(cm, c1)
 
        self.norm1 = nn.LayerNorm(c1)
        self.norm2 = nn.LayerNorm(c1)
        self.dropout = nn.Dropout(dropout)
        self.dropout1 = nn.Dropout(dropout)
        self.dropout2 = nn.Dropout(dropout)
 
        self.act = act
        self.normalize_before = normalize_before
 
    @staticmethod
    def with_pos_embed(tensor, pos=None):
        """Add position embeddings to the tensor if provided."""
        return tensor if pos is None else tensor + pos
 
    def forward_post(self, src, src_mask=None, src_key_padding_mask=None, pos=None):
        """Performs forward pass with post-normalization."""
        q = k = self.with_pos_embed(src, pos)
        src2 = self.ma(q, k, value=src, attn_mask=src_mask, key_padding_mask=src_key_padding_mask)[0]
        src = src + self.dropout1(src2)
        src = self.norm1(src)
        src2 = self.fc2(self.dropout(self.act(self.fc1(src))))
        src = src + self.dropout2(src2)
        return self.norm2(src)
 
    def forward_pre(self, src, src_mask=None, src_key_padding_mask=None, pos=None):
        """Performs forward pass with pre-normalization."""
        src2 = self.norm1(src)
        q = k = self.with_pos_embed(src2, pos)
        src2 = self.ma(q, k, value=src2, attn_mask=src_mask, key_padding_mask=src_key_padding_mask)[0]
        src = src + self.dropout1(src2)
        src2 = self.norm2(src)
        src2 = self.fc2(self.dropout(self.act(self.fc1(src2))))
        return src + self.dropout2(src2)
 
    def forward(self, src, src_mask=None, src_key_padding_mask=None, pos=None):
        """Forward propagates the input through the encoder module."""
        if self.normalize_before:
            return self.forward_pre(src, src_mask, src_key_padding_mask, pos)
        return self.forward_post(src, src_mask, src_key_padding_mask, pos)
    
    
 
class AIFI(TransformerEncoderLayer):
    """Defines the AIFI transformer layer."""
 
    def __init__(self, c1, cm=2048, num_heads=8, dropout=0, act=nn.GELU(), normalize_before=False):
        """Initialize the AIFI instance with specified parameters."""
        super().__init__(c1, cm, num_heads, dropout, act, normalize_before)
 
    def forward(self, x):
        """Forward pass for the AIFI transformer layer."""
        c, h, w = x.shape[1:]
        pos_embed = self.build_2d_sincos_position_embedding(w, h, c)
        # Flatten [B, C, H, W] to [B, HxW, C]
        x = super().forward(x.flatten(2).permute(0, 2, 1), pos=pos_embed.to(device=x.device, dtype=x.dtype))
        return x.permute(0, 2, 1).view([-1, c, h, w]).contiguous()
 
    @staticmethod
    def build_2d_sincos_position_embedding(w, h, embed_dim=256, temperature=10000.0):
        """Builds 2D sine-cosine position embedding."""
        grid_w = torch.arange(int(w), dtype=torch.float32)
        grid_h = torch.arange(int(h), dtype=torch.float32)
        grid_w, grid_h = torch.meshgrid(grid_w, grid_h, indexing="ij")
        assert embed_dim % 4 == 0, "Embed dimension must be divisible by 4 for 2D sin-cos position embedding"
        pos_dim = embed_dim // 4
        omega = torch.arange(pos_dim, dtype=torch.float32) / pos_dim
        omega = 1.0 / (temperature**omega)
 
        out_w = grid_w.flatten()[..., None] @ omega[None]
        out_h = grid_h.flatten()[..., None] @ omega[None]
 
        return torch.cat([torch.sin(out_w), torch.cos(out_w), torch.sin(out_h), torch.cos(out_h)], 1)[None]

yaml文件

# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLOv8 object detection model with P3-P5 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect
 
# Parameters
nc: 80  # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
  # [depth, width, max_channels]
  n: [0.33, 0.25, 1024]  # YOLOv8n summary: 225 layers,  3157200 parameters,  3157184 gradients,   8.9 GFLOPs
  s: [0.33, 0.50, 1024]  # YOLOv8s summary: 225 layers, 11166560 parameters, 11166544 gradients,  28.8 GFLOPs
  m: [0.67, 0.75, 768]   # YOLOv8m summary: 295 layers, 25902640 parameters, 25902624 gradients,  79.3 GFLOPs
  l: [1.00, 1.00, 512]   # YOLOv8l summary: 365 layers, 43691520 parameters, 43691504 gradients, 165.7 GFLOPs
  x: [1.00, 1.25, 512]   # YOLOv8x summary: 365 layers, 68229648 parameters, 68229632 gradients, 258.5 GFLOPs
 
# YOLOv8.0n backbone
backbone:
  # [from, repeats, module, args]
  - [-1, 1, Conv, [64, 3, 2]]  # 0-P1/2
  - [-1, 1, Conv, [128, 3, 2]]  # 1-P2/4
  - [-1, 3, C2f, [128, True]]
  - [-1, 1, Conv, [256, 3, 2]]  # 3-P3/8
  - [-1, 6, C2f, [256, True]]
  - [-1, 1, Conv, [512, 3, 2]]  # 5-P4/16
  - [-1, 6, C2f, [512, True]]
  - [-1, 1, Conv, [1024, 3, 2]]  # 7-P5/32
  - [-1, 3, C2f, [1024, True]]
  - [-1, 1, AIFI, [1024, 8]]  # 9
 
# YOLOv8.0n head
head:
  - [-1, 1, nn.Upsample, [None, 2, 'nearest']]
  - [[-1, 6], 1, Concat, [1]]  # cat backbone P4
  - [-1, 3, C2f, [512]]  # 12
 
  - [-1, 1, nn.Upsample, [None, 2, 'nearest']]
  - [[-1, 4], 1, Concat, [1]]  # cat backbone P3
  - [-1, 3, C2f, [256]]  # 15 (P3/8-small)
 
  - [-1, 1, Conv, [256, 3, 2]]
  - [[-1, 12], 1, Concat, [1]]  # cat head P4
  - [-1, 3, C2f, [512]]  # 18 (P4/16-medium)
 
  - [-1, 1, Conv, [512, 3, 2]]
  - [[-1, 9], 1, Concat, [1]]  # cat head P5
  - [-1, 3, C2f, [1024]]  # 21 (P5/32-large)
 
  - [[15, 18, 21], 1, Detect, [nc]]  # Detect(P3, P4, P5)

不知不觉已经看完了哦，动动小手留个点赞收藏吧--_--