YOLO11 改进 – 主干网络_ EfficientViT 高效视觉Transformer：硬件感知架构平衡全局感受野与局部细节，提升模型适应性
前言
本文介绍了高速度视觉变换器EfficientViT在YOLOv11中的结合应用。现有视觉变换器计算成本高，不适合实时应用，EfficientViT通过采用夹心布局的内存高效模块和级联组注意力操作，减少了多头自注意力中的计算冗余，提高了内存效率和通道间通信。我们将EfficientViT集成进YOLOv11，通过一系列代码修改与配置，经实验验证取得了一定的效果，在速度和准确性之间达成了较好的平衡。
文章目录： YOLOv11改进大全：卷积层、轻量化、注意力机制、损失函数、Backbone、SPPF、Neck、检测头全方位优化汇总
专栏链接: YOLOv11改进专栏
文章目录
[TOC]
介绍
摘要
视觉变换器凭借其卓越的模型表征能力已在计算机视觉领域取得显著成功，然而其优异的性能表现往往伴随着高昂的计算开销，限制了其在实时应用场景中的部署。本文提出了一种高效视觉变换器系列架构——EfficientViT，旨在解决现有变换器模型的计算效率瓶颈。通过深入分析发现，当前变换器模型的速度主要受限于内存效率低下的操作，特别是在多头自注意力机制（MHSA）中的张量重塑和逐元素运算过程。为此，我们设计了一种新颖的夹心式布局模块，该模块在高效前馈神经网络（FFN）层之间嵌入单一内存受限的MHSA层，不仅显著提升了内存利用效率，同时增强了通道间的信息交互能力。进一步研究发现，不同注意力头之间的注意力图存在高度相似性，导致计算冗余问题。针对此问题，我们提出了级联组注意力模块，采用不同分割的完整特征输入至各注意力头，有效降低了计算复杂度并提升了注意力机制的多样性。综合实验结果表明，EfficientViT在推理速度与模型精度之间实现了优异平衡，性能超越现有高效模型。具体而言，EfficientViT-M5在精度上超越MobileNetV3-Large达1.9个百分点，同时在Nvidia V100 GPU和Intel Xeon CPU上的吞吐量分别提升40.4%和45.2%；相较于近期高效模型MobileViT-XXS，EfficientViT-M2精度提升1.8%，GPU/CPU运行速度分别加快5.8倍和3.7倍，ONNX格式转换后速度提升达7.4倍。相关代码与模型均已开源提供。
文章链接
论文地址： 论文地址
代码地址： 代码地址
基本原理
EfficientViT 是一系列高速度的视觉变换器。它采用了一种新的内存高效模块，采用夹心布局，并结合了高效的级联组注意力操作，从而减少了注意力计算的冗余。
YOLO11引入代码
在根目录下的 ultralytics/nn/ 目录，新建一个 backbone 目录，然后新建一个以 EfficientViT 为文件名的py文件， 把代码拷贝进去。
# --------------------------------------------------------
# EfficientViT Model Architecture for Downstream Tasks
# Copyright (c) 2022 Microsoft
# Written by: Xinyu Liu
# --------------------------------------------------------
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.utils.checkpoint as checkpoint
import itertools
from timm.models.layers import SqueezeExcite
import numpy as np
import itertools
class Conv2d_BN(torch.nn.Sequential):
def __init__(self, a, b, ks=1, stride=1, pad=0, dilation=1,
groups=1, bn_weight_init=1, resolution=-10000):
super().__init__()
self.add_module('c', torch.nn.Conv2d(
a, b, ks, stride, pad, dilation, groups, bias=False))
self.add_module('bn', torch.nn.BatchNorm2d(b))
torch.nn.init.constant_(self.bn.weight, bn_weight_init)
torch.nn.init.constant_(self.bn.bias, 0)
@torch.no_grad()
def switch_to_deploy(self):
c, bn = self._modules.values()
w = bn.weight / (bn.running_var + bn.eps)**0.5
w = c.weight * w[:, None, None, None]
b = bn.bias - bn.running_mean * bn.weight / \
(bn.running_var + bn.eps)**0.5
m = torch.nn.Conv2d(w.size(1) * self.c.groups, w.size(
0), w.shape[2:], stride=self.c.stride, padding=self.c.padding, dilation=self.c.dilation, groups=self.c.groups)
m.weight.data.copy_(w)
m.bias.data.copy_(b)
return m
def replace_batchnorm(net):
for child_name, child in net.named_children():
if hasattr(child, 'fuse'):
setattr(net, child_name, child.fuse())
elif isinstance(child, torch.nn.BatchNorm2d):
setattr(net, child_name, torch.nn.Identity())
else:
replace_batchnorm(child)
class PatchMerging(torch.nn.Module):
def __init__(self, dim, out_dim, input_resolution):
super().__init__()
hid_dim = int(dim * 4)
self.conv1 = Conv2d_BN(dim, hid_dim, 1, 1, 0, resolution=input_resolution)
self.act = torch.nn.ReLU()
self.conv2 = Conv2d_BN(hid_dim, hid_dim, 3, 2, 1, groups=hid_dim, resolution=input_resolution)
self.se = SqueezeExcite(hid_dim, .25)
self.conv3 = Conv2d_BN(hid_dim, out_dim, 1, 1, 0, resolution=input_resolution // 2)
def forward(self, x):
x = self.conv3(self.se(self.act(self.conv2(self.act(self.conv1(x))))))
return x
class Residual(torch.nn.Module):
def __init__(self, m, drop=0.):
super().__init__()
self.m = m
self.drop = drop
def forward(self, x):
if self.training and self.drop > 0:
return x + self.m(x) * torch.rand(x.size(0), 1, 1, 1,
device=x.device).ge_(self.drop).div(1 - self.drop).detach()
else:
return x + self.m(x)
class FFN(torch.nn.Module):
def __init__(self, ed, h, resolution):
super().__init__()
self.pw1 = Conv2d_BN(ed, h, resolution=resolution)
self.act = torch.nn.ReLU()
self.pw2 = Conv2d_BN(h, ed, bn_weight_init=0, resolution=resolution)
def forward(self, x):
x = self.pw2(self.act(self.pw1(x)))
return x
class CascadedGroupAttention(torch.nn.Module):
r""" Cascaded Group Attention.
Args:
dim (int): Number of input channels.
key_dim (int): The dimension for query and key.
num_heads (int): Number of attention heads.
attn_ratio (int): Multiplier for the query dim for value dimension.
resolution (int): Input resolution, correspond to the window size.
kernels (List[int]): The kernel size of the dw conv on query.
"""
def __init__(self, dim, key_dim, num_heads=8,
attn_ratio=4,
resolution=14,
kernels=[5, 5, 5, 5],):
super().__init__()
self.num_heads = num_heads
self.scale = key_dim ** -0.5
self.key_dim = key_dim
self.d = int(attn_ratio * key_dim)
self.attn_ratio = attn_ratio
qkvs = []
dws = []
for i in range(num_heads):
qkvs.append(Conv2d_BN(dim // (num_heads), self.key_dim * 2 + self.d, resolution=resolution))
dws.append(Conv2d_BN(self.key_dim, self.key_dim, kernels[i], 1, kernels[i]//2, groups=self.key_dim, resolution=resolution))
self.qkvs = torch.nn.ModuleList(qkvs)
self.dws = torch.nn.ModuleList(dws)
self.proj = torch.nn.Sequential(torch.nn.ReLU(), Conv2d_BN(
self.d * num_heads, dim, bn_weight_init=0, resolution=resolution))
points = list(itertools.product(range(resolution), range(resolution)))
N = len(points)
attention_offsets = {}
idxs = []
for p1 in points:
for p2 in points:
offset = (abs(p1[0] - p2[0]), abs(p1[1] - p2[1]))
if offset not in attention_offsets:
attention_offsets[offset] = len(attention_offsets)
idxs.append(attention_offsets[offset])
self.attention_biases = torch.nn.Parameter(
torch.zeros(num_heads, len(attention_offsets)))
self.register_buffer('attention_bias_idxs',
torch.LongTensor(idxs).view(N, N))
@torch.no_grad()
def train(self, mode=True):
super().train(mode)
if mode and hasattr(self, 'ab'):
del self.ab
else:
self.ab = self.attention_biases[:, self.attention_bias_idxs]
def forward(self, x): # x (B,C,H,W)
B, C, H, W = x.shape
trainingab = self.attention_biases[:, self.attention_bias_idxs]
feats_in = x.chunk(len(self.qkvs), dim=1)
feats_out = []
feat = feats_in[0]
for i, qkv in enumerate(self.qkvs):
if i > 0: # add the previous output to the input
feat = feat + feats_in[i]
feat = qkv(feat)
q, k, v = feat.view(B, -1, H, W).split([self.key_dim, self.key_dim, self.d], dim=1) # B, C/h, H, W
q = self.dws[i](q)
q, k, v = q.flatten(2), k.flatten(2), v.flatten(2) # B, C/h, N
attn = (
(q.transpose(-2, -1) @ k) * self.scale
+
(trainingab[i] if self.training else self.ab[i])
)
attn = attn.softmax(dim=-1) # BNN
feat = (v @ attn.transpose(-2, -1)).view(B, self.d, H, W) # BCHW
feats_out.append(feat)
x = self.proj(torch.cat(feats_out, 1))
return x
class LocalWindowAttention(torch.nn.Module):
r""" Local Window Attention.
Args:
dim (int): Number of input channels.
key_dim (int): The dimension for query and key.
num_heads (int): Number of attention heads.
attn_ratio (int): Multiplier for the query dim for value dimension.
resolution (int): Input resolution.
window_resolution (int): Local window resolution.
kernels (List[int]): The kernel size of the dw conv on query.
"""
def __init__(self, dim, key_dim, num_heads=8,
attn_ratio=4,
resolution=14,
window_resolution=7,
kernels=[5, 5, 5, 5],):
super().__init__()
self.dim = dim
self.num_heads = num_heads
self.resolution = resolution
assert window_resolution > 0, 'window_size must be greater than 0'
self.window_resolution = window_resolution
self.attn = CascadedGroupAttention(dim, key_dim, num_heads,
attn_ratio=attn_ratio,
resolution=window_resolution,
kernels=kernels,)
def forward(self, x):
B, C, H, W = x.shape
if H <= self.window_resolution and W <= self.window_resolution:
x = self.attn(x)
else:
x = x.permute(0, 2, 3, 1)
pad_b = (self.window_resolution - H %
self.window_resolution) % self.window_resolution
pad_r = (self.window_resolution - W %
self.window_resolution) % self.window_resolution
padding = pad_b > 0 or pad_r > 0
if padding:
x = torch.nn.functional.pad(x, (0, 0, 0, pad_r, 0, pad_b))
pH, pW = H + pad_b, W + pad_r
nH = pH // self.window_resolution
nW = pW // self.window_resolution
# window partition, BHWC -> B(nHh)(nWw)C -> BnHnWhwC -> (BnHnW)hwC -> (BnHnW)Chw
x = x.view(B, nH, self.window_resolution, nW, self.window_resolution, C).transpose(2, 3).reshape(
B * nH * nW, self.window_resolution, self.window_resolution, C
).permute(0, 3, 1, 2)
x = self.attn(x)
# window reverse, (BnHnW)Chw -> (BnHnW)hwC -> BnHnWhwC -> B(nHh)(nWw)C -> BHWC
x = x.permute(0, 2, 3, 1).view(B, nH, nW, self.window_resolution, self.window_resolution,
C).transpose(2, 3).reshape(B, pH, pW, C)
if padding:
x = x[:, :H, :W].contiguous()
x = x.permute(0, 3, 1, 2)
return x
class EfficientViTBlock(torch.nn.Module):
""" A basic EfficientViT building block.
Args:
type (str): Type for token mixer. Default: 's' for self-attention.
ed (int): Number of input channels.
kd (int): Dimension for query and key in the token mixer.
nh (int): Number of attention heads.
ar (int): Multiplier for the query dim for value dimension.
resolution (int): Input resolution.
window_resolution (int): Local window resolution.
kernels (List[int]): The kernel size of the dw conv on query.
"""
def __init__(self, type,
ed, kd, nh=8,
ar=4,
resolution=14,
window_resolution=7,
kernels=[5, 5, 5, 5],):
super().__init__()
self.dw0 = Residual(Conv2d_BN(ed, ed, 3, 1, 1, groups=ed, bn_weight_init=0., resolution=resolution))
self.ffn0 = Residual(FFN(ed, int(ed * 2), resolution))
if type == 's':
self.mixer = Residual(LocalWindowAttention(ed, kd, nh, attn_ratio=ar, \
resolution=resolution, window_resolution=window_resolution, kernels=kernels))
self.dw1 = Residual(Conv2d_BN(ed, ed, 3, 1, 1, groups=ed, bn_weight_init=0., resolution=resolution))
self.ffn1 = Residual(FFN(ed, int(ed * 2), resolution))
def forward(self, x):
return self.ffn1(self.dw1(self.mixer(self.ffn0(self.dw0(x)))))
class EfficientViT(torch.nn.Module):
def __init__(self, img_size=400,
patch_size=16,
frozen_stages=0,
in_chans=3,
stages=['s', 's', 's'],
embed_dim=[64, 128, 192],
key_dim=[16, 16, 16],
depth=[1, 2, 3],
num_heads=[4, 4, 4],
window_size=[7, 7, 7],
kernels=[5, 5, 5, 5],
down_ops=[['subsample', 2], ['subsample', 2], ['']],
pretrained=None,
distillation=False,):
super().__init__()
resolution = img_size
self.patch_embed = torch.nn.Sequential(Conv2d_BN(in_chans, embed_dim[0] // 8, 3, 2, 1, resolution=resolution), torch.nn.ReLU(),
Conv2d_BN(embed_dim[0] // 8, embed_dim[0] // 4, 3, 2, 1, resolution=resolution // 2), torch.nn.ReLU(),
Conv2d_BN(embed_dim[0] // 4, embed_dim[0] // 2, 3, 2, 1, resolution=resolution // 4), torch.nn.ReLU(),
Conv2d_BN(embed_dim[0] // 2, embed_dim[0], 3, 1, 1, resolution=resolution // 8))
resolution = img_size // patch_size
attn_ratio = [embed_dim[i] / (key_dim[i] * num_heads[i]) for i in range(len(embed_dim))]
self.blocks1 = []
self.blocks2 = []
self.blocks3 = []
for i, (stg, ed, kd, dpth, nh, ar, wd, do) in enumerate(
zip(stages, embed_dim, key_dim, depth, num_heads, attn_ratio, window_size, down_ops)):
for d in range(dpth):
eval('self.blocks' + str(i+1)).append(EfficientViTBlock(stg, ed, kd, nh, ar, resolution, wd, kernels))
if do[0] == 'subsample':
#('Subsample' stride)
blk = eval('self.blocks' + str(i+2))
resolution_ = (resolution - 1) // do[1] + 1
blk.append(torch.nn.Sequential(Residual(Conv2d_BN(embed_dim[i], embed_dim[i], 3, 1, 1, groups=embed_dim[i], resolution=resolution)),
Residual(FFN(embed_dim[i], int(embed_dim[i] * 2), resolution)),))
blk.append(PatchMerging(*embed_dim[i:i + 2], resolution))
resolution = resolution_
blk.append(torch.nn.Sequential(Residual(Conv2d_BN(embed_dim[i + 1], embed_dim[i + 1], 3, 1, 1, groups=embed_dim[i + 1], resolution=resolution)),
Residual(FFN(embed_dim[i + 1], int(embed_dim[i + 1] * 2), resolution)),))
self.blocks1 = torch.nn.Sequential(*self.blocks1)
self.blocks2 = torch.nn.Sequential(*self.blocks2)
self.blocks3 = torch.nn.Sequential(*self.blocks3)
self.channel = [i.size(1) for i in self.forward(torch.randn(1, 3, 640, 640))]
def forward(self, x):
outs = []
x = self.patch_embed(x)
x = self.blocks1(x)
outs.append(x)
x = self.blocks2(x)
outs.append(x)
x = self.blocks3(x)
outs.append(x)
return outs
EfficientViT_m0 = {
'img_size': 224,
'patch_size': 16,
'embed_dim': [64, 128, 192],
'depth': [1, 2, 3],
'num_heads': [4, 4, 4],
'window_size': [7, 7, 7],
'kernels': [7, 5, 3, 3],
}
EfficientViT_m1 = {
'img_size': 224,
'patch_size': 16,
'embed_dim': [128, 144, 192],
'depth': [1, 2, 3],
'num_heads': [2, 3, 3],
'window_size': [7, 7, 7],
'kernels': [7, 5, 3, 3],
}
EfficientViT_m2 = {
'img_size': 224,
'patch_size': 16,
'embed_dim': [128, 192, 224],
'depth': [1, 2, 3],
'num_heads': [4, 3, 2],
'window_size': [7, 7, 7],
'kernels': [7, 5, 3, 3],
}
EfficientViT_m3 = {
'img_size': 224,
'patch_size': 16,
'embed_dim': [128, 240, 320],
'depth': [1, 2, 3],
'num_heads': [4, 3, 4],
'window_size': [7, 7, 7],
'kernels': [5, 5, 5, 5],
}
EfficientViT_m4 = {
'img_size': 224,
'patch_size': 16,
'embed_dim': [128, 256, 384],
'depth': [1, 2, 3],
'num_heads': [4, 4, 4],
'window_size': [7, 7, 7],
'kernels': [7, 5, 3, 3],
}
EfficientViT_m5 = {
'img_size': 224,
'patch_size': 16,
'embed_dim': [192, 288, 384],
'depth': [1, 3, 4],
'num_heads': [3, 3, 4],
'window_size': [7, 7, 7],
'kernels': [7, 5, 3, 3],
}
def EfficientViT_M0(pretrained='', frozen_stages=0, distillation=False, fuse=False, pretrained_cfg=None, model_cfg=EfficientViT_m0):
model = EfficientViT(frozen_stages=frozen_stages, distillation=distillation, pretrained=pretrained, **model_cfg)
if pretrained:
model.load_state_dict(update_weight(model.state_dict(), torch.load(pretrained)['model']))
if fuse:
replace_batchnorm(model)
return model
def EfficientViT_M1(pretrained='', frozen_stages=0, distillation=False, fuse=False, pretrained_cfg=None, model_cfg=EfficientViT_m1):
model = EfficientViT(frozen_stages=frozen_stages, distillation=distillation, pretrained=pretrained, **model_cfg)
if pretrained:
model.load_state_dict(update_weight(model.state_dict(), torch.load(pretrained)['model']))
if fuse:
replace_batchnorm(model)
return model
def EfficientViT_M2(pretrained='', frozen_stages=0, distillation=False, fuse=False, pretrained_cfg=None, model_cfg=EfficientViT_m2):
model = EfficientViT(frozen_stages=frozen_stages, distillation=distillation, pretrained=pretrained, **model_cfg)
if pretrained:
model.load_state_dict(update_weight(model.state_dict(), torch.load(pretrained)['model']))
if fuse:
replace_batchnorm(model)
return model
def EfficientViT_M3(pretrained='', frozen_stages=0, distillation=False, fuse=False, pretrained_cfg=None, model_cfg=EfficientViT_m3):
model = EfficientViT(frozen_stages=frozen_stages, distillation=distillation, pretrained=pretrained, **model_cfg)
if pretrained:
model.load_state_dict(update_weight(model.state_dict(), torch.load(pretrained)['model']))
if fuse:
replace_batchnorm(model)
return model
def EfficientViT_M4(pretrained='', frozen_stages=0, distillation=False, fuse=False, pretrained_cfg=None, model_cfg=EfficientViT_m4):
model = EfficientViT(frozen_stages=frozen_stages, distillation=distillation, pretrained=pretrained, **model_cfg)
if pretrained:
model.load_state_dict(update_weight(model.state_dict(), torch.load(pretrained)['model']))
if fuse:
replace_batchnorm(model)
return model
def EfficientViT_M5(pretrained='', frozen_stages=0, distillation=False, fuse=False, pretrained_cfg=None, model_cfg=EfficientViT_m5):
model = EfficientViT(frozen_stages=frozen_stages, distillation=distillation, pretrained=pretrained, **model_cfg)
if pretrained:
model.load_state_dict(update_weight(model.state_dict(), torch.load(pretrained)['model']))
if fuse:
replace_batchnorm(model)
return model
def update_weight(model_dict, weight_dict):
idx, temp_dict = 0, {}
for k, v in weight_dict.items():
# k = k[9:]
if k in model_dict.keys() and np.shape(model_dict[k]) == np.shape(v):
temp_dict[k] = v
idx += 1
model_dict.update(temp_dict)
print(f'loading weights... {idx}/{len(model_dict)} items')
return model_dict
if __name__ == '__main__':
model = EfficientViT_M0('efficientvit_m0.pth')
inputs = torch.randn((1, 3, 640, 640))
res = model(inputs)
for i in res:
print(i.size())tasks注册
在 ultralytics/nn/tasks.py 中进行如下操作：
步骤1:
from ultralytics.nn.backbone.EfficientViT import EfficientViT_M0, EfficientViT_M1, EfficientViT_M2, EfficientViT_M3, EfficientViT_M4, EfficientViT_M5
步骤2
修改 def parse_model(d, ch, verbose=True) :
elif m in {EfficientViT_M0, EfficientViT_M1, EfficientViT_M2, EfficientViT_M3, EfficientViT_M4, EfficientViT_M5}:
m = m(*args)
c2 = m.channel 增加代码1
在 def parse_model(d, ch, verbose=True) :
搜索下面的代码 for i, (f, n, m, args) in enumerate(d["backbone"] + d["head"]) ，增加 is_backbone = False 和 t = m
is_backbone = False
for i, (f, n, m, args) in enumerate(d["backbone"] + d["head"]): # from, number, module, args
t = m
m = getattr(torch.nn, m[3:]) if "nn." in m else globals()[m] # get module修改代码
修改 def parse_model(d, ch, verbose=True) 中的：
# m_ = nn.Sequential(*(m(*args) for _ in range(n))) if n > 1 else m(*args) # module
# t = str(m)[8:-2].replace("__main__.", "") # module type
# m.np = sum(x.numel() for x in m_.parameters()) # number params
# m_.i, m_.f, m_.type = i, f, t # attach index, 'from' index, type
# if verbose:
# LOGGER.info(f"{i:>3}{str(f):>20}{n_:>3}{m.np:10.0f} {t:<45}{str(args):<30}") # print
# save.extend(x % i for x in ([f] if isinstance(f, int) else f) if x != -1) # append to savelist
# layers.append(m_)
# if i == 0:
# ch = []
# ch.append(c2)修改为
if isinstance(c2, list) :
is_backbone = True
m_ = m
m_.backbone = True
else:
m_ = nn.Sequential(*(m(*args) for _ in range(n))) if n > 1 else m(*args) # module
t = str(m)[8:-2].replace('__main__.', '') # module type
m_.np = sum(x.numel() for x in m_.parameters()) # number params
m_.i, m_.f, m_.type = i + 4 if is_backbone else i, f, t # attach index, 'from' index, type
if verbose:
LOGGER.info(f"{i:>3}{str(f):>20}{n_:>3}{m_.np:10.0f} {t:<45}{str(args):<30}") # print
save.extend(x % (i + 4 if is_backbone else i) for x in ([f] if isinstance(f, int) else f) if x != -1) # append to savelist
layers.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)替换_predict_once方法
把 _predict_once 替换为下面的代码：
def _predict_once(self, x, profile=False, visualize=False, embed=None):
y, dt, embeddings = [], [], [] # outputs
for idx, m in enumerate(self.model):
if m.f != -1: # if not from previous layer
x = y[m.f] if isinstance(m.f, int) else [x if j == -1 else y[j] for j in m.f] # from earlier layers
if 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) # run
y.append(x if m.i in self.save else None) # save output
if visualize:
feature_visualization(x, m.type, m.i, save_dir=visualize)
if embed and m.i in embed:
embeddings.append(nn.functional.adaptive_avg_pool2d(x, (1, 1)).squeeze(-1).squeeze(-1)) # flatten
if m.i == max(embed):
return torch.unbind(torch.cat(embeddings, 1), dim=0)
return x配置yolov11-EfficientViT.yaml
ultralytics/cfg/models/11/yolov11-EfficientViT.yaml
# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLO11 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=yolo11n.yaml' will call yolo11.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.50, 0.25, 1024] # summary: 319 layers, 2624080 parameters, 2624064 gradients, 6.6 GFLOPs
s: [0.50, 0.50, 1024] # summary: 319 layers, 9458752 parameters, 9458736 gradients, 21.7 GFLOPs
m: [0.50, 1.00, 512] # summary: 409 layers, 20114688 parameters, 20114672 gradients, 68.5 GFLOPs
l: [1.00, 1.00, 512] # summary: 631 layers, 25372160 parameters, 25372144 gradients, 87.6 GFLOPs
x: [1.00, 1.50, 512] # summary: 631 layers, 56966176 parameters, 56966160 gradients, 196.0 GFLOPs
# YOLO11n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, EfficientViT_M0, []] # 4 可选： EfficientViT_M0, EfficientViT_M1, EfficientViT_M2, EfficientViT_M3, EfficientViT_M4, EfficientViT_M5
- [-1, 1, SPPF, [1024, 5]] # 5
- [-1, 2, C2PSA, [1024]] # 6
# YOLO11n head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 3], 1, Concat, [1]] # cat backbone P4
- [-1, 2, C3k2, [512, False]] # 9
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 2], 1, Concat, [1]] # cat backbone P3
- [-1, 2, C3k2, [256, False]] # 12 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 9], 1, Concat, [1]] # cat head P4
- [-1, 2, C3k2, [512, False]] # 15 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 6], 1, Concat, [1]] # cat head P5
- [-1, 2, C3k2, [1024, True]] # 18 (P5/32-large)
- [[12, 15, 18], 1, Detect, [nc]] # Detect(P3, P4, P5)实验
脚本
import warnings
warnings.filterwarnings('ignore')
from ultralytics import YOLO
if __name__ == '__main__':
# 修改为自己的配置文件地址
model = YOLO('/root/ultralytics-main/ultralytics/cfg/models/11/yolov11-EfficientViT.yaml')
# 修改为自己的数据集地址
model.train(data='/root/ultralytics-main/ultralytics/cfg/datasets/coco8.yaml',
cache=False,
imgsz=640,
epochs=10,
single_cls=False, # 是否是单类别检测
batch=8,
close_mosaic=10,
workers=0,
optimizer='SGD',
amp=True,
project='runs/train',
name='EfficientViT',
)
结果
版权声明：
作者：魔改工程师
链接：https://www.sylblog.xin/archives/320
文章版权归作者所有，未经允许请勿转载。
THE END
