💡💡💡创新点：轻量化之王MobileNetV4 开源 | Top-1 精度 87%，手机推理速度 3.8ms，原地起飞！
MobileNetV4（MNv4），其特点是针对移动设备设计的通用高效架构。创新1）：引入了通用倒瓶颈（UIB）搜索块，这是一个统一且灵活的结构，它融合了倒瓶颈（IB）、ConvNext、前馈网络（FFN）以及一种新颖的额外深度可分（ExtraDW）变体；创新2）：一种优化的神经结构搜索(NAS)配方，提高了MNv4的搜索效率；创新3）：为了进一步提升准确度，引入了一种新颖的蒸馏技术。
💡💡💡如何跟YOLOv8结合：替代YOLOv8的backbone
收录
YOLOv8原创自研
💡💡💡全网独家首发创新（原创），适合paper ！！！
💡💡💡 2024年计算机视觉顶会创新点适用于Yolov5、Yolov7、Yolov8等各个Yolo系列，专栏文章提供每一步步骤和源码，轻松带你上手魔改网络 ！！！
💡💡💡重点：通过本专栏的阅读，后续你也可以设计魔改网络，在网络不同位置（Backbone、head、detect、loss等）进行魔改，实现创新！！！
1.原理介绍
论文： https://arxiv.org/pdf/2404.10518
摘要：我们介绍了最新一代的mobilenet，被称为MobileNetV4 (MNv4)，具有普遍有效的移动设备架构设计。在其核心，我们引入了通用倒瓶颈(UIB)搜索块，这是一个统一而灵活的结构，它融合了倒瓶颈(IB)， ConvNext，前馈网络(FFN)和一个新的Extra depth(引渡)变体。除了UIB之外，我们还推出了Mobile MQA，这是一款专为移动加速器量身定制的注意力块，可显著提高39%的速度。介绍了一种优化的神经结构搜索(NAS)配方，提高了MNv4的搜索效率。UIB, Mobile MQA和精致的NAS配方的集成产生了一套新的MNv4模型，这些模型在移动cpu, dsp, gpu以及专用加速器(如Apple Neural Engine和Google Pixel EdgeTPU)上大多是最优的，这是任何其他模型测试中没有发现的特征。最后，为了进一步提高精度，我们介绍了一种新的蒸馏技术。通过这种技术的增强，我们的MNv4-Hybrid-Large模型提供了87%的ImageNet-1K精度，Pixel 8 EdgeTPU运行时间仅为3.8ms。
2. mobilenetv4加入YOLOv8
2.1 新建ultralytics/nn/backbone/mobilenetv4.py
from typing import Any, Callable, Dict, List, Mapping, Optional, Tuple, Union
import torch
import torch.nn as nn
__all__ = ['MobileNetV4ConvSmall', 'MobileNetV4ConvMedium', 'MobileNetV4ConvLarge', 'MobileNetV4HybridMedium', 'MobileNetV4HybridLarge']
MNV4ConvSmall_BLOCK_SPECS = {
"conv0": {
"block_name": "convbn",
"num_blocks": 1,
"block_specs": [
[3, 32, 3, 2]
]
},
"layer1": {
"block_name": "convbn",
"num_blocks": 2,
"block_specs": [
[32, 32, 3, 2],
[32, 32, 1, 1]
]
},
"layer2": {
"block_name": "convbn",
"num_blocks": 2,
"block_specs": [
[32, 96, 3, 2],
[96, 64, 1, 1]
]
},
"layer3": {
"block_name": "uib",
"num_blocks": 6,
"block_specs": [
[64, 96, 5, 5, True, 2, 3],
[96, 96, 0, 3, True, 1, 2],
[96, 96, 0, 3, True, 1, 2],
[96, 96, 0, 3, True, 1, 2],
[96, 96, 0, 3, True, 1, 2],
[96, 96, 3, 0, True, 1, 4],
]
},
"layer4": {
"block_name": "uib",
"num_blocks": 6,
"block_specs": [
[96, 128, 3, 3, True, 2, 6],
[128, 128, 5, 5, True, 1, 4],
[128, 128, 0, 5, True, 1, 4],
[128, 128, 0, 5, True, 1, 3],
[128, 128, 0, 3, True, 1, 4],
[128, 128, 0, 3, True, 1, 4],
]
},
"layer5": {
"block_name": "convbn",
"num_blocks": 2,
"block_specs": [
[128, 960, 1, 1],
[960, 1280, 1, 1]
]
}
}
MNV4ConvMedium_BLOCK_SPECS = {
"conv0": {
"block_name": "convbn",
"num_blocks": 1,
"block_specs": [
[3, 32, 3, 2]
]
},
"layer1": {
"block_name": "fused_ib",
"num_blocks": 1,
"block_specs": [
[32, 48, 2, 4.0, True]
]
},
"layer2": {
"block_name": "uib",
"num_blocks": 2,
"block_specs": [
[48, 80, 3, 5, True, 2, 4],
[80, 80, 3, 3, True, 1, 2]
]
},
"layer3": {
"block_name": "uib",
"num_blocks": 8,
"block_specs": [
[80, 160, 3, 5, True, 2, 6],
[160, 160, 3, 3, True, 1, 4],
[160, 160, 3, 3, True, 1, 4],
[160, 160, 3, 5, True, 1, 4],
[160, 160, 3, 3, True, 1, 4],
[160, 160, 3, 0, True, 1, 4],
[160, 160, 0, 0, True, 1, 2],
[160, 160, 3, 0, True, 1, 4]
]
},
"layer4": {
"block_name": "uib",
"num_blocks": 11,
"block_specs": [
[160, 256, 5, 5, True, 2, 6],
[256, 256, 5, 5, True, 1, 4],
[256, 256, 3, 5, True, 1, 4],
[256, 256, 3, 5, True, 1, 4],
[256, 256, 0, 0, True, 1, 4],
[256, 256, 3, 0, True, 1, 4],
[256, 256, 3, 5, True, 1, 2],
[256, 256, 5, 5, True, 1, 4],
[256, 256, 0, 0, True, 1, 4],
[256, 256, 0, 0, True, 1, 4],
[256, 256, 5, 0, True, 1, 2]
]
},
"layer5": {
"block_name": "convbn",
"num_blocks": 2,
"block_specs": [
[256, 960, 1, 1],
[960, 1280, 1, 1]
]
}
}
MNV4ConvLarge_BLOCK_SPECS = {
"conv0": {
"block_name": "convbn",
"num_blocks": 1,
"block_specs": [
[3, 24, 3, 2]
]
},
"layer1": {
"block_name": "fused_ib",
"num_blocks": 1,
"block_specs": [
[24, 48, 2, 4.0, True]
]
},
"layer2": {
"block_name": "uib",
"num_blocks": 2,
"block_specs": [
[48, 96, 3, 5, True, 2, 4],
[96, 96, 3, 3, True, 1, 4]
]
},
"layer3": {
"block_name": "uib",
"num_blocks": 11,
"block_specs": [
[96, 192, 3, 5, True, 2, 4],
[192, 192, 3, 3, True, 1, 4],
[192, 192, 3, 3, True, 1, 4],
[192, 192, 3, 3, True, 1, 4],
[192, 192, 3, 5, True, 1, 4],
[192, 192, 5, 3, True, 1, 4],
[192, 192, 5, 3, True, 1, 4],
[192, 192, 5, 3, True, 1, 4],
[192, 192, 5, 3, True, 1, 4],
[192, 192, 5, 3, True, 1, 4],
[192, 192, 3, 0, True, 1, 4]
]
},
"layer4": {
"block_name": "uib",
"num_blocks": 13,
"block_specs": [
[192, 512, 5, 5, True, 2, 4],
[512, 512, 5, 5, True, 1, 4],
[512, 512, 5, 5, True, 1, 4],
[512, 512, 5, 5, True, 1, 4],
[512, 512, 5, 0, True, 1, 4],
[512, 512, 5, 3, True, 1, 4],
[512, 512, 5, 0, True, 1, 4],
[512, 512, 5, 0, True, 1, 4],
[512, 512, 5, 3, True, 1, 4],
[512, 512, 5, 5, True, 1, 4],
[512, 512, 5, 0, True, 1, 4],
[512, 512, 5, 0, True, 1, 4],
[512, 512, 5, 0, True, 1, 4]
]
},
"layer5": {
"block_name": "convbn",
"num_blocks": 2,
"block_specs": [
[512, 960, 1, 1],
[960, 1280, 1, 1]
]
}
}
MNV4HybridConvMedium_BLOCK_SPECS = {
}
MNV4HybridConvLarge_BLOCK_SPECS = {
}
MODEL_SPECS = {
"MobileNetV4ConvSmall": MNV4ConvSmall_BLOCK_SPECS,
"MobileNetV4ConvMedium": MNV4ConvMedium_BLOCK_SPECS,
"MobileNetV4ConvLarge": MNV4ConvLarge_BLOCK_SPECS,
"MobileNetV4HybridMedium": MNV4HybridConvMedium_BLOCK_SPECS,
"MobileNetV4HybridLarge": MNV4HybridConvLarge_BLOCK_SPECS,
}
def make_divisible(
value: float,
divisor: int,
min_value: Optional[float] = None,
round_down_protect: bool = True,
) -> int:
"""
This function is copied from here
"https://github.com/tensorflow/models/blob/master/official/vision/modeling/layers/nn_layers.py"
This is to ensure that all layers have channels that are divisible by 8.
Args:
value: A `float` of original value.
divisor: An `int` of the divisor that need to be checked upon.
min_value: A `float` of minimum value threshold.
round_down_protect: A `bool` indicating whether round down more than 10%
will be allowed.
Returns:
The adjusted value in `int` that is divisible against divisor.
"""
if min_value is None:
min_value = divisor
new_value = max(min_value, int(value + divisor / 2) // divisor * divisor)
# Make sure that round down does not go down by more than 10%.
if round_down_protect and new_value < 0.9 * value:
new_value += divisor
return int(new_value)
def conv_2d(inp, oup, kernel_size=3, stride=1, groups=1, bias=False, norm=True, act=True):
conv = nn.Sequential()
padding = (kernel_size - 1) // 2
conv.add_module('conv', nn.Conv2d(inp, oup, kernel_size, stride, padding, bias=bias, groups=groups))
if norm:
conv.add_module('BatchNorm2d', nn.BatchNorm2d(oup))
if act:
conv.add_module('Activation', nn.ReLU6())
return conv
class InvertedResidual(nn.Module):
def __init__(self, inp, oup, stride, expand_ratio, act=False):
super(InvertedResidual, self).__init__()
self.stride = stride
assert stride in [1, 2]
hidden_dim = int(round(inp * expand_ratio))
self.block = nn.Sequential()
if expand_ratio != 1:
self.block.add_module('exp_1x1', conv_2d(inp, hidden_dim, kernel_size=1, stride=1))
self.block.add_module('conv_3x3', conv_2d(hidden_dim, hidden_dim, kernel_size=3, stride=stride, groups=hidden_dim))
self.block.add_module('red_1x1', conv_2d(hidden_dim, oup, kernel_size=1, stride=1, act=act))
self.use_res_connect = self.stride == 1 and inp == oup
def forward(self, x):
if self.use_res_connect:
return x + self.block(x)
else:
return self.block(x)
class UniversalInvertedBottleneckBlock(nn.Module):
def __init__(self,
inp,
oup,
start_dw_kernel_size,
middle_dw_kernel_size,
middle_dw_downsample,
stride,
expand_ratio
):
super().__init__()
# Starting depthwise conv.
self.start_dw_kernel_size = start_dw_kernel_size
if self.start_dw_kernel_size:
stride_ = stride if not middle_dw_downsample else 1
self._start_dw_ = conv_2d(inp, inp, kernel_size=start_dw_kernel_size, stride=stride_, groups=inp, act=False)
# Expansion with 1x1 convs.
expand_filters = make_divisible(inp * expand_ratio, 8)
self._expand_conv = conv_2d(inp, expand_filters, kernel_size=1)
# Middle depthwise conv.
self.middle_dw_kernel_size = middle_dw_kernel_size
if self.middle_dw_kernel_size:
stride_ = stride if middle_dw_downsample else 1
self._middle_dw = conv_2d(expand_filters, expand_filters, kernel_size=middle_dw_kernel_size, stride=stride_, groups=expand_filters)
# Projection with 1x1 convs.
self._proj_conv = conv_2d(expand_filters, oup, kernel_size=1, stride=1, act=False)
# Ending depthwise conv.
# this not used
# _end_dw_kernel_size = 0
# self._end_dw = conv_2d(oup, oup, kernel_size=_end_dw_kernel_size, stride=stride, groups=inp, act=False)
def forward(self, x):
if self.start_dw_kernel_size:
x = self._start_dw_(x)
# print("_start_dw_", x.shape)
x = self._expand_conv(x)
# print("_expand_conv", x.shape)
if self.middle_dw_kernel_size:
x = self._middle_dw(x)
# print("_middle_dw", x.shape)
x = self._proj_conv(x)
# print("_proj_conv", x.shape)
return x
def build_blocks(layer_spec):
if not layer_spec.get('block_name'):
return nn.Sequential()
block_names = layer_spec['block_name']
layers = nn.Sequential()
if block_names == "convbn":
schema_ = ['inp', 'oup', 'kernel_size', 'stride']
args = {}
for i in range(layer_spec['num_blocks']):
args = dict(zip(schema_, layer_spec['block_specs'][i]))
layers.add_module(f"convbn_{i}", conv_2d(**args))
elif block_names == "uib":
schema_ = ['inp', 'oup', 'start_dw_kernel_size', 'middle_dw_kernel_size', 'middle_dw_downsample', 'stride', 'expand_ratio']
args = {}
for i in range(layer_spec['num_blocks']):
args = dict(zip(schema_, layer_spec['block_specs'][i]))
layers.add_module(f"uib_{i}", UniversalInvertedBottleneckBlock(**args))
elif block_names == "fused_ib":
schema_ = ['inp', 'oup', 'stride', 'expand_ratio', 'act']
args = {}
for i in range(layer_spec['num_blocks']):
args = dict(zip(schema_, layer_spec['block_specs'][i]))
layers.add_module(f"fused_ib_{i}", InvertedResidual(**args))
else:
raise NotImplementedError
return layers
class MobileNetV4(nn.Module):
def __init__(self, model):
# MobileNetV4ConvSmall MobileNetV4ConvMedium MobileNetV4ConvLarge
# MobileNetV4HybridMedium MobileNetV4HybridLarge
"""Params to initiate MobilenNetV4
Args:
model : support 5 types of models as indicated in
"https://github.com/tensorflow/models/blob/master/official/vision/modeling/backbones/mobilenet.py"
"""
super().__init__()
assert model in MODEL_SPECS.keys()
self.model = model
self.spec = MODEL_SPECS[self.model]
# conv0
self.conv0 = build_blocks(self.spec['conv0'])
# layer1
self.layer1 = build_blocks(self.spec['layer1'])
# layer2
self.layer2 = build_blocks(self.spec['layer2'])
# layer3
self.layer3 = build_blocks(self.spec['layer3'])
# layer4
self.layer4 = build_blocks(self.spec['layer4'])
# layer5
self.layer5 = build_blocks(self.spec['layer5'])
self.features = nn.ModuleList([self.conv0, self.layer1, self.layer2, self.layer3, self.layer4, self.layer5])
self.channel = [i.size(1) for i in self.forward(torch.randn(1, 3, 640, 640))]
def forward(self, x):
input_size = x.size(2)
scale = [4, 8, 16, 32]
features = [None, None, None, None]
for f in self.features:
x = f(x)
if input_size // x.size(2) in scale:
features[scale.index(input_size // x.size(2))] = x
return features
def MobileNetV4ConvSmall():
model = MobileNetV4('MobileNetV4ConvSmall')
return model
def MobileNetV4ConvMedium():
model = MobileNetV4('MobileNetV4ConvMedium')
return model
def MobileNetV4ConvLarge():
model = MobileNetV4('MobileNetV4ConvLarge')
return model
def MobileNetV4HybridMedium():
model = MobileNetV4('MobileNetV4HybridMedium')
return model
def MobileNetV4HybridLarge():
model = MobileNetV4('MobileNetV4HybridLarge')
return model
if __name__ == '__main__':
model = MobileNetV4ConvSmall()
inputs = torch.randn((1, 3, 640, 640))
res = model(inputs)
for i in res:
print(i.size())2.2 修改task.py
1)首先进行注册
from ultralytics.nn.backbone.mobilenetv4 import *2)修改def parse_model(d, ch, verbose=True): # model_dict, input_channels(3)
建议直接替换
def parse_model(d, ch, verbose=True): # model_dict, input_channels(3)
"""Parse a YOLO model.yaml dictionary into a PyTorch model."""
import ast
# Args
max_channels = float("inf")
nc, act, scales = (d.get(x) for x in ("nc", "activation", "scales"))
depth, width, kpt_shape = (d.get(x, 1.0) for x in ("depth_multiple", "width_multiple", "kpt_shape"))
if scales:
scale = d.get("scale")
if not scale:
scale = tuple(scales.keys())[0]
LOGGER.warning(f"WARNING ⚠️ no model scale passed. Assuming scale='{scale}'.")
depth, width, max_channels = scales[scale]
if act:
Conv.default_act = eval(act) # redefine default activation, i.e. Conv.default_act = nn.SiLU()
if verbose:
LOGGER.info(f"{colorstr('activation:')} {act}") # print
if verbose:
LOGGER.info(f"\n{'':>3}{'from':>20}{'n':>3}{'params':>10} {'module':<45}{'arguments':<30}")
ch = [ch]
layers, save, c2 = [], [], ch[-1] # layers, savelist, ch out
is_backbone = False
for i, (f, n, m, args) in enumerate(d["backbone"] + d["head"]): # from, number, module, args
try:
if m == 'node_mode':
m = d[m]
if len(args) > 0:
if args[0] == 'head_channel':
args[0] = int(d[args[0]])
t = m
m = getattr(torch.nn, m[3:]) if 'nn.' in m else globals()[m] # get module
except:
pass
for j, a in enumerate(args):
if isinstance(a, str):
with contextlib.suppress(ValueError):
try:
args[j] = locals()[a] if a in locals() else ast.literal_eval(a)
except:
args[j] = a
n = n_ = max(round(n * depth), 1) if n > 1 else n # depth gain
if m in (
Classify,
Conv,
ConvTranspose,
GhostConv,
Bottleneck,
GhostBottleneck,
SPP,
SPPF,
DWConv,
Focus,
BottleneckCSP,
C1,
C2,
C2f,
C2fAttn,
C3,
C3TR,
C3Ghost,
nn.ConvTranspose2d,
DWConvTranspose2d,
C3x,
RepC3
):
c1, c2 = ch[f], args[0]
if c2 != nc: # if c2 not equal to number of classes (i.e. for Classify() output)
c2 = make_divisible(min(c2, max_channels) * width, 8)
if m is C2fAttn:
args[1] = make_divisible(min(args[1], max_channels // 2) * width, 8) # embed channels
args[2] = int(
max(round(min(args[2], max_channels // 2 // 32)) * width, 1) if args[2] > 1 else args[2]
) # num heads
args = [c1, c2, *args[1:]]
if m in (BottleneckCSP, C1, C2, C2f, C2fAttn, C3, C3TR, C3Ghost, C3x, RepC3):
args.insert(2, n) # number of repeats
n = 1
elif m is AIFI:
args = [ch[f], *args]
elif m is DySample:
c2 = ch[f]
args = [c2, *args]
elif m in (HGStem, HGBlock):
c1, cm, c2 = ch[f], args[0], args[1]
args = [c1, cm, c2, *args[2:]]
if m is HGBlock:
args.insert(4, n) # number of repeats
n = 1
elif m is ResNetLayer:
c2 = args[1] if args[3] else args[1] * 4
elif m is nn.BatchNorm2d:
args = [ch[f]]
elif m is Concat:
c2 = sum(ch[x] for x in f)
elif m in (Detect, WorldDetect, Segment, Pose, OBB, ImagePoolingAttn):
args.append([ch[x] for x in f])
if m is Segment:
args[2] = make_divisible(min(args[2], max_channels) * width, 8)
elif m is RTDETRDecoder: # special case, channels arg must be passed in index 1
args.insert(1, [ch[x] for x in f])
##### backbone
elif isinstance(m, str):
t = m
if len(args) == 2:
m = timm.create_model(m, pretrained=args[0], pretrained_cfg_overlay={'file':args[1]}, features_only=True)
elif len(args) == 1:
m = timm.create_model(m, pretrained=args[0], features_only=True)
c2 = m.feature_info.channels()
elif m in {
MobileNetV4ConvSmall, MobileNetV4ConvMedium, MobileNetV4ConvLarge
}:
m = m(*args)
c2 = m.channel
##### backbone
else:
c2 = ch[f]
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)
return nn.Sequential(*layers), sorted(save)3）修改def _predict_once(self, x, profile=False, visualize=False, embed=None):
建议直接替换
def _predict_once(self, x, profile=False, visualize=False, embed=None):
"""
Perform a forward pass through the network.
Args:
x (torch.Tensor): The input tensor to the model.
profile (bool): Print the computation time of each layer if True, defaults to False.
visualize (bool): Save the feature maps of the model if True, defaults to False.
embed (list, optional): A list of feature vectors/embeddings to return.
Returns:
(torch.Tensor): The last output of the model.
"""
y, dt, embeddings = [], [], [] # outputs
for m in 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)
# for i in x:
# if i is not None:
# print(i.size())
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 x4） class DetectionModel(BaseModel):修改
# Build strides
m = self.model[-1] # Detect()
if isinstance(m, Detect): # includes all Detect subclasses like Segment, Pose, OBB, WorldDetect
s = 640 # 2x min stride
m.inplace = self.inplace
forward = lambda x: self.forward(x)[0] if isinstance(m, (Segment, Pose, OBB)) else self.forward(x)
try:
m.stride = torch.tensor([s / x.shape[-2] for x in forward(torch.zeros(2, ch, s, s))]) # forward
except RuntimeError as e:
if 'Not implemented on the CPU' in str(e) or 'Input type (torch.FloatTensor) and weight type (torch.cuda.FloatTensor)' in str(e) or 'CUDA tensor' in str(e) or 'is_cuda()' in str(e):
self.model.to(torch.device('cuda'))
m.stride = torch.tensor([s / x.shape[-2] for x in forward(torch.zeros(2, ch, s, s).to(torch.device('cuda')))]) # forward
else:
raise e
self.stride = m.stride
m.bias_init() # only run once
else:
self.stride = torch.Tensor([32]) # default stride for i.e. RTDETR2.3 yolov8-mobilenetv4.yaml
# 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
# 0-P1/2
# 1-P2/4
# 2-P3/8
# 3-P4/16
# 4-P5/32
# YOLOv8.0n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, MobileNetV4ConvSmall, []] # 4
- [-1, 1, SPPF, [1024, 5]] # 5
# YOLOv8.0n head
head:
- [-1, 1, nn.Upsample, [None, 2, 'nearest']] # 6
- [[-1, 3], 1, Concat, [1]] # 7 cat backbone P4
- [-1, 3, C2f, [512]] # 8
- [-1, 1, nn.Upsample, [None, 2, 'nearest']] # 9
- [[-1, 2], 1, Concat, [1]] # 10 cat backbone P3
- [-1, 3, C2f, [256]] # 11 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]] # 12
- [[-1, 8], 1, Concat, [1]] # 13 cat head P4
- [-1, 3, C2f, [512]] # 14 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]] # 15
- [[-1, 5], 1, Concat, [1]] # 16 cat head P5
- [-1, 3, C2f, [1024]] # 17 (P5/32-large)
- [[11, 14, 17], 1, Detect, [nc]] # Detect(P3, P4, P5)