目标检测算法——YOLOv5结合ConvNeXt结构
关注”PandaCVer“公众号
深度学习Tricks，第一时间送达
论文题目：A ConvNet for the 2020s
论文地址：https://arxiv.org/abs/2201.03545
源代码：https://github.com/facebookresearch/ConvNeXt
（一）前言
计算机视觉迎来了一个“咆哮”的2020s年代，它的起点从引入视觉Transformer开始，即ViT，它能快速超过CNN并取得SOTA的识别性能。而原始的ViT架构，在通用的计算机视觉任务上如目标检测和语义分割等面临不少困难。直到具有分层架构的Transformer如Swin Transformer，通过重新引入ConvNet一些设计，它作为一种通用的视觉backbone并在多个视觉任务上取得优良的表现，才让Transformer变得实用。但是，这种混合架构的有效性，在很大程度归功于Transformer的内在优势，而不是卷积固有的归纳偏差（inductive biases）。这篇文章重新审视设计的空间，并测试一个纯CNN网络能取得什么样的上限。作者通过逐渐将一个标准的ResNet模型，不断往ViT的设计中改造，并发现了几个关键的成分导致了性能的差异。作者构造的纯ConvNet系列模型，能够取得超过Swin Transformer的性能，在ImageNet-1K上取得了超过87.8%的Top1精度。作者分别对比了CNN和Transformer中最具代表性的模型，CNN模型如ResNet、ConvNeXt，Transformer模型如DeiT、Swin Transformer，ConvNeXt在精度和运算量上能取得最好的平衡，在扩展性上也能与Swin Transformer相当但设计更加简单。圆圈的直径越大，运算量越大。
（二）YOLOv5结合ConvNeXt结构
1.配置.yaml文件
# anchors
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
# YOLOv5 backbone
backbone:
# [from, number, module, args]
[[-1, 1, Focus, [64, 3]], # 0-P1/2
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
[-1, 3, C3, [128]],
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
[-1, 9, C3, [256]],
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
[-1, 9, C3, [512]],
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
[-1, 1, SPP, [1024, [5, 9, 13]]],
[-1, 3, C3, [1024, False]], # 9
]
# YOLOv5 head
head:
[[-1, 1, Conv, [512, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 6], 1, Concat, [1]], # cat backbone P4
[-1, 3, CNeB, [512]], # 13
[-1, 1, Conv, [256, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 4], 1, Concat, [1]], # cat backbone P3
[-1, 3, CNeB, [256]], # 17 (P3/8-small)
[-1, 1, Conv, [256, 3, 2]],
[[-1, 14], 1, Concat, [1]], # cat head P4
[-1, 3, CNeB, [512]], # 20 (P4/16-medium)
[-1, 1, Conv, [512, 3, 2]],
[[-1, 10], 1, Concat, [1]], # cat head P5
[-1, 3, CNeB, [1024]], # 23 (P5/32-large)
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
]
2.配置common.py
复制粘贴下面代码：
class LayerNorm_s(nn.Module):
def __init__(self, normalized_shape, eps=1e-6, data_format="channels_last"):
super().__init__()
self.weight = nn.Parameter(torch.ones(normalized_shape))
self.bias = nn.Parameter(torch.zeros(normalized_shape))
self.eps = eps
self.data_format = data_format
if self.data_format not in ["channels_last", "channels_first"]:
raise NotImplementedError
self.normalized_shape = (normalized_shape,)
def forward(self, x):
if self.data_format == "channels_last":
return F.layer_norm(x, self.normalized_shape, self.weight, self.bias, self.eps)
elif self.data_format == "channels_first":
u = x.mean(1, keepdim=True)
s = (x - u).pow(2).mean(1, keepdim=True)
x = (x - u) / torch.sqrt(s + self.eps)
x = self.weight[:, None, None] * x + self.bias[:, None, None]
return x
class ConvNextBlock(nn.Module):
def __init__(self, dim, drop_path=0., layer_scale_init_value=1e-6):
super().__init__()
self.dwconv = nn.Conv2d(dim, dim, kernel_size=7, padding=3, groups=dim) # depthwise conv
self.norm = LayerNorm_s(dim, eps=1e-6)
self.pwconv1 = nn.Linear(dim, 4 * dim)
self.act = nn.GELU()
self.pwconv2 = nn.Linear(4 * dim, dim)
self.gamma = nn.Parameter(layer_scale_init_value * torch.ones((dim)),
requires_grad=True) if layer_scale_init_value > 0 else None
self.drop_path = DropPath(drop_path) if drop_path > 0. else nn.Identity()
def forward(self, x):
input = x
x = self.dwconv(x)
x = x.permute(0, 2, 3, 1) # (N, C, H, W) -> (N, H, W, C)
x = self.norm(x)
x = self.pwconv1(x)
x = self.act(x)
x = self.pwconv2(x)
if self.gamma is not None:
x = self.gamma * x
x = x.permute(0, 3, 1, 2) # (N, H, W, C) -> (N, C, H, W)
x = input + self.drop_path(x)
return x
class DropPath(nn.Module):
"""Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).
"""
def __init__(self, drop_prob=None):
super(DropPath, self).__init__()
self.drop_prob = drop_prob
def forward(self, x):
return drop_path_f(x, self.drop_prob, self.training)
def drop_path_f(x, drop_prob: float = 0., training: bool = False):
if drop_prob == 0. or not training:
return x
keep_prob = 1 - drop_prob
shape = (x.shape[0],) + (1,) * (x.ndim - 1) # work with diff dim tensors, not just 2D ConvNets
random_tensor = keep_prob + torch.rand(shape, dtype=x.dtype, device=x.device)
random_tensor.floor_() # binarize
output = x.div(keep_prob) * random_tensor
return output
class CNeB(nn.Module):
# CSP ConvNextBlock with 3 convolutions by iscyy/yoloair
def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): # ch_in, ch_out, number, shortcut, groups, expansion
super().__init__()
c_ = int(c2 * e) # hidden channels
self.cv1 = Conv(c1, c_, 1, 1)
self.cv2 = Conv(c1, c_, 1, 1)
self.cv3 = Conv(2 * c_, c2, 1)
self.m = nn.Sequential(*(ConvNextBlock(c_) for _ in range(n)))
def forward(self, x):
return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), dim=1))
3.修改yolo.py
复制粘贴下面代码：
elif m is CNeB:
c1, c2 = ch[f], args[0]
if c2 != no:
c2 = make_divisible(c2 * gw, 8)
args = [c1, c2, *args[1:]]
if m is CNeB:
args.insert(2, n)
n = 1
最后一步！——小伙伴们可以自行训练自己的数据集啦！！！