P8周：YOLOv5-C3模块实现
一、前期准备
1.设置GPU
import torch
import torch.nn as nn
import torchvision.transforms as transforms
import torchvision
from torchvision import transforms,datasets
import os,PIL,pathlib,warnings
warnings.filterwarnings("ignore")
device = torch.device("cuda" if torch.cuda.is_available() else "CPU")
device
device(type=‘cuda’)
2.导入数据
import os,PIL,random,pathlib
data_dir = r"D:\z_temp\data\weather_photos"
data_dir = pathlib.Path(data_dir)
data_paths = list(data_dir.glob("*"))
classNames = list(str(path).split("\\")[4] for path in data_paths)
classNames
[‘cloudy’, ‘rain’, ‘shine’, ‘sunrise’]
train_transforms = transforms.Compose([
transforms.Resize([224,224]),
transforms.ToTensor(),
transforms.Normalize(
mean = [0.485,0.456,0.406],
std = [0.229,0.224,0.225])
])
test_transforms = transforms.Compose([
transforms.Resize([224,224]),
transforms.ToTensor(),
transforms.Normalize(
mean = [0.485,0.456,0.406],
std = [0.229,0.224,0.225])
])
total_data = datasets.ImageFolder(r"D:\z_temp\data\weather_photos",transform = train_transforms)
total_data
Dataset ImageFolder
Number of datapoints: 1125
Root location: D:\z_temp\data\weather_photos
StandardTransform
Transform: Compose(
Resize(size=[224, 224], interpolation=bilinear, max_size=None, antialias=True)
ToTensor()
Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
)
total_data.class_to_idx
{‘cloudy’: 0, ‘rain’: 1, ‘shine’: 2, ‘sunrise’: 3}
3.划分数据集
train_size = int(0.8*len(total_data))
test_size = len(total_data)-train_size
train_dataset,test_dataset = torch.utils.data.random_split(total_data,[train_size,test_size])
train_dataset,test_dataset
(<torch.utils.data.dataset.Subset at 0x19f98169700>,
<torch.utils.data.dataset.Subset at 0x19f981692e0>)
batch_size = 4
train_dl = torch.utils.data.DataLoader(train_dataset,
batch_size = batch_size,
shuffle = True,
num_workers = 1)
test_dl = torch.utils.data.DataLoader(test_dataset,
batch_size = batch_size,
shuffle = True,
num_workers = 1)
for X,y in test_dl:
print("Shape of X [N,C,H,W]:",X.shape)
print("Shape of y:",y.shape,y.dtype)
break
Shape of X [N,C,H,W]: torch.Size([4, 3, 224, 224])
Shape of y: torch.Size([4]) torch.int64
二、搭建包含C3模块的模型
1.搭建模型
import torch.nn.functional as F
def autopad(k,p = None):
if p is None:
p = k//2 if isinstance(k,int) else [x // 2 for x in k]
return p
class Conv(nn.Module):
def __init__(self,c1,c2,k=1,s=1,p=None,g=1,act=True):
super().__init__()
self.conv = nn.Conv2d(c1,c2,k,s,autopad(k,p),groups = g,bias = False)
self.bn = nn.BatchNorm2d(c2)
self.act = nn.SiLU() if act is True else (act if ininstance(act,nn.Module) else nn.Identity())
def forward(self,x):
return self.act(self.bn(self.conv(x)))
class Bottleneck(nn.Module):
def __init__(self,c1,c2,shortcut = True,g=1,e=0.5):
super().__init__()
c_ = int(c2 * e)
self.cv1 = Conv(c1,c_,1,1)
self.cv2 = Conv(c_,c2,3,1,g=g)
self.add = shortcut and c1 == c2
def forward(self,x):
return x+self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))
class C3(nn.Module):
def __init__(self,c1,c2,n=1,shortcut=True,g=1,e=0.5):
super().__init__()
c_ = int(c2*e)
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(*(Bottleneck(c_,c_,shortcut,g,e=1.0) for _ in range(n)))
def forward(self,x):
return self.cv3(torch.cat((self.m(self.cv1(x)),self.cv2(x)),dim=1))
class model_K(nn.Module):
def __init__(self):
super(model_K,self).__init__()
self.Conv = Conv(3,32,3,2)
self.C3_1 = C3(32,64,3,2)
self.classifier = nn.Sequential(
nn.Linear(in_features = 802816,out_features = 100),# in_features = 64*112*112
nn.ReLU(),
nn.Linear(in_features = 100,out_features = 4)
)
def forward(self,x):
x = self.Conv(x)
x = self.C3_1(x)
x = torch.flatten(x,start_dim = 1)
x = self.classifier(x)
return x
device = 'cuda' if torch.cuda.is_available() else 'CPU'
print('Using {} device'.format(device))
model = model_K().to(device)
model
model_K(
(Conv): Conv(
(conv): Conv2d(3, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): SiLU()
)
(C3_1): C3(
(cv1): Conv(
(conv): Conv2d(32, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): SiLU()
)
(cv2): Conv(
(conv): Conv2d(32, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): SiLU()
)
(cv3): Conv(
(conv): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): SiLU()
)
(m): Sequential(
(0): Bottleneck(
(cv1): Conv(
(conv): Conv2d(32, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): SiLU()
)
(cv2): Conv(
(conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): SiLU()
)
)
(1): Bottleneck(
(cv1): Conv(
(conv): Conv2d(32, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): SiLU()
)
(cv2): Conv(
(conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): SiLU()
)
)
(2): Bottleneck(
(cv1): Conv(
(conv): Conv2d(32, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): SiLU()
)
(cv2): Conv(
(conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): SiLU()
)
)
)
)
(classifier): Sequential(
(0): Linear(in_features=802816, out_features=100, bias=True)
(1): ReLU()
(2): Linear(in_features=100, out_features=4, bias=True)
)
)
2.查看模型详情
# 统计模型参数量以及其他指标
import torchsummary as summary
summary.summary(model, (3, 224, 224))
Layer (type) Output Shape Param #================================================================
Conv2d-1 [-1, 32, 112, 112] 864
BatchNorm2d-2 [-1, 32, 112, 112] 64
SiLU-3 [-1, 32, 112, 112] 0
Conv-4 [-1, 32, 112, 112] 0
Conv2d-5 [-1, 32, 112, 112] 1,024
BatchNorm2d-6 [-1, 32, 112, 112] 64
SiLU-7 [-1, 32, 112, 112] 0
Conv-8 [-1, 32, 112, 112] 0
Conv2d-9 [-1, 32, 112, 112] 1,024
BatchNorm2d-10 [-1, 32, 112, 112] 64
SiLU-11 [-1, 32, 112, 112] 0
Conv-12 [-1, 32, 112, 112] 0
Conv2d-13 [-1, 32, 112, 112] 9,216
BatchNorm2d-14 [-1, 32, 112, 112] 64
SiLU-15 [-1, 32, 112, 112] 0
Conv-16 [-1, 32, 112, 112] 0
Bottleneck-17 [-1, 32, 112, 112] 0
Conv2d-18 [-1, 32, 112, 112] 1,024
BatchNorm2d-19 [-1, 32, 112, 112] 64
SiLU-20 [-1, 32, 112, 112] 0
Conv-21 [-1, 32, 112, 112] 0
Conv2d-22 [-1, 32, 112, 112] 9,216
BatchNorm2d-23 [-1, 32, 112, 112] 64
SiLU-24 [-1, 32, 112, 112] 0
Conv-25 [-1, 32, 112, 112] 0
Bottleneck-26 [-1, 32, 112, 112] 0
Conv2d-27 [-1, 32, 112, 112] 1,024
BatchNorm2d-28 [-1, 32, 112, 112] 64
SiLU-29 [-1, 32, 112, 112] 0
Conv-30 [-1, 32, 112, 112] 0
Conv2d-31 [-1, 32, 112, 112] 9,216
BatchNorm2d-32 [-1, 32, 112, 112] 64
SiLU-33 [-1, 32, 112, 112] 0
Conv-34 [-1, 32, 112, 112] 0
Bottleneck-35 [-1, 32, 112, 112] 0
Conv2d-36 [-1, 32, 112, 112] 1,024
BatchNorm2d-37 [-1, 32, 112, 112] 64
SiLU-38 [-1, 32, 112, 112] 0
Conv-39 [-1, 32, 112, 112] 0
Conv2d-40 [-1, 64, 112, 112] 4,096
BatchNorm2d-41 [-1, 64, 112, 112] 128
SiLU-42 [-1, 64, 112, 112] 0
Conv-43 [-1, 64, 112, 112] 0
C3-44 [-1, 64, 112, 112] 0
Linear-45 [-1, 100] 80,281,700
ReLU-46 [-1, 100] 0
Linear-47 [-1, 4] 404
================================================================
Total params: 80,320,536Trainable params: 80,320,536Non-trainable params: 0
----------------------------------------------------------------
nput size (MB): 0.57Forward/backward pass size (MB): 150.06Params size (MB): 306.40Estimated Total Size (MB): 457.04
----------------------------------------------------------------
三、训练模型
1.编写训练函数
# 训练循环
def train(dataloader, model, loss_fn, optimizer):
size = len(dataloader.dataset) # 训练集的大小
num_batches = len(dataloader) # 批次数目, (size/batch_size，向上取整)
train_loss, train_acc = 0, 0 # 初始化训练损失和正确率
for X, y in dataloader: # 获取图片及其标签
X, y = X.to(device), y.to(device)
# 计算预测误差
pred = model(X) # 网络输出
loss = loss_fn(pred, y) # 计算网络输出和真实值之间的差距，targets为真实值，计算二者差值即为损失
# 反向传播
optimizer.zero_grad() # grad属性归零
loss.backward() # 反向传播
optimizer.step() # 每一步自动更新
# 记录acc与loss
train_acc += (pred.argmax(1) == y).type(torch.float).sum().item()
train_loss += loss.item()
train_acc /= size
train_loss /= num_batches
return train_acc, train_loss
2.编写测试函数
def test (dataloader, model, loss_fn):
size = len(dataloader.dataset) # 测试集的大小
num_batches = len(dataloader) # 批次数目, (size/batch_size，向上取整)
test_loss, test_acc = 0, 0
# 当不进行训练时，停止梯度更新，节省计算内存消耗
with torch.no_grad():
for imgs, target in dataloader:
imgs, target = imgs.to(device), target.to(device)
# 计算loss
target_pred = model(imgs)
loss = loss_fn(target_pred, target)
test_loss += loss.item()
test_acc += (target_pred.argmax(1) == target).type(torch.float).sum().item()
test_acc /= size
test_loss /= num_batches
return test_acc, test_loss
3.正式训练
import copy
optimizer = torch.optim.Adam(model.parameters(), lr= 1e-4)
loss_fn = nn.CrossEntropyLoss() # 创建损失函数
epochs = 20
train_loss = []
train_acc = []
test_loss = []
test_acc = []
best_acc = 0 # 设置一个最佳准确率，作为最佳模型的判别指标
for epoch in range(epochs):
model.train()
epoch_train_acc, epoch_train_loss = train(train_dl, model, loss_fn, optimizer)
model.eval()
epoch_test_acc, epoch_test_loss = test(test_dl, model, loss_fn)
# 保存最佳模型到 best_model
if epoch_test_acc > best_acc:
best_acc = epoch_test_acc
best_model = copy.deepcopy(model)
train_acc.append(epoch_train_acc)
train_loss.append(epoch_train_loss)
test_acc.append(epoch_test_acc)
test_loss.append(epoch_test_loss)
# 获取当前的学习率
lr = optimizer.state_dict()['param_groups'][0]['lr']
template = ('Epoch:{:2d}, Train_acc:{:.1f}%, Train_loss:{:.3f}, Test_acc:{:.1f}%, Test_loss:{:.3f}, Lr:{:.2E}')
print(template.format(epoch+1, epoch_train_acc*100, epoch_train_loss,
epoch_test_acc*100, epoch_test_loss, lr))
Epoch: 1, Train_acc:69.4%, Train_loss:1.455, Test_acc:84.9%, Test_loss:0.553, Lr:1.00E-04
Epoch: 2, Train_acc:85.3%, Train_loss:0.473, Test_acc:84.4%, Test_loss:0.628, Lr:1.00E-04
Epoch: 3, Train_acc:90.7%, Train_loss:0.270, Test_acc:89.3%, Test_loss:0.565, Lr:1.00E-04
Epoch: 4, Train_acc:95.2%, Train_loss:0.151, Test_acc:84.9%, Test_loss:0.680, Lr:1.00E-04
Epoch: 5, Train_acc:97.6%, Train_loss:0.066, Test_acc:88.4%, Test_loss:0.563, Lr:1.00E-04
Epoch: 6, Train_acc:99.3%, Train_loss:0.022, Test_acc:89.3%, Test_loss:0.546, Lr:1.00E-04
Epoch: 7, Train_acc:99.6%, Train_loss:0.020, Test_acc:89.8%, Test_loss:0.610, Lr:1.00E-04
Epoch: 8, Train_acc:98.4%, Train_loss:0.040, Test_acc:85.3%, Test_loss:0.704, Lr:1.00E-04
Epoch: 9, Train_acc:96.7%, Train_loss:0.142, Test_acc:85.3%, Test_loss:0.623, Lr:1.00E-04
Epoch:10, Train_acc:96.6%, Train_loss:0.126, Test_acc:83.1%, Test_loss:1.319, Lr:1.00E-04
Epoch:11, Train_acc:98.8%, Train_loss:0.050, Test_acc:89.3%, Test_loss:0.689, Lr:1.00E-04
Epoch:12, Train_acc:99.0%, Train_loss:0.031, Test_acc:86.2%, Test_loss:0.614, Lr:1.00E-04
Epoch:13, Train_acc:98.1%, Train_loss:0.077, Test_acc:90.7%, Test_loss:0.636, Lr:1.00E-04
Epoch:14, Train_acc:99.2%, Train_loss:0.041, Test_acc:87.6%, Test_loss:0.874, Lr:1.00E-04
Epoch:15, Train_acc:99.8%, Train_loss:0.009, Test_acc:89.8%, Test_loss:0.665, Lr:1.00E-04
Epoch:16, Train_acc:100.0%, Train_loss:0.002, Test_acc:91.6%, Test_loss:0.596, Lr:1.00E-04
Epoch:17, Train_acc:99.2%, Train_loss:0.028, Test_acc:90.2%, Test_loss:0.714, Lr:1.00E-04
Epoch:18, Train_acc:99.8%, Train_loss:0.009, Test_acc:90.7%, Test_loss:0.648, Lr:1.00E-04
Epoch:19, Train_acc:99.2%, Train_loss:0.049, Test_acc:88.0%, Test_loss:0.742, Lr:1.00E-04
Epoch:20, Train_acc:99.1%, Train_loss:0.034, Test_acc:90.2%, Test_loss:0.449, Lr:1.00E-04
四、结果可视化
1.Loss与Accuracy图
import matplotlib.pyplot as plt
#隐藏警告
import warnings
warnings.filterwarnings("ignore") #忽略警告信息
plt.rcParams['font.sans-serif'] = ['SimHei'] # 用来正常显示中文标签
plt.rcParams['axes.unicode_minus'] = False # 用来正常显示负号
plt.rcParams['figure.dpi'] = 100 #分辨率
from datetime import datetime
current_time = datetime.now() # 获取当前时间
epochs_range = range(epochs)
plt.figure(figsize=(12, 3))
plt.subplot(1, 2, 1)
plt.plot(epochs_range, train_acc, label='Training Accuracy')
plt.plot(epochs_range, test_acc, label='Test Accuracy')
plt.legend(loc='lower right')
plt.title('Training and Validation Accuracy')
plt.xlabel(current_time) # 打卡请带上时间戳，否则代码截图无效
plt.subplot(1, 2, 2)
plt.plot(epochs_range, train_loss, label='Training Loss')
plt.plot(epochs_range, test_loss, label='Test Loss')
plt.legend(loc='upper right')
plt.title('Training and Validation Loss')
plt.show()
2.模型评估
best_model.eval()
epoch_test_acc, epoch_test_loss = test(test_dl, best_model, loss_fn)
epoch_test_acc, epoch_test_loss
epoch_test_acc, epoch_test_loss
# 查看是否与我们记录的最高准确率一致
epoch_test_acc
0.9155555555555556
五、总结
1. YOLOv5-C3介绍
C3模块，全称 Cross Stage Partial Bottleneck with 3 convolutions，是 YOLOv5 中提出的一种改进型的残差模块（Residual Block），灵感来自 CSPNet（Cross Stage Partial Network） 的思想。
其主要作用是：
- 加强特征提取（提高网络表达能力）
- 减少计算量和参数量（比传统残差结构更轻量）
C3 的网络结构组成
│
┌────┴────────┐
│ │
│ ┌─▼─┐
│ │Conv│
│ └─┬─┘
│ ┌────▼────┐
│ │ 残差结构 │ × n次（Bottleneck）
│ └────┬────┘
│ ┌─▼─┐
│ │Conv│
│ └─┬─┘
└────┬────────▼─────────┐
│ Add（或Concat）
▼
输出
2.C3的模块
auto padding
为了保持图像大小卷积前后一致
def autopad(k, p=None): # kernel padding 根据卷积核大小k自动计算卷积核padding数（0填充）
"""
:param k: 卷积核的 kernel_size
:param p: 卷积的padding 一般是None
:return: 自动计算的需要pad值(0填充)
"""
if p is None:
# k 是 int 整数则除以2, 若干的整数值则循环整除
p = k // 2 if isinstance(k, int) else [x // 2 for x in k]
return p
Conv模块
class Conv(nn.Module):
def __init__(self, c1, c2, k=1, s=1, p=None, act=True, g=1):
"""
:param c1: 输入的channel值
:param c2: 输出的channel值
:param k: 卷积的kernel_size
:param s: 卷积的stride
:param p: 卷积的padding 一般是None
:param act: 激活函数类型 True就是SiLU(), False就是不使用激活函数
:param g: 卷积的groups数 =1就是普通的卷积 >1就是深度可分离卷积
"""
super(Conv, self).__init__()
self.conv_1 = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g, bias=True)
self.bn = nn.BatchNorm2d(c2)
self.act = nn.SiLU() if act else nn.Identity() # 若act=True, 则激活, act=False, 不激活
def forward(self, x):
return self.act(self.bn(self.conv_1(x)))
Bottleneck
Bottleneck模块中包含一个残差连接结构（左），和不包含的残差结构（右），就需要传入参数,来判断是否需要使用残差结构
class Bottleneck(nn.Module):
def __init__(self, c1, c2, e=0.5, shortcut=True, g=1):
"""
:param c1: 整个Bottleneck的输入channel
:param c2: 整个Bottleneck的输出channel
:param e: expansion ratio c2*e 就是第一个卷积的输出channel=第二个卷积的输入channel
:param shortcut: bool Bottleneck中是否有shortcut，默认True
:param g: Bottleneck中的3x3卷积类型 =1普通卷积 >1深度可分离卷积
"""
super(Bottleneck, self).__init__()
c_ = int(c2*e) # 使通道减半, c_具体多少取决于e
self.conv_1 = Conv(c1, c_, 1, 1)
self.conv_2 = Conv(c_, c2, 3, 1, g=g)
self.add = shortcut and c1 == c2
def forward(self, x):
return x + self.conv_2(self.conv_1(x)) if self.add else self.conv_2(self.conv_1(x))
C3
class C3(nn.Module):
def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
"""
:param c1: 整个 C3 的输入channel
:param c2: 整个 C3 的输出channel
:param n: 有n个Bottleneck
:param shortcut: bool Bottleneck中是否有shortcut，默认True
:param g: C3中的3x3卷积类型 =1普通卷积 >1深度可分离卷积
:param e: expansion ratio
"""
super(C3, self).__init__()
c_ = int(c2 * e)
self.cv_1 = Conv(c1, c_, 1, 1)
self.cv_2 = Conv(c1, c_, 1, 1)
# *操作符可以把一个list拆开成一个个独立的元素,然后再送入Sequential来构造m,相当于m用了n次Bottleneck的操作
self.m = nn.Sequential(*[Bottleneck(c_, c_, e=1, shortcut=True, g=1) for _ in range(n)])
self.cv_3 = Conv(2*c_, c2, 1, 1)
def forward(self, x):
return self.cv_3(torch.cat((self.m(self.cv_1(x)), self.cv_2(x)), dim=1))
其他
class BottleneckCSP(nn.Module):
def __init__(self, c1, c2, e=0.5, n=1):
"""
:param c1: 整个BottleneckCSP的输入channel
:param c2: 整个BottleneckCSP的输出channel
:param e: expansion ratio c2*e=中间其他所有层的卷积核个数/中间所有层的输入输出channel数
:param n: 有 n 个Bottleneck
"""
super(BottleneckCSP, self).__init__()
c_ = int(c2*e)
self.conv_1 = Conv(c1, c_, 1, 1)
self.m = nn.Sequential(*[Bottleneck(c_, c_, e=1, shortcut=True, g=1) for _ in range(n)])
self.conv_3 = Conv(c_, c_, 1, 1)
self.conv_2 = Conv(c1, c_, 1, 1)
self.bn = nn.BatchNorm2d(2*c_)
self.LeakyRelu = nn.LeakyReLU()
self.conv_4 = Conv(2*c_, c2, 1, 1)
def forward(self, x):
x_1 = self.conv_3(self.m(self.conv_1(x)))
x_2 = self.conv_2(x)
x_3 = torch.cat([x_1, x_2], dim=1)
x_4 = self.LeakyRelu(self.bn(x_3))
x = self.conv_4(x_4)
return x
class SPP(nn.Module):
def __init__(self, c1, c2, e=0.5, k1=5, k2=9, k3=13):
"""
:param c1: SPP模块的输入channel
:param c2: SPP模块的输出channel
:param e: expansion ratio
:param k1: Maxpool 的卷积核大小
:param k2: Maxpool 的卷积核大小
:param k3: Maxpool 的卷积核大小
"""
super(SPP, self).__init__()
c_ = int(c2*e)
self.cv_1 = Conv(c1, c_, 1, 1)
self.pool_1 = nn.MaxPool2d(kernel_size=k1, stride=1, padding=k1 // 2)
self.pool_2 = nn.MaxPool2d(kernel_size=k2, stride=1, padding=k2 // 2)
self.pool_3 = nn.MaxPool2d(kernel_size=k3, stride=1, padding=k3 // 2)
self.cv_2 = Conv(4*c_, c2, 1, 1)
def forward(self, x):
return self.cv_2(torch.cat((self.pool_1(self.cv_1(x)), self.pool_2(self.cv_1(x)), self.pool_3(self.cv_1(x)), self.cv_1(x)), dim=1))
扫一扫
910
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
