- 🍨 本文为🔗365天深度学习训练营 中的学习记录博客
- 🍖 原作者：K同学啊 | 接辅导、项目定制
🏡我的环境：
- 语言环境：Python3.11.4
- 编译器：Jupyter Notebook
- torcch版本：2.0.1
一、前期准备
1、加载数据包
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") #忽略警告信息
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
device2、导入数据
import os,PIL,random,pathlib
data_dir = '/Users/wendyweng/Desktop/weather_photos'
data_dir = pathlib.Path(data_dir)
data_paths = list(data_dir.glob('*'))
classeNames = [str(path).split("/")[5] for path in data_paths]
classeNames# 关于transforms.Compose的更多介绍可以参考：https://blog.csdn.net/qq_38251616/article/details/124878863
train_transforms = transforms.Compose([
transforms.Resize([224, 224]), # 将输入图片resize成统一尺寸
# transforms.RandomHorizontalFlip(), # 随机水平翻转
transforms.ToTensor(), # 将PIL Image或numpy.ndarray转换为tensor，并归一化到[0,1]之间
transforms.Normalize( # 标准化处理-->转换为标准正太分布（高斯分布），使模型更容易收敛
mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225]) # 其中 mean=[0.485,0.456,0.406]与std=[0.229,0.224,0.225] 从数据集中随机抽样计算得到的。
])
test_transform = transforms.Compose([
transforms.Resize([224, 224]), # 将输入图片resize成统一尺寸
transforms.ToTensor(), # 将PIL Image或numpy.ndarray转换为tensor，并归一化到[0,1]之间
transforms.Normalize( # 标准化处理-->转换为标准正太分布（高斯分布），使模型更容易收敛
mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225]) # 其中 mean=[0.485,0.456,0.406]与std=[0.229,0.224,0.225] 从数据集中随机抽样计算得到的。
])
total_data = datasets.ImageFolder("/Users/wendyweng/Desktop/weather_photos",transform=train_transforms)
total_data
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 0x2bbb0779330>,
<torch.utils.data.dataset.Subset at 0x2bbb0779e10>)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二、搭建包含Backbone模块的模型
1. 搭建模型
import torch.nn.functional as F
def autopad(k, p=None): # kernel, padding
# Pad to 'same'
if p is None:
p = k // 2 if isinstance(k, int) else [x // 2 for x in k] # auto-pad
return p
class Conv(nn.Module):
# Standard convolution
def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True): # ch_in, ch_out, kernel, stride, padding, groups
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 isinstance(act, nn.Module) else nn.Identity())
def forward(self, x):
return self.act(self.bn(self.conv(x)))
class Bottleneck(nn.Module):
# Standard bottleneck
def __init__(self, c1, c2, shortcut=True, g=1, e=0.5): # ch_in, ch_out, shortcut, groups, expansion
super().__init__()
c_ = int(c2 * e) # hidden channels
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):
# CSP Bottleneck with 3 convolutions
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) # act=FReLU(c2)
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 SPPF(nn.Module):
# Spatial Pyramid Pooling - Fast (SPPF) layer for YOLOv5 by Glenn Jocher
def __init__(self, c1, c2, k=5): # equivalent to SPP(k=(5, 9, 13))
super().__init__()
c_ = c1 // 2 # hidden channels
self.cv1 = Conv(c1, c_, 1, 1)
self.cv2 = Conv(c_ * 4, c2, 1, 1)
self.m = nn.MaxPool2d(kernel_size=k, stride=1, padding=k // 2)
def forward(self, x):
x = self.cv1(x)
with warnings.catch_warnings():
warnings.simplefilter('ignore') # suppress torch 1.9.0 max_pool2d() warning
y1 = self.m(x)
y2 = self.m(y1)
return self.cv2(torch.cat([x, y1, y2, self.m(y2)], 1))
"""
这个是YOLOv5, 6.0版本的主干网络，这里进行复现
（注：有部分删改，详细讲解将在后续进行展开）
"""
class YOLOv5_backbone(nn.Module):
def __init__(self):
super(YOLOv5_backbone, self).__init__()
self.Conv_1 = Conv(3, 64, 3, 2, 2)
self.Conv_2 = Conv(64, 128, 3, 2)
self.C3_3 = C3(128,128)
self.Conv_4 = Conv(128, 256, 3, 2)
self.C3_5 = C3(256,256)
self.Conv_6 = Conv(256, 512, 3, 2)
self.C3_7 = C3(512,512)
self.Conv_8 = Conv(512, 1024, 3, 2)
self.C3_9 = C3(1024, 1024)
self.SPPF = SPPF(1024, 1024, 5)
# 全连接网络层，用于分类
self.classifier = nn.Sequential(
nn.Linear(in_features=65536, out_features=100),
nn.ReLU(),
nn.Linear(in_features=100, out_features=4)
)
def forward(self, x):
x = self.Conv_1(x)
x = self.Conv_2(x)
x = self.C3_3(x)
x = self.Conv_4(x)
x = self.C3_5(x)
x = self.Conv_6(x)
x = self.C3_7(x)
x = self.Conv_8(x)
x = self.C3_9(x)
x = self.SPPF(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 = YOLOv5_backbone().to(device)
modelUsing cuda device
YOLOv5_backbone(
(Conv_1): Conv(
(conv): Conv2d(3, 64, kernel_size=(3, 3), stride=(2, 2), padding=(2, 2), bias=False)
(bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): SiLU()
)
(Conv_2): Conv(
(conv): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): SiLU()
)
(C3_3): C3(
(cv1): Conv(
(conv): Conv2d(128, 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()
)
(cv2): Conv(
(conv): Conv2d(128, 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()
)
(cv3): Conv(
(conv): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): SiLU()
)
(m): Sequential(
(0): Bottleneck(
(cv1): 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()
)
(cv2): Conv(
(conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): SiLU()
)
)
)
)
(Conv_4): Conv(
(conv): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): SiLU()
)
(C3_5): C3(
(cv1): Conv(
(conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): SiLU()
)
(cv2): Conv(
(conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): SiLU()
)
(cv3): Conv(
(conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): SiLU()
)
(m): Sequential(
(0): Bottleneck(
(cv1): Conv(
(conv): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): SiLU()
)
(cv2): Conv(
(conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): SiLU()
)
)
)
)
(Conv_6): Conv(
(conv): Conv2d(256, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): SiLU()
)
(C3_7): C3(
(cv1): Conv(
(conv): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): SiLU()
)
(cv2): Conv(
(conv): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): SiLU()
)
(cv3): Conv(
(conv): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): SiLU()
)
(m): Sequential(
(0): Bottleneck(
(cv1): Conv(
(conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): SiLU()
)
(cv2): Conv(
(conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): SiLU()
)
)
)
)
(Conv_8): Conv(
(conv): Conv2d(512, 1024, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): SiLU()
)
(C3_9): C3(
(cv1): Conv(
(conv): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): SiLU()
)
(cv2): Conv(
(conv): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): SiLU()
)
(cv3): Conv(
(conv): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): SiLU()
)
(m): Sequential(
(0): Bottleneck(
(cv1): Conv(
(conv): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): SiLU()
)
(cv2): Conv(
(conv): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): SiLU()
)
)
)
)
(SPPF): SPPF(
(cv1): Conv(
(conv): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): SiLU()
)
(cv2): Conv(
(conv): Conv2d(2048, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): SiLU()
)
(m): MaxPool2d(kernel_size=5, stride=1, padding=2, dilation=1, ceil_mode=False)
)
(classifier): Sequential(
(0): Linear(in_features=65536, 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, 64, 113, 113] 1,728
BatchNorm2d-2 [-1, 64, 113, 113] 128
SiLU-3 [-1, 64, 113, 113] 0
Conv-4 [-1, 64, 113, 113] 0
Conv2d-5 [-1, 128, 57, 57] 73,728
BatchNorm2d-6 [-1, 128, 57, 57] 256
SiLU-7 [-1, 128, 57, 57] 0
Conv-8 [-1, 128, 57, 57] 0
Conv2d-9 [-1, 64, 57, 57] 8,192
BatchNorm2d-10 [-1, 64, 57, 57] 128
SiLU-11 [-1, 64, 57, 57] 0
Conv-12 [-1, 64, 57, 57] 0
Conv2d-13 [-1, 64, 57, 57] 4,096
BatchNorm2d-14 [-1, 64, 57, 57] 128
SiLU-15 [-1, 64, 57, 57] 0
Conv-16 [-1, 64, 57, 57] 0
Conv2d-17 [-1, 64, 57, 57] 36,864
BatchNorm2d-18 [-1, 64, 57, 57] 128
SiLU-19 [-1, 64, 57, 57] 0
Conv-20 [-1, 64, 57, 57] 0
Bottleneck-21 [-1, 64, 57, 57] 0
Conv2d-22 [-1, 64, 57, 57] 8,192
BatchNorm2d-23 [-1, 64, 57, 57] 128
SiLU-24 [-1, 64, 57, 57] 0
Conv-25 [-1, 64, 57, 57] 0
Conv2d-26 [-1, 128, 57, 57] 16,384
BatchNorm2d-27 [-1, 128, 57, 57] 256
SiLU-28 [-1, 128, 57, 57] 0
Conv-29 [-1, 128, 57, 57] 0
C3-30 [-1, 128, 57, 57] 0
Conv2d-31 [-1, 256, 29, 29] 294,912
BatchNorm2d-32 [-1, 256, 29, 29] 512
SiLU-33 [-1, 256, 29, 29] 0
Conv-34 [-1, 256, 29, 29] 0
Conv2d-35 [-1, 128, 29, 29] 32,768
BatchNorm2d-36 [-1, 128, 29, 29] 256
SiLU-37 [-1, 128, 29, 29] 0
Conv-38 [-1, 128, 29, 29] 0
Conv2d-39 [-1, 128, 29, 29] 16,384
BatchNorm2d-40 [-1, 128, 29, 29] 256
SiLU-41 [-1, 128, 29, 29] 0
Conv-42 [-1, 128, 29, 29] 0
Conv2d-43 [-1, 128, 29, 29] 147,456
BatchNorm2d-44 [-1, 128, 29, 29] 256
SiLU-45 [-1, 128, 29, 29] 0
Conv-46 [-1, 128, 29, 29] 0
Bottleneck-47 [-1, 128, 29, 29] 0
Conv2d-48 [-1, 128, 29, 29] 32,768
BatchNorm2d-49 [-1, 128, 29, 29] 256
SiLU-50 [-1, 128, 29, 29] 0
Conv-51 [-1, 128, 29, 29] 0
Conv2d-52 [-1, 256, 29, 29] 65,536
BatchNorm2d-53 [-1, 256, 29, 29] 512
SiLU-54 [-1, 256, 29, 29] 0
Conv-55 [-1, 256, 29, 29] 0
C3-56 [-1, 256, 29, 29] 0
Conv2d-57 [-1, 512, 15, 15] 1,179,648
BatchNorm2d-58 [-1, 512, 15, 15] 1,024
SiLU-59 [-1, 512, 15, 15] 0
Conv-60 [-1, 512, 15, 15] 0
Conv2d-61 [-1, 256, 15, 15] 131,072
BatchNorm2d-62 [-1, 256, 15, 15] 512
SiLU-63 [-1, 256, 15, 15] 0
Conv-64 [-1, 256, 15, 15] 0
Conv2d-65 [-1, 256, 15, 15] 65,536
BatchNorm2d-66 [-1, 256, 15, 15] 512
SiLU-67 [-1, 256, 15, 15] 0
Conv-68 [-1, 256, 15, 15] 0
Conv2d-69 [-1, 256, 15, 15] 589,824
BatchNorm2d-70 [-1, 256, 15, 15] 512
SiLU-71 [-1, 256, 15, 15] 0
Conv-72 [-1, 256, 15, 15] 0
Bottleneck-73 [-1, 256, 15, 15] 0
Conv2d-74 [-1, 256, 15, 15] 131,072
BatchNorm2d-75 [-1, 256, 15, 15] 512
SiLU-76 [-1, 256, 15, 15] 0
Conv-77 [-1, 256, 15, 15] 0
Conv2d-78 [-1, 512, 15, 15] 262,144
BatchNorm2d-79 [-1, 512, 15, 15] 1,024
SiLU-80 [-1, 512, 15, 15] 0
Conv-81 [-1, 512, 15, 15] 0
C3-82 [-1, 512, 15, 15] 0
Conv2d-83 [-1, 1024, 8, 8] 4,718,592
BatchNorm2d-84 [-1, 1024, 8, 8] 2,048
SiLU-85 [-1, 1024, 8, 8] 0
Conv-86 [-1, 1024, 8, 8] 0
Conv2d-87 [-1, 512, 8, 8] 524,288
BatchNorm2d-88 [-1, 512, 8, 8] 1,024
SiLU-89 [-1, 512, 8, 8] 0
Conv-90 [-1, 512, 8, 8] 0
Conv2d-91 [-1, 512, 8, 8] 262,144
BatchNorm2d-92 [-1, 512, 8, 8] 1,024
SiLU-93 [-1, 512, 8, 8] 0
Conv-94 [-1, 512, 8, 8] 0
Conv2d-95 [-1, 512, 8, 8] 2,359,296
BatchNorm2d-96 [-1, 512, 8, 8] 1,024
SiLU-97 [-1, 512, 8, 8] 0
Conv-98 [-1, 512, 8, 8] 0
Bottleneck-99 [-1, 512, 8, 8] 0
Conv2d-100 [-1, 512, 8, 8] 524,288
BatchNorm2d-101 [-1, 512, 8, 8] 1,024
SiLU-102 [-1, 512, 8, 8] 0
Conv-103 [-1, 512, 8, 8] 0
Conv2d-104 [-1, 1024, 8, 8] 1,048,576
BatchNorm2d-105 [-1, 1024, 8, 8] 2,048
SiLU-106 [-1, 1024, 8, 8] 0
Conv-107 [-1, 1024, 8, 8] 0
C3-108 [-1, 1024, 8, 8] 0
Conv2d-109 [-1, 512, 8, 8] 524,288
BatchNorm2d-110 [-1, 512, 8, 8] 1,024
SiLU-111 [-1, 512, 8, 8] 0
Conv-112 [-1, 512, 8, 8] 0
MaxPool2d-113 [-1, 512, 8, 8] 0
MaxPool2d-114 [-1, 512, 8, 8] 0
MaxPool2d-115 [-1, 512, 8, 8] 0
Conv2d-116 [-1, 1024, 8, 8] 2,097,152
BatchNorm2d-117 [-1, 1024, 8, 8] 2,048
SiLU-118 [-1, 1024, 8, 8] 0
Conv-119 [-1, 1024, 8, 8] 0
SPPF-120 [-1, 1024, 8, 8] 0
Linear-121 [-1, 100] 6,553,700
ReLU-122 [-1, 100] 0
Linear-123 [-1, 4] 404
================================================================
Total params: 21,729,592
Trainable params: 21,729,592
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 0.57
Forward/backward pass size (MB): 137.59
Params size (MB): 82.89
Estimated Total Size (MB): 221.06
----------------------------------------------------------------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_loss2. 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_loss3. 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 = 60
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))
# 保存最佳模型到文件中
PATH = './best_model.pth' # 保存的参数文件名
torch.save(best_model.state_dict(), PATH)
print('Done')Epoch: 1, Train_acc:56.6%, Train_loss:1.162, Test_acc:60.9%, Test_loss:0.849, Lr:1.00E-04
Epoch: 2, Train_acc:65.4%, Train_loss:0.833, Test_acc:74.7%, Test_loss:0.628, Lr:1.00E-04
Epoch: 3, Train_acc:72.6%, Train_loss:0.684, Test_acc:74.2%, Test_loss:0.606, Lr:1.00E-04
Epoch: 4, Train_acc:74.1%, Train_loss:0.620, Test_acc:68.4%, Test_loss:0.836, Lr:1.00E-04
Epoch: 5, Train_acc:77.3%, Train_loss:0.545, Test_acc:82.2%, Test_loss:0.476, Lr:1.00E-04
Epoch: 6, Train_acc:80.4%, Train_loss:0.498, Test_acc:83.1%, Test_loss:0.483, Lr:1.00E-04
Epoch: 7, Train_acc:81.2%, Train_loss:0.474, Test_acc:83.1%, Test_loss:0.467, Lr:1.00E-04
Epoch: 8, Train_acc:83.0%, Train_loss:0.446, Test_acc:80.0%, Test_loss:0.647, Lr:1.00E-04
Epoch: 9, Train_acc:86.2%, Train_loss:0.370, Test_acc:89.8%, Test_loss:0.375, Lr:1.00E-04
Epoch:10, Train_acc:84.0%, Train_loss:0.402, Test_acc:89.3%, Test_loss:0.475, Lr:1.00E-04
Epoch:11, Train_acc:86.4%, Train_loss:0.332, Test_acc:90.2%, Test_loss:0.422, Lr:1.00E-04
Epoch:12, Train_acc:88.9%, Train_loss:0.290, Test_acc:84.4%, Test_loss:0.466, Lr:1.00E-04
Epoch:13, Train_acc:88.4%, Train_loss:0.314, Test_acc:88.4%, Test_loss:0.466, Lr:1.00E-04
Epoch:14, Train_acc:90.9%, Train_loss:0.234, Test_acc:92.0%, Test_loss:0.335, Lr:1.00E-04
Epoch:15, Train_acc:92.9%, Train_loss:0.202, Test_acc:87.6%, Test_loss:0.357, Lr:1.00E-04
Epoch:16, Train_acc:92.8%, Train_loss:0.204, Test_acc:88.4%, Test_loss:0.387, Lr:1.00E-04
Epoch:17, Train_acc:90.8%, Train_loss:0.258, Test_acc:88.4%, Test_loss:0.387, Lr:1.00E-04
Epoch:18, Train_acc:92.0%, Train_loss:0.178, Test_acc:93.3%, Test_loss:0.372, Lr:1.00E-04
Epoch:19, Train_acc:95.0%, Train_loss:0.133, Test_acc:92.4%, Test_loss:0.351, Lr:1.00E-04
Epoch:20, Train_acc:95.6%, Train_loss:0.114, Test_acc:90.2%, Test_loss:0.409, Lr:1.00E-04
Epoch:21, Train_acc:96.1%, Train_loss:0.105, Test_acc:88.9%, Test_loss:0.532, Lr:1.00E-04
Epoch:22, Train_acc:94.4%, Train_loss:0.150, Test_acc:91.6%, Test_loss:0.391, Lr:1.00E-04
Epoch:23, Train_acc:96.1%, Train_loss:0.106, Test_acc:88.9%, Test_loss:0.471, Lr:1.00E-04
Epoch:24, Train_acc:97.9%, Train_loss:0.078, Test_acc:91.1%, Test_loss:0.500, Lr:1.00E-04
Epoch:25, Train_acc:97.8%, Train_loss:0.075, Test_acc:89.3%, Test_loss:0.522, Lr:1.00E-04
Epoch:26, Train_acc:94.6%, Train_loss:0.173, Test_acc:87.1%, Test_loss:0.694, Lr:1.00E-04
Epoch:27, Train_acc:95.2%, Train_loss:0.147, Test_acc:92.9%, Test_loss:0.431, Lr:1.00E-04
Epoch:28, Train_acc:97.2%, Train_loss:0.072, Test_acc:92.0%, Test_loss:0.474, Lr:1.00E-04
Epoch:29, Train_acc:97.2%, Train_loss:0.085, Test_acc:92.9%, Test_loss:0.488, Lr:1.00E-04
Epoch:30, Train_acc:96.8%, Train_loss:0.099, Test_acc:89.8%, Test_loss:0.664, Lr:1.00E-04
Epoch:31, Train_acc:96.8%, Train_loss:0.120, Test_acc:85.3%, Test_loss:0.775, Lr:1.00E-04
Epoch:32, Train_acc:97.4%, Train_loss:0.097, Test_acc:84.4%, Test_loss:0.686, Lr:1.00E-04
Epoch:33, Train_acc:97.2%, Train_loss:0.094, Test_acc:90.7%, Test_loss:0.484, Lr:1.00E-04
Epoch:34, Train_acc:98.4%, Train_loss:0.052, Test_acc:91.6%, Test_loss:0.481, Lr:1.00E-04
Epoch:35, Train_acc:98.4%, Train_loss:0.043, Test_acc:91.1%, Test_loss:0.591, Lr:1.00E-04
Epoch:36, Train_acc:98.6%, Train_loss:0.041, Test_acc:88.9%, Test_loss:0.709, Lr:1.00E-04
Epoch:37, Train_acc:97.3%, Train_loss:0.077, Test_acc:89.8%, Test_loss:0.669, Lr:1.00E-04
Epoch:38, Train_acc:98.2%, Train_loss:0.046, Test_acc:91.6%, Test_loss:0.667, Lr:1.00E-04
Epoch:39, Train_acc:97.4%, Train_loss:0.098, Test_acc:92.0%, Test_loss:0.518, Lr:1.00E-04
Epoch:40, Train_acc:97.4%, Train_loss:0.062, Test_acc:90.7%, Test_loss:0.572, Lr:1.00E-04
Epoch:41, Train_acc:97.1%, Train_loss:0.084, Test_acc:92.0%, Test_loss:0.623, Lr:1.00E-04
Epoch:42, Train_acc:98.9%, Train_loss:0.025, Test_acc:89.8%, Test_loss:0.853, Lr:1.00E-04
Epoch:43, Train_acc:98.7%, Train_loss:0.040, Test_acc:91.1%, Test_loss:0.617, Lr:1.00E-04
Epoch:44, Train_acc:98.9%, Train_loss:0.035, Test_acc:92.9%, Test_loss:0.457, Lr:1.00E-04
Epoch:45, Train_acc:100.0%, Train_loss:0.003, Test_acc:93.3%, Test_loss:0.486, Lr:1.00E-04
Epoch:46, Train_acc:99.3%, Train_loss:0.024, Test_acc:91.6%, Test_loss:0.522, Lr:1.00E-04
Epoch:47, Train_acc:97.2%, Train_loss:0.090, Test_acc:82.7%, Test_loss:0.790, Lr:1.00E-04
Epoch:48, Train_acc:95.4%, Train_loss:0.144, Test_acc:88.4%, Test_loss:0.700, Lr:1.00E-04
Epoch:49, Train_acc:99.1%, Train_loss:0.028, Test_acc:90.2%, Test_loss:0.700, Lr:1.00E-04
Epoch:50, Train_acc:98.7%, Train_loss:0.031, Test_acc:89.3%, Test_loss:0.787, Lr:1.00E-04
Epoch:51, Train_acc:98.1%, Train_loss:0.066, Test_acc:90.2%, Test_loss:0.523, Lr:1.00E-04
Epoch:52, Train_acc:98.8%, Train_loss:0.040, Test_acc:91.6%, Test_loss:0.534, Lr:1.00E-04
Epoch:53, Train_acc:98.2%, Train_loss:0.038, Test_acc:92.0%, Test_loss:0.426, Lr:1.00E-04
Epoch:54, Train_acc:99.6%, Train_loss:0.020, Test_acc:92.0%, Test_loss:0.431, Lr:1.00E-04
Epoch:55, Train_acc:99.9%, Train_loss:0.007, Test_acc:92.4%, Test_loss:0.413, Lr:1.00E-04
Epoch:56, Train_acc:99.2%, Train_loss:0.027, Test_acc:89.8%, Test_loss:0.557, Lr:1.00E-04
Epoch:57, Train_acc:99.6%, Train_loss:0.010, Test_acc:90.7%, Test_loss:0.514, Lr:1.00E-04
Epoch:58, Train_acc:100.0%, Train_loss:0.002, Test_acc:93.3%, Test_loss:0.432, Lr:1.00E-04
Epoch:59, Train_acc:99.9%, Train_loss:0.003, Test_acc:92.9%, Test_loss:0.637, Lr:1.00E-04
Epoch:60, Train_acc:100.0%, Train_loss:0.003, Test_acc:91.6%, Test_loss:0.478, Lr:1.00E-04
Done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
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.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
# 将参数加载到model当中
best_model.load_state_dict(torch.load(PATH, map_location=device))
epoch_test_acc, epoch_test_loss = test(test_dl, best_model, loss_fn)epoch_test_acc, epoch_test_loss(0.9333333333333333, 0.37150110182017415)
# 查看是否与我们记录的最高准确率一致
epoch_test_acc0.9333333333333333五、小结
spp介绍：
在卷积神经网络中我们经常看到固定输入的设计，但是如果我们输入的不能是固定尺寸的该怎么办呢？
通常来说，我们有以下几种方法：
（1）对输入进行resize操作，让他们统统变成你设计的层的输入规格那样。但是这样过于暴力直接，可能会丢失很多信息或者多出很多不该有的信息（图片变形等），影响最终的结果。
（2）替换网络中的全连接层，对最后的卷积层使用global average pooling，全局平均池化只和通道数有关，而与特征图大小没有关系
SPP结构又被称为空间金字塔池化，能将任意大小的特征图转换成固定大小的特征向量。
接下来我们来详述一下SPP是怎么处理滴~
输入层：首先我们现在有一张任意大小的图片，其大小为w * h。
输出层：21个神经元 -- 即我们待会希望提取到21个特征。
分析如下图所示：分别对1 * 1分块，2 * 2分块和4 * 4子图里分别取每一个框内的max值（即取蓝框框内的最大值），这一步就是作最大池化，这样最后提取出来的特征值（即取出来的最大值）一共有1 * 1 + 2 * 2 + 4 * 4 = 21个。得出的特征再concat在一起。
而在YOLOv5中SPP的结构图如下图所示：
sppf介绍：
（原文链接：https://blog.csdn.net/weixin_55073640/article/details/122621148）
252
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
