第P9周：YOLOv5-Backbone模块实现
第P9周：YOLOv5-Backbone模块实现
● 本文为365天深度学习训练营 中的学习记录博客
● 参考文章：Pytorch实战 | 第P9周：YOLOv5-Backbone模块实现(训练营内部成员可读)
● 原作者：K同学啊|接辅导、项目定制
本次我将利用YOLOv5算法中的Backbone模块搭建网络，后续理论部分介绍将在语雀以及公众号（K同学啊）中详细展开，本次内容除了网络结构部分外，其余部分均与上周相同。
YOLOv5是目标检测算法，是否可以尝试将其网络结构用在目标识别上，或进行改进形成一个全新的算法（类似之前介绍过的VGG1-6）。如果效果不错的话，还可以搞一篇期刊文章出来~
分享一张我自己绘制的YOLOv5_6.0版本的算法框架图，希望它可以有助于你完成本次探索~
前期准备
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") #忽略警告信息
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
device
device(type='cpu')
导入数据
import os,PIL,random,pathlib
data_dir = '/home/liangjie/test/Modelwhale/deep learning/P9/9-data'
data_dir = pathlib.Path(data_dir)
data_paths = list(data_dir.glob('*'))
classeNames = [str(path).split("/")[-1] for path in data_paths]
classeNames
['cloudy', 'rain', 'shine', 'sunrise']
# 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("./9-data/",transform=train_transforms)
total_data
Dataset ImageFolder
Number of datapoints: 1125
Root location: ./9-data/
StandardTransform
Transform: Compose(
Resize(size=[224, 224], interpolation=bilinear, max_size=None, antialias=None)
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}
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
(,
)
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
搭建包含Backbone模块的模型
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)
model
Using cpu 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)
)
)
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
----------------------------------------------------------------
训练模型
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
编写测试函数
测试函数和训练函数大致相同，但是由于不进行梯度下降对网络权重进行更新，所以不需要传入优化器
# 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
正式训练
model.train()、model.eval()训练营往期文章中有详细的介绍。
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:54.2%, Train_loss:1.157, Test_acc:68.9%, Test_loss:0.832, Lr:1.00E-04
Epoch: 2, Train_acc:63.3%, Train_loss:0.866, Test_acc:57.8%, Test_loss:0.974, Lr:1.00E-04
Epoch: 3, Train_acc:74.9%, Train_loss:0.638, Test_acc:79.6%, Test_loss:0.505, Lr:1.00E-04
Epoch: 4, Train_acc:75.9%, Train_loss:0.621, Test_acc:79.6%, Test_loss:0.508, Lr:1.00E-04
Epoch: 5, Train_acc:81.6%, Train_loss:0.503, Test_acc:76.4%, Test_loss:0.673, Lr:1.00E-04
Epoch: 6, Train_acc:80.7%, Train_loss:0.497, Test_acc:82.2%, Test_loss:0.469, Lr:1.00E-04
Epoch: 7, Train_acc:84.0%, Train_loss:0.435, Test_acc:77.3%, Test_loss:0.675, Lr:1.00E-04
Epoch: 8, Train_acc:87.0%, Train_loss:0.357, Test_acc:86.2%, Test_loss:0.346, Lr:1.00E-04
Epoch: 9, Train_acc:91.4%, Train_loss:0.262, Test_acc:90.2%, Test_loss:0.266, Lr:1.00E-04
Epoch:10, Train_acc:90.3%, Train_loss:0.274, Test_acc:88.0%, Test_loss:0.336, Lr:1.00E-04
Epoch:11, Train_acc:92.7%, Train_loss:0.236, Test_acc:92.0%, Test_loss:0.174, Lr:1.00E-04
Epoch:12, Train_acc:91.8%, Train_loss:0.222, Test_acc:90.2%, Test_loss:0.325, Lr:1.00E-04
Epoch:13, Train_acc:93.9%, Train_loss:0.168, Test_acc:88.9%, Test_loss:0.400, Lr:1.00E-04
Epoch:14, Train_acc:94.3%, Train_loss:0.204, Test_acc:89.3%, Test_loss:0.391, Lr:1.00E-04
Epoch:15, Train_acc:91.1%, Train_loss:0.249, Test_acc:86.7%, Test_loss:0.395, Lr:1.00E-04
Epoch:16, Train_acc:93.8%, Train_loss:0.188, Test_acc:88.9%, Test_loss:0.273, Lr:1.00E-04
Epoch:17, Train_acc:95.2%, Train_loss:0.133, Test_acc:86.7%, Test_loss:0.409, Lr:1.00E-04
Epoch:18, Train_acc:94.8%, Train_loss:0.141, Test_acc:88.9%, Test_loss:0.356, Lr:1.00E-04
Epoch:19, Train_acc:97.2%, Train_loss:0.087, Test_acc:93.8%, Test_loss:0.214, Lr:1.00E-04
Epoch:20, Train_acc:97.4%, Train_loss:0.071, Test_acc:92.9%, Test_loss:0.287, Lr:1.00E-04
Epoch:21, Train_acc:96.0%, Train_loss:0.128, Test_acc:88.9%, Test_loss:0.319, Lr:1.00E-04
Epoch:22, Train_acc:95.8%, Train_loss:0.114, Test_acc:87.1%, Test_loss:0.411, Lr:1.00E-04
Epoch:23, Train_acc:96.1%, Train_loss:0.099, Test_acc:93.3%, Test_loss:0.244, Lr:1.00E-04
Epoch:24, Train_acc:98.3%, Train_loss:0.045, Test_acc:92.9%, Test_loss:0.205, Lr:1.00E-04
Epoch:25, Train_acc:98.3%, Train_loss:0.051, Test_acc:89.8%, Test_loss:0.376, Lr:1.00E-04
Epoch:26, Train_acc:94.3%, Train_loss:0.168, Test_acc:91.1%, Test_loss:0.357, Lr:1.00E-04
Epoch:27, Train_acc:96.0%, Train_loss:0.114, Test_acc:89.8%, Test_loss:0.412, Lr:1.00E-04
Epoch:28, Train_acc:98.4%, Train_loss:0.057, Test_acc:92.9%, Test_loss:0.312, Lr:1.00E-04
Epoch:29, Train_acc:98.2%, Train_loss:0.049, Test_acc:90.2%, Test_loss:0.439, Lr:1.00E-04
Epoch:30, Train_acc:97.7%, Train_loss:0.059, Test_acc:95.1%, Test_loss:0.298, Lr:1.00E-04
Epoch:31, Train_acc:98.1%, Train_loss:0.062, Test_acc:92.4%, Test_loss:0.317, Lr:1.00E-04
Epoch:32, Train_acc:97.4%, Train_loss:0.075, Test_acc:90.2%, Test_loss:0.290, Lr:1.00E-04
Epoch:33, Train_acc:97.4%, Train_loss:0.057, Test_acc:87.1%, Test_loss:0.442, Lr:1.00E-04
Epoch:34, Train_acc:97.2%, Train_loss:0.075, Test_acc:91.1%, Test_loss:0.317, Lr:1.00E-04
Epoch:35, Train_acc:97.1%, Train_loss:0.074, Test_acc:89.3%, Test_loss:0.319, Lr:1.00E-04
Epoch:36, Train_acc:97.2%, Train_loss:0.066, Test_acc:90.7%, Test_loss:0.386, Lr:1.00E-04
Epoch:37, Train_acc:96.8%, Train_loss:0.109, Test_acc:90.2%, Test_loss:0.528, Lr:1.00E-04
Epoch:38, Train_acc:93.4%, Train_loss:0.221, Test_acc:88.4%, Test_loss:0.548, Lr:1.00E-04
Epoch:39, Train_acc:97.6%, Train_loss:0.078, Test_acc:89.8%, Test_loss:0.371, Lr:1.00E-04
Epoch:40, Train_acc:99.2%, Train_loss:0.015, Test_acc:90.2%, Test_loss:0.338, Lr:1.00E-04
Epoch:41, Train_acc:99.4%, Train_loss:0.016, Test_acc:92.4%, Test_loss:0.279, Lr:1.00E-04
Epoch:42, Train_acc:100.0%, Train_loss:0.004, Test_acc:92.4%, Test_loss:0.240, Lr:1.00E-04
Epoch:43, Train_acc:100.0%, Train_loss:0.001, Test_acc:91.6%, Test_loss:0.235, Lr:1.00E-04
Epoch:44, Train_acc:99.9%, Train_loss:0.004, Test_acc:93.3%, Test_loss:0.276, Lr:1.00E-04
Epoch:45, Train_acc:99.9%, Train_loss:0.004, Test_acc:94.2%, Test_loss:0.233, Lr:1.00E-04
Epoch:46, Train_acc:100.0%, Train_loss:0.001, Test_acc:92.4%, Test_loss:0.274, Lr:1.00E-04
Epoch:47, Train_acc:95.7%, Train_loss:0.171, Test_acc:89.3%, Test_loss:0.527, Lr:1.00E-04
Epoch:48, Train_acc:96.7%, Train_loss:0.099, Test_acc:89.3%, Test_loss:0.285, Lr:1.00E-04
Epoch:49, Train_acc:99.3%, Train_loss:0.022, Test_acc:90.7%, Test_loss:0.226, Lr:1.00E-04
Epoch:50, Train_acc:99.3%, Train_loss:0.020, Test_acc:91.6%, Test_loss:0.334, Lr:1.00E-04
Epoch:51, Train_acc:97.9%, Train_loss:0.074, Test_acc:84.4%, Test_loss:0.626, Lr:1.00E-04
Epoch:52, Train_acc:98.6%, Train_loss:0.053, Test_acc:91.1%, Test_loss:0.376, Lr:1.00E-04
Epoch:53, Train_acc:99.8%, Train_loss:0.008, Test_acc:90.2%, Test_loss:0.332, Lr:1.00E-04
Epoch:54, Train_acc:100.0%, Train_loss:0.003, Test_acc:93.8%, Test_loss:0.225, Lr:1.00E-04
Epoch:55, Train_acc:100.0%, Train_loss:0.002, Test_acc:94.7%, Test_loss:0.213, Lr:1.00E-04
Epoch:56, Train_acc:100.0%, Train_loss:0.002, Test_acc:95.1%, Test_loss:0.210, Lr:1.00E-04
Epoch:57, Train_acc:97.3%, Train_loss:0.088, Test_acc:85.3%, Test_loss:0.907, Lr:1.00E-04
Epoch:58, Train_acc:97.0%, Train_loss:0.127, Test_acc:89.8%, Test_loss:0.394, Lr:1.00E-04
Epoch:59, Train_acc:98.1%, Train_loss:0.072, Test_acc:94.7%, Test_loss:0.223, Lr:1.00E-04
Epoch:60, Train_acc:99.0%, Train_loss:0.028, Test_acc:90.2%, Test_loss:0.408, Lr:1.00E-04
Done
结果可视化
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()
findfont: Font family ['sans-serif'] not found. Falling back to DejaVu Sans.
findfont: Generic family 'sans-serif' not found because none of the following families were found: SimHei
findfont: Font family ['sans-serif'] not found. Falling back to DejaVu Sans.
findfont: Generic family 'sans-serif' not found because none of the following families were found: SimHei
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
(0.9511111111111111, 0.2984761347562884)
# 查看是否与我们记录的最高准确率一致
epoch_test_acc
0.9511111111111111
识别本地图片
local_test_image = PIL.Image.open ("/home/liangjie/test/Modelwhale/deep learning/P9/p3_testdata/c3.jpg").convert('RGB')
#local_test_data = torchvision.transforms.functional.resize(local_test_data,[224,224])
local_transforms = 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
])
local_test_data = local_transforms(local_test_image)
PIL.Image.open ("/home/liangjie/test/Modelwhale/deep learning/P9/p3_testdata/c3.jpg").convert('RGB')##显示照片
_,result=torch.max(model(local_test_data.to(device).unsqueeze(0)),1)
classeNames[result]
'rain'
local_test_image = PIL.Image.open ("/home/liangjie/test/Modelwhale/deep learning/P9/p3_testdata/r1.jpg").convert('RGB')
#local_test_data = torchvision.transforms.functional.resize(local_test_data,[224,224])
local_transforms = 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
])
local_test_data = local_transforms(local_test_image)
PIL.Image.open ("/home/liangjie/test/Modelwhale/deep learning/P9/p3_testdata/r1.jpg").convert('RGB')##显示照片
_,result=torch.max(model(local_test_data.to(device).unsqueeze(0)),1)
classeNames[result]
'rain'