具体实现
（一）环境
语言环境：Python 3.10
编 译 器: PyCharm
框 架: Pytorch
（二）具体步骤
1. Utils.py
import torch
import pathlib
import matplotlib.pyplot as plt
from torchvision.transforms import transforms
# 第一步：设置GPU
def USE_GPU():
if torch.cuda.is_available():
print('CUDA is available, will use GPU')
device = torch.device("cuda")
else:
print('CUDA is not available. Will use CPU')
device = torch.device("cpu")
return device
temp_dict = dict()
def recursive_iterate(path):
"""
根据所提供的路径遍历该路径下的所有子目录，列出所有子目录下的文件
:param path: 路径
:return: 返回最后一级目录的数据
""" path = pathlib.Path(path)
for file in path.iterdir():
if file.is_file():
temp_key = str(file).split('\\')[-2]
if temp_key in temp_dict:
temp_dict.update({temp_key: temp_dict[temp_key] + 1})
else:
temp_dict.update({temp_key: 1})
# print(file)
elif file.is_dir():
recursive_iterate(file)
return temp_dict
def data_from_directory(directory, train_dir=None, test_dir=None, show=False):
"""
提供是的数据集是文件形式的，提供目录方式导入数据，简单分析数据并返回数据分类
:param test_dir: 是否设置了测试集目录
:param train_dir: 是否设置了训练集目录
:param directory: 数据集所在目录
:param show: 是否需要以柱状图形式显示数据分类情况,默认显示
:return: 数据分类列表,类型: list
""" global total_image
print("数据目录：{}".format(directory))
data_dir = pathlib.Path(directory)
# for d in data_dir.glob('**/*'): # **/*通配符可以遍历所有子目录
# if d.is_dir():
# print(d) class_name = []
total_image = 0
# temp_sum = 0
if train_dir is None or test_dir is None:
data_path = list(data_dir.glob('*'))
class_name = [str(path).split('\\')[-1] for path in data_path]
print("数据分类: {}, 类别数量：{}".format(class_name, len(list(data_dir.glob('*')))))
total_image = len(list(data_dir.glob('*/*')))
print("图片数据总数: {}".format(total_image))
else:
temp_dict.clear()
train_data_path = directory + '/' + train_dir
train_data_info = recursive_iterate(train_data_path)
print("{}目录:{},{}".format(train_dir, train_data_path, train_data_info))
temp_dict.clear()
test_data_path = directory + '/' + test_dir
print("{}目录:{},{}".format(test_dir, test_data_path, recursive_iterate(test_data_path)))
class_name = temp_dict.keys()
if show:
# 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
for i in class_name:
data = len(list(pathlib.Path((directory + '\\' + i + '\\')).glob('*')))
plt.title('数据分类情况')
plt.grid(ls='--', alpha=0.5)
plt.bar(i, data)
plt.text(i, data, str(data), ha='center', va='bottom')
print("类别-{}:{}".format(i, data))
# temp_sum += data
plt.show()
# if temp_sum == total_image:
# print("图片数据总数检查一致")
# else: # print("数据数据总数检查不一致，请检查数据集是否正确！")
return class_name
def get_transforms_setting(size):
"""
获取transforms的初始设置
:param size: 图片大小
:return: transforms.compose设置
""" transform_setting = {
'train': transforms.Compose([
transforms.Resize(size),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
]),
'test': transforms.Compose([
transforms.Resize(size),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
])
}
return transform_setting
# 训练循环
def train(dataloader, device, 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
def test(dataloader, device, 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
from PIL import Image
def predict_one_image(image_path, device, model, transform, classes):
"""
预测单张图片
:param image_path: 图片路径
:param device: CPU or GPU :param model: cnn模型
:param transform: :param classes: :return:
""" test_img = Image.open(image_path).convert('RGB')
plt.imshow(test_img) # 展示预测的图片
test_img = transform(test_img)
img = test_img.to(device).unsqueeze(0)
model.eval()
output = model(img)
_, pred = torch.max(output, 1)
pred_class = classes[pred]
print(f'预测结果是：{pred_class}')
2. config.py
import argparse
def get_options(parser=argparse.ArgumentParser()):
parser.add_argument('--workers', type=int, default=0, help='Number of parallel workers')
parser.add_argument('--batch-size', type=int, default=4, help='input batch size, default=32')
parser.add_argument('--lr', type=float, default=1e-4, help='learning rate, default=0.0001')
parser.add_argument('--epochs', type=int, default=20, help='number of epochs')
parser.add_argument('--seed', type=int, default=112, help='random seed')
parser.add_argument('--save-path', type=str, default='./models/', help='path to save checkpoints')
opt = parser.parse_args()
if opt:
print(f'num_workers:{opt.workers}')
print(f'batch_size:{opt.batch_size}')
print(f'learn rate:{opt.lr}')
print(f'epochs:{opt.epochs}')
print(f'random seed:{opt.seed}')
print(f'save_path:{opt.save_path}')
return opt
if __name__ == '__main__':
opt = get_options()
3. main.py
import torch
import torch.nn.functional as F
from sympy.codegen import Print
from torch import nn
from torchvision import transforms, datasets
from Utils import USE_GPU, data_from_directory, get_transforms_setting, train, test, predict_one_image
from config import get_options
import warnings
warnings.filterwarnings("ignore")
opt = get_options()
# 设置使用GPU
device = USE_GPU()
# 导入数据
DATA_DIR = "./data/weather_photos"
classNames = data_from_directory(DATA_DIR)
transform = get_transforms_setting([224, 224])
total_data = datasets.ImageFolder(DATA_DIR, transform=transform['train'])
print(total_data)
# 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])
print(train_dataset, test_dataset)
train_dl = torch.utils.data.DataLoader(train_dataset, batch_size=opt.batch_size, shuffle=True)
test_dl = torch.utils.data.DataLoader(test_dataset, batch_size=opt.batch_size, shuffle=True)
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
# 搭建模型
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 model_K(nn.Module):
def __init__(self):
super(model_K, self).__init__()
# 卷积模块
self.Conv = Conv(3, 32, 3, 2)
# C3模块1
self.C3_1 = C3(32, 64, 3, 2)
# 全连接网络层，用于分类
self.classifier = nn.Sequential(
nn.Linear(in_features=802816, out_features=100),
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
model = model_K().to(device)
print(model)
# 查看模型详情
import torchsummary as summary
summary.summary(model, (3, 224, 224))
# 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, device, model, loss_fn, optimizer)
model.eval()
epoch_test_acc, epoch_test_loss = test(test_dl, device, 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 = './models/weather-yolov5.pth' # 保存的参数文件名
torch.save(model.state_dict(), PATH)
print('Done')
# 模型训练结果可视化
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()
# 评估模型
best_model.eval()
epoch_test_acc, epoch_test_loss = test(test_dl, device, best_model, loss_fn)
print(epoch_test_acc, epoch_test_loss)
运行结果：
num_workers:0
batch_size:4
learn rate:0.0001
epochs:20
random seed:112
save_path:./models/
CUDA is available, will use GPU
数据目录：./data/weather_photos
数据分类: ['cloudy', 'rain', 'shine', 'sunrise'], 类别数量：4
图片数据总数: 1125
Dataset ImageFolder
Number of datapoints: 1125
Root location: ./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])
)
<torch.utils.data.dataset.Subset object at 0x000001A399B6BC70> <torch.utils.data.dataset.Subset object at 0x000001A399B6BBB0>
Shape of X[N, C, H, W]: torch.Size([4, 3, 224, 224])
Shape of y: torch.Size([4]) torch.int64
Using cuda device
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)
)
)
----------------------------------------------------------------
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: 80,320,536
Trainable params: 80,320,536
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 0.57
Forward/backward pass size (MB): 150.06
Params size (MB): 306.40
Estimated Total Size (MB): 457.04
----------------------------------------------------------------
Epoch: 1, Train_acc:69.0%, Train_loss:1.549, Test_acc:78.2%, Test_loss:0.632, Lr:1.00E-04
Epoch: 2, Train_acc:86.2%, Train_loss:0.429, Test_acc:82.7%, Test_loss:0.521, Lr:1.00E-04
Epoch: 3, Train_acc:91.8%, Train_loss:0.225, Test_acc:85.3%, Test_loss:0.512, Lr:1.00E-04
Epoch: 4, Train_acc:92.0%, Train_loss:0.220, Test_acc:91.6%, Test_loss:0.435, Lr:1.00E-04
Epoch: 5, Train_acc:94.6%, Train_loss:0.187, Test_acc:87.6%, Test_loss:0.564, Lr:1.00E-04
Epoch: 6, Train_acc:96.0%, Train_loss:0.118, Test_acc:88.0%, Test_loss:0.536, Lr:1.00E-04
Epoch: 7, Train_acc:98.1%, Train_loss:0.073, Test_acc:91.1%, Test_loss:0.551, Lr:1.00E-04
Epoch: 8, Train_acc:99.0%, Train_loss:0.045, Test_acc:87.1%, Test_loss:0.665, Lr:1.00E-04
Epoch: 9, Train_acc:99.0%, Train_loss:0.029, Test_acc:88.9%, Test_loss:0.560, Lr:1.00E-04
Epoch:10, Train_acc:98.9%, Train_loss:0.028, Test_acc:83.6%, Test_loss:1.033, Lr:1.00E-04
Epoch:11, Train_acc:98.9%, Train_loss:0.046, Test_acc:86.7%, Test_loss:0.870, Lr:1.00E-04
Epoch:12, Train_acc:98.1%, Train_loss:0.058, Test_acc:89.3%, Test_loss:0.658, Lr:1.00E-04
Epoch:13, Train_acc:98.4%, Train_loss:0.076, Test_acc:87.6%, Test_loss:0.628, Lr:1.00E-04
Epoch:14, Train_acc:96.6%, Train_loss:0.157, Test_acc:88.0%, Test_loss:0.885, Lr:1.00E-04
Epoch:15, Train_acc:98.1%, Train_loss:0.133, Test_acc:88.9%, Test_loss:0.922, Lr:1.00E-04
Epoch:16, Train_acc:98.4%, Train_loss:0.050, Test_acc:88.0%, Test_loss:0.976, Lr:1.00E-04
Epoch:17, Train_acc:99.6%, Train_loss:0.024, Test_acc:88.0%, Test_loss:0.922, Lr:1.00E-04
Epoch:18, Train_acc:98.7%, Train_loss:0.059, Test_acc:89.8%, Test_loss:0.885, Lr:1.00E-04
Epoch:19, Train_acc:98.9%, Train_loss:0.053, Test_acc:90.2%, Test_loss:0.727, Lr:1.00E-04
Epoch:20, Train_acc:99.0%, Train_loss:0.040, Test_acc:82.7%, Test_loss:2.917, Lr:1.00E-04
Done
0.9155555555555556 0.4347304363102905
进程已结束，退出代码为 0
