目录
前言
- 🍨 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
一、导入数据
from torchvision.transforms import transforms
from torch.utils.data import DataLoader
from torchvision import datasets
import torchvision.models as models
import torch.nn.functional as F
import torch.nn as nn
import torch,torchvision
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
device1. 获取类别名
data_paths = list(data_dir.glob('*'))
data_paths_str = [str(path) for path in data_paths]
data_paths_str['沪G1CE81', '云G86LR6', '鄂U71R9F'。。。'辽Z9C5T4', '贵NY7W90', '渝H3V0S4', '蒙A05N5Y']
data_paths = list(data_dir.glob('*'))
data_paths_str = [str(path) for path in data_paths]
data_paths_str['/Users/Downloads/015_licence_plate/000008250_沪G1CE81.jpg', '/Users/Downloads/015_licence_plate/000015082_云G86LR6.jpg', '/Users/Downloads/015_licence_plate/000004721_鄂U71R9F.jpg',。。。'/Users/haorunkun/Downloads/015_licence_plate/000006515_鄂Q8S08J.jpg', ...]
2. 数据可视化
plt.figure(figsize=(14,5))
plt.suptitle("数据示例",fontsize=15)
for i in range(18):
plt.subplot(3,6,i+1)
# plt.xticks([])
# plt.yticks([])
# plt.grid(False)
# 显示图片
images = plt.imread(data_paths_str[i])
plt.imshow(images)
plt.show()
3. 标签数字化
import numpy as np
char_enum = ["京","沪","津","渝","冀","晋","蒙","辽","吉","黑","苏","浙","皖","闽","赣","鲁",\
"豫","鄂","湘","粤","桂","琼","川","贵","云","藏","陕","甘","青","宁","新","军","使"]
number = [str(i) for i in range(0, 10)] # 0 到 9 的数字
alphabet = [chr(i) for i in range(65, 91)] # A 到 Z 的字母
char_set = char_enum + number + alphabet
char_set_len = len(char_set)
label_name_len = len(classeNames[0])
# 将字符串数字化
def text2vec(text):
vector = np.zeros([label_name_len, char_set_len])
for i, c in enumerate(text):
idx = char_set.index(c)
vector[i][idx] = 1.0
return vector
all_labels = [text2vec(i) for i in classeNames]4. 加载数据文件
import os
import pandas as pd
from torchvision.io import read_image
from torch.utils.data import Dataset
import torch.utils.data as data
from PIL import Image
class MyDataset(data.Dataset):
def __init__(self, all_labels, data_paths_str, transform):
self.img_labels = all_labels # 获取标签信息
self.img_dir = data_paths_str # 图像目录路径
self.transform = transform # 目标转换函数
def __len__(self):
return len(self.img_labels)
def __getitem__(self, index):
image = Image.open(self.img_dir[index]).convert('RGB')#plt.imread(self.img_dir[index]) # 使用 torchvision.io.read_image 读取图像
label = self.img_labels[index] # 获取图像对应的标签
if self.transform:
image = self.transform(image)
return image, label # 返回图像和标签total_datadir = './03_traffic_sign/'
# 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.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 = MyDataset(all_labels, data_paths_str, train_transforms)
total_data5. 划分数据
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_size,test_size(10940, 2735)
train_loader = torch.utils.data.DataLoader(train_dataset,
batch_size=16,
shuffle=True)
test_loader = torch.utils.data.DataLoader(test_dataset,
batch_size=16,
shuffle=True)
print("The number of images in a training set is: ", len(train_loader)*16)
print("The number of images in a test set is: ", len(test_loader)*16)
print("The number of batches per epoch is: ", len(train_loader))The number of images in a training set is: 10944
The number of images in a test set is: 2736
The number of batches per epoch is: 684
for X, y in test_loader:
print("Shape of X [N, C, H, W]: ", X.shape)
print("Shape of y: ", y.shape, y.dtype)
breakShape of X [N, C, H, W]: torch.Size([16, 3, 224, 224])
Shape of y: torch.Size([16, 7, 69]) torch.float64
二、自建模型
class Network_bn(nn.Module):
def __init__(self):
super(Network_bn, self).__init__()
"""
nn.Conv2d()函数：
第一个参数（in_channels）是输入的channel数量
第二个参数（out_channels）是输出的channel数量
第三个参数（kernel_size）是卷积核大小
第四个参数（stride）是步长，默认为1
第五个参数（padding）是填充大小，默认为0
"""
self.conv1 = nn.Conv2d(in_channels=3, out_channels=12, kernel_size=5, stride=1, padding=0)
self.bn1 = nn.BatchNorm2d(12)
self.conv2 = nn.Conv2d(in_channels=12, out_channels=12, kernel_size=5, stride=1, padding=0)
self.bn2 = nn.BatchNorm2d(12)
self.pool = nn.MaxPool2d(2,2)
self.conv4 = nn.Conv2d(in_channels=12, out_channels=24, kernel_size=5, stride=1, padding=0)
self.bn4 = nn.BatchNorm2d(24)
self.conv5 = nn.Conv2d(in_channels=24, out_channels=24, kernel_size=5, stride=1, padding=0)
self.bn5 = nn.BatchNorm2d(24)
self.fc1 = nn.Linear(24*50*50, label_name_len*char_set_len)
self.reshape = Reshape([label_name_len,char_set_len])
def forward(self, x):
x = F.relu(self.bn1(self.conv1(x)))
x = F.relu(self.bn2(self.conv2(x)))
x = self.pool(x)
x = F.relu(self.bn4(self.conv4(x)))
x = F.relu(self.bn5(self.conv5(x)))
x = self.pool(x)
x = x.view(-1, 24*50*50)
x = self.fc1(x)
# 最终reshape
x = self.reshape(x)
return x
# 定义Reshape层
class Reshape(nn.Module):
def __init__(self, shape):
super(Reshape, self).__init__()
self.shape = shape
def forward(self, x):
return x.view(x.size(0), *self.shape)
device = "cuda" if torch.cuda.is_available() else "cpu"
print("Using {} device".format(device))
model = Network_bn().to(device)
modelUsing cuda device
Network_bn(
(conv1): Conv2d(3, 12, kernel_size=(5, 5), stride=(1, 1))
(bn1): BatchNorm2d(12, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(12, 12, kernel_size=(5, 5), stride=(1, 1))
(bn2): BatchNorm2d(12, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(pool): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(conv4): Conv2d(12, 24, kernel_size=(5, 5), stride=(1, 1))
(bn4): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv5): Conv2d(24, 24, kernel_size=(5, 5), stride=(1, 1))
(bn5): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(fc1): Linear(in_features=60000, out_features=483, bias=True)
(reshape): Reshape()
)
import torchsummary
''' 显示网络结构 '''
torchsummary.summary(model, (3, 224, 224))----------------------------------------------------------------
Layer (type) Output Shape Param #
================================================================
Conv2d-1 [-1, 12, 220, 220] 912
BatchNorm2d-2 [-1, 12, 220, 220] 24
Conv2d-3 [-1, 12, 216, 216] 3,612
BatchNorm2d-4 [-1, 12, 216, 216] 24
MaxPool2d-5 [-1, 12, 108, 108] 0
Conv2d-6 [-1, 24, 104, 104] 7,224
BatchNorm2d-7 [-1, 24, 104, 104] 48
Conv2d-8 [-1, 24, 100, 100] 14,424
BatchNorm2d-9 [-1, 24, 100, 100] 48
MaxPool2d-10 [-1, 24, 50, 50] 0
Linear-11 [-1, 483] 28,980,483
Reshape-12 [-1, 7, 69] 0
================================================================
Total params: 29,006,799
Trainable params: 29,006,799
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 0.57
Forward/backward pass size (MB): 26.56
Params size (MB): 110.65
Estimated Total Size (MB): 137.79
----------------------------------------------------------------
三、模型训练
1. 优化器与损失函数
optimizer = torch.optim.Adam(model.parameters(),
lr=1e-4,
weight_decay=0.0001)
loss_model = nn.CrossEntropyLoss()from torch.autograd import Variable
def test(model, test_loader, loss_model):
size = len(test_loader.dataset)
num_batches = len(test_loader)
model.eval()
test_loss, correct = 0, 0
with torch.no_grad():
for X, y in test_loader:
X, y = X.to(device), y.to(device)
pred = model(X)
test_loss += loss_model(pred, y).item()
test_loss /= num_batches
print(f"Avg loss: {test_loss:>8f} \n")
return correct,test_loss
def train(model,train_loader,loss_model,optimizer):
model=model.to(device)
model.train()
for i, (images, labels) in enumerate(train_loader, 0): #0是标起始位置的值。
images = Variable(images.to(device))
labels = Variable(labels.to(device))
optimizer.zero_grad()
outputs = model(images)
loss = loss_model(outputs, labels)
loss.backward()
optimizer.step()
if i % 1000 == 0:
print('[%5d] loss: %.3f' % (i, loss))2. 模型的训练
test_acc_list = []
test_loss_list = []
epochs = 30
for t in range(epochs):
print(f"Epoch {t+1}\n-------------------------------")
train(model,train_loader,loss_model,optimizer)
test_acc,test_loss = test(model, test_loader, loss_model)
test_acc_list.append(test_acc)
test_loss_list.append(test_loss)
print("Done!")
。。。
四、结果分析
import numpy as np
import matplotlib.pyplot as plt
from datetime import datetime
current_time = datetime.now() # 获取当前时间
x = [i for i in range(1,31)]
plt.plot(x, test_loss_list, label="Loss", alpha=0.8)
plt.xlabel("Epoch")
plt.ylabel("Loss")
plt.title(current_time) # 打卡请带上时间戳，否则代码截图无效
plt.legend()
plt.show()
五、总结
在之前的案例中，我们多是使用datasets.ImageFolder函数直接导入已经分类好的数据集形成Dataset，然后使用DataLoader加载Dataset，但是这次对无法分类数据集，自定义一个MyDataset加载车牌数据集并完成车牌识别。模型的输出[-1, 7, 69]，我们之前的网络结构输出都是[-1, 7]、[-1, 2]、[-1, 4]这样的二维数据，如果要求模型输出结果是多维数据，那么本案例将是很好的示例