- 🍨 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
一边码字总结,一边跑着P10的代码,基础部分的学习到这就算告一段落了。下周开始进阶学习各类经典算法。2024年已经过半,人生有几多个10年,几多个10周,努力~🧗♂️
实验目的:
学习并理解本实验,尝试对单张车牌进行识别
实验环境:
- 语言环境:python 3.8
- 编译器:Google colab
- 深度学习环境:Pytorch
- torch==2.3.0+cu121
- torchvision==0.18.0+cu121
实验流程:
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,但是如果对无法分类的数据集,我们如何导入,并进行识别呢?本次实验将通过自定义一个MyDataset加载车牌数据集并完成车牌识别
1. 设置GPU
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")
device
2. 获取类别名
import os,PIL,random,pathlib
import matplotlib.pyplot as plt
plt.rcParams['font.sans-serif'] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
data_dir = '/content/drive/MyDrive/P10'
data_dir = pathlib.Path(data_dir)
data_paths = list(data_dir.glob('*'))
classeNames = [str(path).split("\\")[-1].split("_")[1].split(".")[0] for path in data_paths]
print(classeNames)
data_paths = list(data_dir.glob('*'))
data_paths_str = [str(path) for path in data_paths]
data_paths_str
3. 数据可视化
plt.figure(figsize=(14,5))
plt.suptitle("Samples",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()
4. 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]
5. 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 = './P10_traffic_sign/'
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_data
6. 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
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))
for X, y in test_loader:
print("Shape of X [N, C, H, W]: ", X.shape)
print("Shape of y: ", y.shape, y.dtype)
break
7. 搭建模型
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)
model
# 统计模型参数量以及其他指标
import torchsummary
torchsummary.summary(model, (3, 224, 224))
注意对比观察模型的输出[-1, 7, 69],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,那么本实验将是很好的示例。
📮提问:[-1, 7, 69]中的-1是什么意思?
**在神经网络中,如果我们不确定一个维度的大小,但是希望在计算中自动推断它,可以使用 -1。**这个-1告诉 PyTorch 在计算中自动推断这个维度的大小,以确保其他维度的尺寸不变,并且能够保持张量的总大小不变。
例如,[-1, 7, 69]表示这个张量的形状是一个三维张量,其中第一个维度的大小是不确定的,第二维大小为7,第三大小分别为69。-1的作用是使得总的张量大小等于7 * 69,以适应实际的输入数据大小。
在实际的使用中,通常-1用在批处理维度上,因为在训练过程中,批处理大小可能会有所不同。使用-1可以使模型适应不同大小的批处理输入数据。
8. 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()
本周任务之一:补充acc统计更新部分,即获取每一次测试的ACC值。
# 计算准确率部分即为补充代码
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()
# 计算准确率
pred = pred.view(-1, 69) # 将预测结果展平
y = y.view(-1, 69) # 将真实标签展平
_, predicted = torch.max(pred, 1)
_, target = torch.max(y, 1)
correct += (predicted == target).sum().item()
test_loss /= num_batches
accuracy = correct / size
print(f"Avg loss: {test_loss:>8f} \n")
print(f"Accuracy: {accuracy:>8f}")
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):
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))
9. 模型训练
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!")
10. 结果分析
import numpy as np
import matplotlib.pyplot as plt
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.legend()
plt.show()
11. 指定图片预测
from PIL import Image
classes = list(total_data.class_to_idx)
def predict_one_image(image_path, model, transform, classes):
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}')
# 预测训练集中的某张照片
predict_one_image(image_path='/content/drive/MyDrive/P10/000000005_湘G0H422.jpg',
model=model,
transform=train_transforms,
classes=classes)
12. 总结
本次实验主要是熟悉如何导入并识别无法分类的数据集,以及通过自定义一个MyDataset加载车牌数据集并完成车牌识别。同时理解了在要求模型输出结果是多维数据时,可以使用 -1 在计算中自动推断。由于近期任务比较繁重,所以这次实验有些划水了。原本想尝试作图对loss与accuracy进行实时显示,以及复习一些其他的操作都没有完成,希望下周开启进阶营后能多花些时间好好钻研。