第P4周-Pytorch实现猴痘病识别
- 🍨 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
目标
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
# 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
def data_from_directory(directory, show=True):
"""
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 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
""" print("数据目录:{}".format(directory))
data_dir = pathlib.Path(directory)
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))
temp_sum = 0
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
2. model.py
import torch.nn as nn
import torch
mport torch.nn.functional as F
class Network_bn(nn.Module):
def __init__(self, classNames):
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, len(classNames))
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)
return x
3. main.py
from mpmath.identification import transforms
from torch import nn
from Utils import USE_GPU, data_from_directory
from model import Network_bn
import torch
import torchvision
from torchvision import transforms, datasets
import os, PIL, pathlib
import matplotlib.pyplot as plt
device = USE_GPU()
DATA_DIR = "./data/monkeypox"
class_names = data_from_directory(DATA_DIR)
train_transforms = transforms.Compose([
transforms.Resize((224, 224)),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
])
total_data = datasets.ImageFolder(DATA_DIR, transform=train_transforms)
print(total_data)
print(total_data.class_to_idx)
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)
print("train size: {}, test size: {}".format(train_size, test_size))
batch_size = 32
train_dataloader = torch.utils.data.DataLoader(train_dataset, batch_size=batch_size, shuffle=True)
test_dataloader = torch.utils.data.DataLoader(test_dataset, batch_size=batch_size, shuffle=True)
for X, y in train_dataloader:
print("Shape of X[N, C, H, W]: ", X.shape)
print("Shape of y: ", y.shape)
break
model = Network_bn(class_names).to(device)
print(model)
loss_fn = nn.CrossEntropyLoss()
learn_rate = 1e-4
optimizer = torch.optim.SGD(model.parameters(), lr=learn_rate)
def train(dataloader, model, loss_fn, optimizer):
size = len(dataloader.dataset)
num_batches = len(dataloader)
train_loss, train_acc = 0, 0
for X, y in dataloader:
X, y = X.to(device), y.to(device)
pred = model(X)
loss = loss_fn(pred, y)
optimizer.zero_grad()
loss.backward()
optimizer.step()
train_loss += loss.item()
train_acc += (pred.argmax(1) == y).type(torch.float).sum().item()
train_acc /= size
train_loss /= num_batches
return train_acc, train_loss
def test(dataloader, model, loss_fn):
size = len(dataloader.dataset)
num_batches = len(dataloader)
test_loss, test_acc = 0, 0
with torch.no_grad():
for imgs, targets in dataloader:
imgs, targets = imgs.to(device), targets.to(device)
target_pred = model(imgs)
loss = loss_fn(target_pred, targets)
test_loss += loss.item()
test_acc += (target_pred.argmax(1) == targets).type(torch.float).sum().item()
test_acc /= size
test_loss /= num_batches
return test_acc, test_loss
epochs = 20
train_loss, train_acc, test_loss, test_acc = [], [], [], []
for epoch in range(epochs):
model.train()
epoch_train_acc, epoch_train_loss = train(train_dataloader, model, loss_fn, optimizer)
model.eval()
epoch_test_acc, epoch_test_loss = test(test_dataloader, model, loss_fn)
train_acc.append(epoch_train_acc)
test_acc.append(epoch_test_acc)
train_loss.append(epoch_train_loss)
test_loss.append(epoch_test_loss)
template = ('Epoch:{:2d}, Train_acc:{:.1f}%, Train_loss:{:.3f}, Test_acc:{:.1f}%,Test_loss:{:.3f}')
print(template.format(epoch + 1, epoch_train_acc * 100, epoch_train_loss, epoch_test_acc * 100, epoch_test_loss))
print('Done')