大家好，我是K同学啊，今天讲《深度学习100例》PyTorch版的第4个例子，前面一些例子主要还是以带大家了解PyTorch为主，建议手动敲一下代码，只有自己动手了，才能真正体会到里面的内容，光看不练是没有用的。今天的重点是在PyTorch调用VGG-16算法模型。先来了解一下PyTorch与TensorFlow的区别
PyTorch VS TensorFlow：
TensorFlow：简单，模块封装比较好，容易上手，对新手比较友好。在工业界最重要的是模型落地，目前国内的大部分企业支持TensorFlow模型在线部署，不支持Pytorch。PyTorch：前沿算法多为PyTorch版本，如果是你高校学生or研究人员，建议学这个。相对于TensorFlow，Pytorch在易用性上更有优势，更加方便调试。
当然如果你时间充足，我建议两个模型都是需要了解一下的，这两者都还是很重要的。
🍨 本文的重点：将讲解如何使用PyTorch构建神经网络模型（将对这一块展开详细的讲解）
🍖 我的环境：
- 语言环境：Python3.8
- 编译器：Jupyter Lab
- 深度学习环境：
- torch==1.10.0+cu113
- torchvision==0.11.1+cu113
- 创作平台：🔗 极链AI云
- 创作教程：🔎 操作手册
深度学习环境配置教程：小白入门深度学习 | 第四篇：配置PyTorch环境
👉 往期精彩内容
- 🔥 本文选自专栏：《深度学习100例》Pytorch版
- ? 镜像专栏：《深度学习100例》TensorFlow版
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
1. 获取类别名字
import os,PIL,random,pathlib
data_dir = './04-data/'
data_dir = pathlib.Path(data_dir)
data_paths = list(data_dir.glob('*'))
classeNames = [str(path).split("\\")[1] for path in data_paths]
classeNames
['Apple',
'Banana',
'Carambola',
'Guava',
'Kiwi',
'Mango',
'muskmelon',
'Orange',
'Peach',
'Pear',
'Persimmon',
'Pitaya',
'Plum',
'Pomegranate',
'Tomatoes']
2. 加载数据文件
total_datadir = './04-data/'
# 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 = datasets.ImageFolder(total_datadir,transform=train_transforms)
total_data
Dataset ImageFolder
Number of datapoints: 12000
Root location: ./04-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])
)
3. 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_dataset, test_dataset
(<torch.utils.data.dataset.Subset at 0x24bbdb84ac0>,
<torch.utils.data.dataset.Subset at 0x24bbdb84610>)
train_size,test_size
(9600, 2400)
train_loader = torch.utils.data.DataLoader(train_dataset,
batch_size=16,
shuffle=True,
num_workers=1)
test_loader = torch.utils.data.DataLoader(test_dataset,
batch_size=16,
shuffle=True,
num_workers=1)
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: 9600
The number of images in a test set is: 2400
The number of batches per epoch is: 600
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
Shape of X [N, C, H, W]: torch.Size([16, 3, 224, 224])
Shape of y: torch.Size([16]) torch.int64
二、自建模型
nn.Conv2d()函数：
- 第一个参数（in_channels）是输入的channel数量，彩色图片为3，黑白图片为1。
- 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，就是卷积操作时每次移动的格子数，默认为1
- 第五个参数（padding）是填充大小，默认为0
这里大家最难理解的可能就是nn.Linear(24*50*50, len(classeNames))这行代码了,在理解它之前你需要先补习一下👉卷积计算 的相关知识，然后可参照下面的网络结构图来进行理解
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, len(classeNames))
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
device = "cuda" if torch.cuda.is_available() else "cpu"
print("Using {} device".format(device))
model = Network_bn().to(device)
model
Using 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=15, bias=True)
)
三、模型训练
1. 优化器与损失函数
optimizer = torch.optim.Adam(model.parameters(), lr=0.0001, 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()
correct += (pred.argmax(1) == y).type(torch.float).sum().item()
test_loss /= num_batches
correct /= size
print(f"Test Error: \n Accuracy: {(100*correct):>0.1f}%, 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):
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 = []
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)
print("Done!")
Epoch 1
-------------------------------
[ 0] loss: 2.780
Test Error:
Accuracy: 85.8%, Avg loss: 0.440920
Epoch 2
-------------------------------
[ 0] loss: 0.468
Test Error:
Accuracy: 89.2%, Avg loss: 0.377265
......
Epoch 29
-------------------------------
[ 0] loss: 0.000
Test Error:
Accuracy: 91.2%, Avg loss: 0.885408
Epoch 30
-------------------------------
[ 0] loss: 0.000
Test Error:
Accuracy: 91.8%, Avg loss: 0.660563
Done!
四、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_acc_list, label="Accuracy", alpha=0.8)
plt.xlabel("Epoch")
plt.ylabel("Accuracy")
plt.legend()
plt.show()
