1.参考视频:
2.1 pytorch官方demo(Lenet)_哔哩哔哩_bilibili
2.总结:
(1)LeNet网络就是 我最开始用来预测mnist数据集的那个网络,简单的2个conv+2个maxpool+3个linear层
(2)up主整理的train.py等内容里面的细节分析值得学习
(3)对于预测代码的撰写,可以参考代码的predict.py文件
3.几个文件的源代码我都贴一下(都不多——但很精):
(1)首先是 model.py:
import torch.nn as nn
import torch.nn.functional as F
class LeNet(nn.Module):
def __init__(self):
super(LeNet, self).__init__()
self.conv1 = nn.Conv2d(3, 16, 5)
self.pool1 = nn.MaxPool2d(2, 2)
self.conv2 = nn.Conv2d(16, 32, 5)
self.pool2 = nn.MaxPool2d(2, 2)
self.fc1 = nn.Linear(32*5*5, 120)
self.fc2 = nn.Linear(120, 84)
self.fc3 = nn.Linear(84, 10)
def forward(self, x):
x = F.relu(self.conv1(x)) # input(3, 32, 32) output(16, 28, 28)
x = self.pool1(x) # output(16, 14, 14)
x = F.relu(self.conv2(x)) # output(32, 10, 10)
x = self.pool2(x) # output(32, 5, 5)
x = x.view(-1, 32*5*5) # output(32*5*5)
x = F.relu(self.fc1(x)) # output(120)
x = F.relu(self.fc2(x)) # output(84)
x = self.fc3(x) # output(10)
return x
模型 == 2个conv + 2个max_pool + 3个linear
(2) train.py训练模型的文件:
import torch
import torchvision
import torch.nn as nn
from model import LeNet
import torch.optim as optim
import torchvision.transforms as transforms
def main():
# 定义transform的数据增强
transform = transforms.Compose(
[transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])
# 处理cifar10的 train和val的数据集的问题
# 50000张训练图片
# 第一次使用时要将download设置为True才会自动去下载数据集
train_set = torchvision.datasets.CIFAR10(root='./data', train=True,
download=False, transform=transform)
train_loader = torch.utils.data.DataLoader(train_set, batch_size=36,
shuffle=True, num_workers=0)
# 10000张验证图片
# 第一次使用时要将download设置为True才会自动去下载数据集
val_set = torchvision.datasets.CIFAR10(root='./data', train=False,
download=False, transform=transform)
val_loader = torch.utils.data.DataLoader(val_set, batch_size=5000,
shuffle=False, num_workers=0)
val_data_iter = iter(val_loader)
val_image, val_label = next(val_data_iter)
# classes = ('plane', 'car', 'bird', 'cat',
# 'deer', 'dog', 'frog', 'horse', 'ship', 'truck')
# 训练前的准备: 实例化model网络net , 定义 loss函数 CrossEntropyLoss() 和 Adam优化器
net = LeNet()
loss_function = nn.CrossEntropyLoss()
optimizer = optim.Adam(net.parameters(), lr=0.001)
# 开始训练:zero_grad() + outputs + loss backward + optim step
for epoch in range(5): # loop over the dataset multiple times
running_loss = 0.0
for step, data in enumerate(train_loader, start=0):
# get the inputs; data is a list of [inputs, labels]
inputs, labels = data
# zero the parameter gradients
optimizer.zero_grad()
# forward + backward + optimize
outputs = net(inputs)
loss = loss_function(outputs, labels)
loss.backward()
optimizer.step()
# print statistics
running_loss += loss.item()
if step % 500 == 499: # print every 500 mini-batches
with torch.no_grad():
outputs = net(val_image) # [batch, 10]
predict_y = torch.max(outputs, dim=1)[1]
accuracy = torch.eq(predict_y, val_label).sum().item() / val_label.size(0)
print('[%d, %5d] train_loss: %.3f test_accuracy: %.3f' %
(epoch + 1, step + 1, running_loss / 500, accuracy))
running_loss = 0.0
print('Finished Training')
# 最后把 model的 参数save 为一个.pth文件
save_path = './Lenet.pth'
torch.save(net.state_dict(), save_path)
if __name__ == '__main__':
main()
分析:数据集划分 + 实例化网络_优化器_loss函数 + 分epoch开始寻 + save_pth权重
(3)predict.py:
import torch
import torchvision.transforms as transforms
from PIL import Image
from model import LeNet
def main():
# 将需要检测图像 裁剪为32*32
transform = transforms.Compose(
[transforms.Resize((32, 32)),
transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])
classes = ('plane', 'car', 'bird', 'cat',
'deer', 'dog', 'frog', 'horse', 'ship', 'truck')
#实例化网络 + 才入权重
net = LeNet()
net.load_state_dict(torch.load('Lenet.pth'))
# 打开图像,转换格式
im = Image.open('1.jpg')
im = transform(im) # [C, H, W]
im = torch.unsqueeze(im, dim=0) # [N, C, H, W]
# 输入到网络中, 得到预测的结果
with torch.no_grad():
outputs = net(im)
predict = torch.max(outputs, dim=1)[1].numpy()
print(classes[int(predict)])
if __name__ == '__main__':
main()
predict == 处理图像 + 实例化权重 + 得到预测结果