pytorch深度学习-CNN google Net
google Net结构
Inception
效果
GoogleNet 代码
import torch
from torchvision import transforms
from torchvision import datasets
from torch.utils.data import DataLoader
import torch.nn.functional as F
import torch.nn as nn
import torch.optim as optim
batch_size = 64
transform = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.137,),(0.3081,))
])
train_dataset = datasets.MNIST(root='../dataset/mnist',
train=True,
download=True,
transform=transform)
train_loder = DataLoader(train_dataset,
shuffle=True,
batch_size=batch_size)
test_dataset = datasets.MNIST(root='../dataset/mnist',
train=False,
download=True,
transform=transform)
test_loder = DataLoader(test_dataset,
shuffle=False,
batch_size=batch_size)
class InceptionA(nn.Module):
def __init__(self,in_channels):
super(InceptionA, self).__init__()
self.branch_pool = nn.Conv2d(in_channels,24,kernel_size=1)
self.branch1x1 = nn.Conv2d(in_channels,16,kernel_size=1)
self.branch5x5_1 = nn.Conv2d(in_channels,16,kernel_size=1)
self.branch5x5_2 = nn.Conv2d(16,24,kernel_size=5,padding=2)
self.branch3x3_1 = nn.Conv2d(in_channels,16,kernel_size=1)
self.branch3x3_2 = nn.Conv2d(16,24,kernel_size=3,padding=1)
self.branch3x3_3 = nn.Conv2d(24,24,kernel_size=3,padding=1)
def forward(self,x):
branch_pool = F.avg_pool2d(x,kernel_size=3,stride=1,padding=1)
branch_pool = self.branch_pool(branch_pool)
branch1x1 = self.branch1x1(x)
branch5x5 = self.branch5x5_1(x)
branch5x5 = self.branch5x5_2(branch5x5)
branch3x3 = self.branch3x3_1(x)
branch3x3 = self.branch3x3_2(branch3x3)
branch3x3 = self.branch3x3_3(branch3x3)
outputs = [branch_pool,branch1x1,branch5x5,branch3x3]
return torch.cat(outputs,dim=1)
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.conv1 = nn.Conv2d(1,10,kernel_size=5)
self.conv2 = nn.Conv2d(88,20,kernel_size=5)
self.incep1 = InceptionA(in_channels=10)
self.incep2 = InceptionA(in_channels=20)
self.mp = nn.MaxPool2d(2)
self.fc = torch.nn.Linear(1408,10)
def forward(self,x):
in_size = x.size(0)
x = F.relu(self.mp(self.conv1(x)))
x = self.incep1(x)
x = F.relu(self.mp(self.conv2(x)))
x = self.incep2(x)
x = x.view(in_size,-1)
x = self.fc(x)
return x
model = Net()
device = torch.device("cuda:0" if torch.cuda.is_available() else"cpu")
model.to(device)
criterion = torch.nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(model.parameters(),lr=0.01)
def train(epoch):
running_loss = 0.0
for batch_idx,data in enumerate(train_loder,0):
inputs,target = data
inputs,target = inputs.to(device),target.to(device)
optimizer.zero_grad()
outputs = model(inputs)
loss = criterion(outputs,target)
loss.backward()
optimizer.step()
running_loss += loss.item()
if batch_idx % 300 == 299:
print(' [%d,%5d] loss: %.3f' % (epoch + 1,batch_idx + 1, running_loss / 300))
running_loss = 0.0
def test():
correct = 0
total = 0
with torch.no_grad():
for data in test_loder:
inputs,target = data
inputs, target = inputs.to(device), target.to(device)
outputs = model(inputs)
_,predicted = torch.max(outputs.data,dim=1)
total += target.size(0)
correct += (predicted == target).sum().item()
print('Accuracy on test set: %d %% '%(100 * correct / total))
if __name__ == '__main__':
for epoch in range(10):
train(epoch)
test()
GoogleNet
[1, 300] loss: 1.293
[1, 600] loss: 0.324
[1, 900] loss: 0.225
Accuracy on test set: 94 %
[2, 300] loss: 0.170
[2, 600] loss: 0.146
[2, 900] loss: 0.134
Accuracy on test set: 96 %
[3, 300] loss: 0.113
[3, 600] loss: 0.105
[3, 900] loss: 0.101
Accuracy on test set: 97 %
[4, 300] loss: 0.092
[4, 600] loss: 0.088
[4, 900] loss: 0.082
Accuracy on test set: 97 %
[5, 300] loss: 0.078
[5, 600] loss: 0.073
[5, 900] loss: 0.080
Accuracy on test set: 98 %
[6, 300] loss: 0.066
[6, 600] loss: 0.071
[6, 900] loss: 0.071
Accuracy on test set: 98 %
[7, 300] loss: 0.062
[7, 600] loss: 0.061
[7, 900] loss: 0.066
Accuracy on test set: 98 %
[8, 300] loss: 0.057
[8, 600] loss: 0.058
[8, 900] loss: 0.059
Accuracy on test set: 98 %
[9, 300] loss: 0.053
[9, 600] loss: 0.051
[9, 900] loss: 0.055
Accuracy on test set: 98 %
[10, 300] loss: 0.053
[10, 600] loss: 0.049
[10, 900] loss: 0.050
Accuracy on test set: 98 %
Process finished with exit code 0