首先這是VGG的結構圖，VGG11則是紅色框里的結構，共分五個block，如紅框中的VGG11第一個block就是一個conv3-64卷積層：
一，寫VGG代碼時，首先定義一個 vgg_block(n,in,out)方法，用來構建VGG中每個block中的卷積核和池化層：
n是這個block中卷積層的數目，in是輸入的通道數，out是輸出的通道數
有了block以后，我們還需要一個方法把形成的block疊在一起，我們定義這個方法叫vgg_stack：
def vgg_stack(num_convs, channels): # vgg_net = vgg_stack((1, 1, 2, 2, 2), ((3, 64), (64, 128), (128, 256), (256, 512), (512, 512)))
net = []
for n, c in zip(num_convs, channels):
in_c = c[0]
out_c = c[1]
net.append(vgg_block(n, in_c, out_c))
return nn.Sequential(*net)
右邊的注釋
vgg_net = vgg_stack((1, 1, 2, 2, 2), ((3, 64), (64, 128), (128, 256), (256, 512), (512, 512)))
里，(1, 1, 2, 2, 2)表示五個block里，各自的卷積層數目，((3, 64), (64, 128), (128, 256), (256, 512), (512, 512))表示每個block中的卷積層的類型，如(3,64)表示這個卷積層輸入通道數是3，輸出通道數是64。vgg_stack方法返回的就是完整的vgg11模型了。
接著定義一個vgg類，包含vgg_stack方法：
#vgg類
class vgg(nn.Module):
def __init__(self):
super(vgg, self).__init__()
self.feature = vgg_net
self.fc = nn.Sequential(
nn.Linear(512, 100),
nn.ReLU(True),
nn.Linear(100, 10)
)
def forward(self, x):
x = self.feature(x)
x = x.view(x.shape[0], -1)
x = self.fc(x)
return x
最后：
net = vgg() #就能獲取到vgg網絡
那么構建vgg網絡完整的pytorch代碼是：
def vgg_block(num_convs, in_channels, out_channels):
net = [nn.Conv2d(in_channels, out_channels, kernel_size=3, padding=1), nn.ReLU(True)]
for i in range(num_convs - 1): # 定義后面的許多層
net.append(nn.Conv2d(out_channels, out_channels, kernel_size=3, padding=1))
net.append(nn.ReLU(True))
net.append(nn.MaxPool2d(2, 2)) # 定義池化層
return nn.Sequential(*net)
# 下面我們定義一個函數對這個 vgg block 進行堆疊
def vgg_stack(num_convs, channels): # vgg_net = vgg_stack((1, 1, 2, 2, 2), ((3, 64), (64, 128), (128, 256), (256, 512), (512, 512)))
net = []
for n, c in zip(num_convs, channels):
in_c = c[0]
out_c = c[1]
net.append(vgg_block(n, in_c, out_c))
return nn.Sequential(*net)
#確定vgg的類型，是vgg11 還是vgg16還是vgg19
vgg_net = vgg_stack((1, 1, 2, 2, 2), ((3, 64), (64, 128), (128, 256), (256, 512), (512, 512)))
#vgg類
class vgg(nn.Module):
def __init__(self):
super(vgg, self).__init__()
self.feature = vgg_net
self.fc = nn.Sequential(
nn.Linear(512, 100),
nn.ReLU(True),
nn.Linear(100, 10)
)
def forward(self, x):
x = self.feature(x)
x = x.view(x.shape[0], -1)
x = self.fc(x)
return x
#獲取vgg網絡
net = vgg()
基于VGG11的cifar10訓練代碼：
import sys
import numpy as np
import torch
from torch import nn
from torch.autograd import Variable
from torchvision.datasets import CIFAR10
import torchvision.transforms as transforms
def vgg_block(num_convs, in_channels, out_channels):
net = [nn.Conv2d(in_channels, out_channels, kernel_size=3, padding=1), nn.ReLU(True)]
for i in range(num_convs - 1): # 定義后面的許多層
net.append(nn.Conv2d(out_channels, out_channels, kernel_size=3, padding=1))
net.append(nn.ReLU(True))
net.append(nn.MaxPool2d(2, 2)) # 定義池化層
return nn.Sequential(*net)
# 下面我們定義一個函數對這個 vgg block 進行堆疊
def vgg_stack(num_convs, channels): # vgg_net = vgg_stack((1, 1, 2, 2, 2), ((3, 64), (64, 128), (128, 256), (256, 512), (512, 512)))
net = []
for n, c in zip(num_convs, channels):
in_c = c[0]
out_c = c[1]
net.append(vgg_block(n, in_c, out_c))
return nn.Sequential(*net)
#vgg類
class vgg(nn.Module):
def __init__(self):
super(vgg, self).__init__()
self.feature = vgg_net
self.fc = nn.Sequential(
nn.Linear(512, 100),
nn.ReLU(True),
nn.Linear(100, 10)
)
def forward(self, x):
x = self.feature(x)
x = x.view(x.shape[0], -1)
x = self.fc(x)
return x
# 然后我們可以訓練我們的模型看看在 cifar10 上的效果
def data_tf(x):
x = np.array(x, dtype='float32') / 255
x = (x - 0.5) / 0.5
x = x.transpose((2, 0, 1)) ## 將 channel 放到第一維，只是 pytorch 要求的輸入方式
x = torch.from_numpy(x)
return x
transform = transforms.Compose([transforms.ToTensor(),
transforms.Normalize(mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5)),
])
def get_acc(output, label):
total = output.shape[0]
_, pred_label = output.max(1)
num_correct = (pred_label == label).sum().item()
return num_correct / total
def train(net, train_data, valid_data, num_epochs, optimizer, criterion):
if torch.cuda.is_available():
net = net.cuda()
for epoch in range(num_epochs):
train_loss = 0
train_acc = 0
net = net.train()
for im, label in train_data:
if torch.cuda.is_available():
im = Variable(im.cuda())
label = Variable(label.cuda())
else:
im = Variable(im)
label = Variable(label)
# forward
output = net(im)
loss = criterion(output, label)
# forward
optimizer.zero_grad()
loss.backward()
optimizer.step()
train_loss += loss.item()
train_acc += get_acc(output, label)
if valid_data is not None:
valid_loss = 0
valid_acc = 0
net = net.eval()
for im, label in valid_data:
if torch.cuda.is_available():
with torch.no_grad():
im = Variable(im.cuda())
label = Variable(label.cuda())
else:
with torch.no_grad():
im = Variable(im)
label = Variable(label)
output = net(im)
loss = criterion(output, label)
valid_loss += loss.item()
valid_acc += get_acc(output, label)
epoch_str = (
"Epoch %d. Train Loss: %f, Train Acc: %f, Valid Loss: %f, Valid Acc: %f, "
% (epoch, train_loss / len(train_data),
train_acc / len(train_data), valid_loss / len(valid_data),
valid_acc / len(valid_data)))
else:
epoch_str = ("Epoch %d. Train Loss: %f, Train Acc: %f, " %
(epoch, train_loss / len(train_data),
train_acc / len(train_data)))
# prev_time = cur_time
print(epoch_str)
if __name__ == '__main__':
# 作為實例，我們定義一個稍微簡單一點的 vgg11 結構，其中有 8 個卷積層
vgg_net = vgg_stack((1, 1, 2, 2, 2), ((3, 64), (64, 128), (128, 256), (256, 512), (512, 512)))
print(vgg_net)
train_set = CIFAR10('./data', train=True, transform=transform, download=True)
train_data = torch.utils.data.DataLoader(train_set, batch_size=64, shuffle=True)
test_set = CIFAR10('./data', train=False, transform=transform, download=True)
test_data = torch.utils.data.DataLoader(test_set, batch_size=128, shuffle=False)
net = vgg()
optimizer = torch.optim.SGD(net.parameters(), lr=1e-1)
criterion = nn.CrossEntropyLoss() #損失函數為交叉熵
train(net, train_data, test_data, 50, optimizer, criterion)
torch.save(net, 'vgg_model.pth')
結束后，會出現一個模型文件vgg_model.pth
二，然后網上找張圖片，把圖片縮成32x32，放到預測代碼中，即可有預測結果出現，預測代碼如下：
import torch
import cv2
import torch.nn.functional as F
from vgg2 import vgg ##重要，雖然顯示灰色(即在次代碼中沒用到)，但若沒有引入這個模型代碼，加載模型時會找不到模型
from torch.autograd import Variable
from torchvision import datasets, transforms
import numpy as np
classes = ('plane', 'car', 'bird', 'cat',
'deer', 'dog', 'frog', 'horse', 'ship', 'truck')
if __name__ == '__main__':
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model = torch.load('vgg_model.pth') # 加載模型
model = model.to(device)
model.eval() # 把模型轉為test模式
img = cv2.imread("horse.jpg") # 讀取要預測的圖片
trans = transforms.Compose(
[
transforms.ToTensor(),
transforms.Normalize(mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5))
])
img = trans(img)
img = img.to(device)
img = img.unsqueeze(0) # 圖片擴展多一維,因為輸入到保存的模型中是4維的[batch_size,通道,長，寬]，而普通圖片只有三維，[通道,長，寬]
# 擴展后，為[1，1，28，28]
output = model(img)
prob = F.softmax(output,dim=1) #prob是10個分類的概率
print(prob)
value, predicted = torch.max(output.data, 1)
print(predicted.item())
print(value)
pred_class = classes[predicted.item()]
print(pred_class)
# prob = F.softmax(output, dim=1)
# prob = Variable(prob)
# prob = prob.cpu().numpy() # 用GPU的數據訓練的模型保存的參數都是gpu形式的，要顯示則先要轉回cpu，再轉回numpy模式
# print(prob) # prob是10個分類的概率
# pred = np.argmax(prob) # 選出概率最大的一個
# # print(pred)
# # print(pred.item())
# pred_class = classes[pred]
# print(pred_class)
縮成32x32的圖片：
運行結果：
以上這篇pytorch VGG11識別cifar10數據集(訓練+預測單張輸入圖片操作)就是小編分享給大家的全部內容了，希望能給大家一個參考，也希望大家多多支持腳本之家。
)
