pytorch練習例——手書きデジタル識別(CNNネットワーク+MNISTデータセット)
6391 ワード
例を見たときに実現したい点はいくつかあります(元の例を出すことができることに基づいて):(実現、テストセットの精度99%程度)1、自分のデータでモデルをテストします;(実現、現在は0~9しか試したことがないので、精度が分からない)2、ネットワークを変更し、結果を得る.(cnnネットワーク構造を理解し、stride、padding、kernel_size、ネットワーク層数などを変更する)3を実現し、より良いテスト精度を得る.(しばらくなく、一般的に98.3%前後)4、可視化訓練過程;(おすすめはTensorboardで、先に置いておくということです)
トレーニングデータ取得モデル:Vscode実行:途中で小さな問題が発生し、torch内のモジュールがインポートできない場合もあります.解決方法:
訓練した模型でテストする
自分でcnnネットワークを修正して、まずcnn参考ブログを理解します.
OK、寝て、勉強は果てしなくて、引き続き頑張ります!
トレーニングデータ取得モデル:Vscode実行:途中で小さな問題が発生し、torch内のモジュールがインポートできない場合もあります.解決方法:
#VSCode pytorch 'torch' has no member 'xxx'
https://blog.csdn.net/qq_34403736/article/details/84726504
import torch
import torch.nn as nn
import torchvision
import torchvision.transforms as transforms
# Device configuration
device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
# Hyper parameters
num_epochs = 5
num_classes = 10
batch_size = 100
learning_rate = 0.001
# MNIST dataset
train_dataset = torchvision.datasets.MNIST(root='data/',
train=True,
transform=transforms.ToTensor(),
download=True)
test_dataset = torchvision.datasets.MNIST(root='data/',
train=False,
transform=transforms.ToTensor())
# Data loader
train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
batch_size=batch_size,
shuffle=True)
test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
batch_size=batch_size,
shuffle=False)
# Convolutional neural network (two convolutional layers)
class ConvNet(nn.Module):
def __init__(self, num_classes=10):
super(ConvNet, self).__init__()
self.layer1 = nn.Sequential(
nn.Conv2d(1, 16, kernel_size=5, stride=1, padding=2),
nn.BatchNorm2d(16),
nn.ReLU(),
nn.MaxPool2d(kernel_size=2, stride=2))
self.layer2 = nn.Sequential(
nn.Conv2d(16, 32, kernel_size=5, stride=1, padding=2),
nn.BatchNorm2d(32),
nn.ReLU(),
nn.MaxPool2d(kernel_size=2, stride=2))
self.fc = nn.Linear(7 * 7 * 32, num_classes)
def forward(self, x):
out = self.layer1(x)
out = self.layer2(out)
out = out.reshape(out.size(0), -1)
out = self.fc(out)
return out
model = ConvNet(num_classes).to(device)
# Loss and optimizer
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
# Train the model
total_step = len(train_loader)
for epoch in range(num_epochs):
for i, (images, labels) in enumerate(train_loader):
images = images.to(device)
labels = labels.to(device)
# Forward pass
outputs = model(images)
loss = criterion(outputs, labels)
# Backward and optimize
optimizer.zero_grad()
loss.backward()
optimizer.step()
if (i + 1) % 100 == 0:
print('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}'
.format(epoch + 1, num_epochs, i + 1, total_step, loss.item()))
# Test the model
model.eval() # eval mode (batchnorm uses moving mean/variance instead of mini-batch mean/variance)
with torch.no_grad():
correct = 0
total = 0
for images, labels in test_loader:
images = images.to(device)
labels = labels.to(device)
outputs = model(images)
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).sum().item()
print('Test Accuracy of the model on the 10000 test images: {} %'.format(100 * correct / total))
# Save the model checkpoint
torch.save(model.state_dict(), 'model.ckpt')
訓練した模型でテストする
import torch
from PIL import Image
import torch.nn as nn
import torchvision
import matplotlib.pyplot as plt
from torchvision import transforms
import numpy as np
class ConvNet(nn.Module):
def __init__(self, num_classes=10):
super(ConvNet, self).__init__()
self.layer1 = nn.Sequential(
nn.Conv2d(1, 16, kernel_size=5, stride=1, padding=2),
nn.BatchNorm2d(16),
nn.ReLU(),
nn.MaxPool2d(kernel_size=2, stride=2))
self.layer2 = nn.Sequential(
nn.Conv2d(16, 32, kernel_size=5, stride=1, padding=2),
nn.BatchNorm2d(32),
nn.ReLU(),
nn.MaxPool2d(kernel_size=2, stride=2))
self.fc = nn.Linear(7 * 7 * 32, num_classes)
def forward(self, x):
out = self.layer1(x)
out = self.layer2(out)
out = out.reshape(out.size(0), -1)
out = self.fc(out)
return out
def test_mydata():
#
im = plt.imread('8.png')
images = Image.open('8.png')
images = images.resize((28,28))
images = images.convert('L')
transform = transforms.ToTensor()
images = transform(images)
images = images.resize(1,1,28,28)
#
model = ConvNet()
model.load_state_dict(torch.load('model.ckpt'))
model.eval()
outputs = model(images)
values,indices=outputs.data.max(1)
plt.title('{}'.format(int(indices[0])))
plt.imshow(im)
plt.show()
def test_MNISTdata():
test_set = torchvision.datasets.MNIST(
root='data/'#
,train=False
,download=False
,transform=transforms.Compose([
transforms.ToTensor()
])
)
test_loader = torch.utils.data.DataLoader(
test_set, batch_size=10
)
batch = next(iter(test_loader))
#
images, labels = batch
model = ConvNet()
model.load_state_dict(torch.load('model.ckpt'))
model.eval()
outputs = model(images)
grid = torchvision.utils.make_grid(images,nrow=10)#make_grid 。
plt.imshow(np.transpose(grid,(1,2,0)))# ,
values,indices=outputs.data.max(1)
plt.title('{}'.format(indices))
plt.show()
test_mydata()
自分でcnnネットワークを修正して、まずcnn参考ブログを理解します.
https://blog.csdn.net/weixin_34344403/article/details/91689617
https://blog.csdn.net/liufanghuangdi/article/details/81188563
https://zhuanlan.zhihu.com/p/33841176
OK、寝て、勉強は果てしなくて、引き続き頑張ります!