import torch
import torch.nn as nn
import torchvision.datasets as dsets
import torchvision.transforms as transforms
import torch.nn.functional as F
batch_size = 50
# MNIST dataset
train_dataset = dsets.MNIST(root='../../data_sets/mnist', # 选择数据的根目录
train=True, # 选择训练集
transform=transforms.ToTensor(), # 转换成tensor变量
download=False) # 不从网络上download图片
test_dataset = dsets.MNIST(root='../../data_sets/mnist', # 选择数据的根目录
train=False, # 选择训练集
transform=transforms.ToTensor(), # 转换成tensor变量
download=False) # 不从网络上download图片
# 加载数据
train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
batch_size=batch_size,
shuffle=True) # 将数据打乱
test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
batch_size=batch_size,
shuffle=True)
class Net(torch.nn.Module):
def __init__(self):
super(Net, self).__init__()
self.conv1 = nn.Sequential(
nn.Conv2d(1, 16, 5, 1, 2),# 10 *32 *32 out = 16*28*28
nn.ReLU(),
nn.MaxPool2d(2)#16*14*14
)#output 10*
self.conv2 = nn.Sequential(
nn.Conv2d(16, 32, 5, 1, 2), # 10 × 18 x 18-> 14 *14 * 32
nn.ReLU(),
nn.MaxPool2d(2)#32*7*7
)
self.out = nn.Linear(32*7*7, 10)
def forward(self, x):
x = self.conv1(x)
x = self.conv2(x)
x = x.view(x.size(0), -1)
x = self.out(x)
return x
# define the neural net
net = Net()
if torch.cuda.is_available():
net.cuda()
optimizer = torch.optim.SGD(net.parameters(), lr=0.0510) # 0.052
optimizer = torch.optim.Adam(net.parameters(), lr=0.001)
loss_func = torch.nn.CrossEntropyLoss()
for epoch in range(10):
for i, (images, labels) in enumerate(train_loader): # 利用enumerate取出一个可迭代对象的内容
#images = images.reshape(-1, 28 * 28)
labels = labels
if torch.cuda.is_available():
images=images.cuda()
labels=labels.cuda()
out = net(images)
loss = loss_func(out, labels)
optimizer.zero_grad()
loss.backward()
optimizer.step()
if i % 100 == 0:
print('current loss = %.5f' % loss.item())
with torch.no_grad():
correct = 0
total = 0
for images, labels in test_loader:
#images = images.reshape(-1, 28 * 28)
labels = labels
if torch.cuda.is_available():
images = images.cuda()
labels = labels.cuda()
output_t = net(images)
_, predicted = torch.max(output_t.data, 1)
total += labels.size(0)
correct += (predicted == labels).sum().item()
print('Accuracy of the network on the 10000 test images: {} %'.format(100 * correct / total))
in this code , if add function reshape(-1,28,28) to images
it will be error ,and
i found that Conv Layer input shape is [batch_size,input_channel,size_x,size_y]
and how to reshape like this ?
i correct to this :reshape(50,1,28,28)?
and it can Run
is it right?