Pytorch_学习笔记2

Pytorch_学习笔记2

思维导图

在这里插入图片描述

代码

# import packages
import torch
from torch import nn  # neural network
from torch.nn import functional as F  # commonly used functions
from torch import optim  # optimization toolkit

import torchvision  # visual sense
from matplotlib import pyplot as plt  # draw pictures

from utils import plot_image, plot_curve, one_hot  # function

batch_size = 512  # the number of pictures

# load dataset
train_loader = torch.utils.data.DataLoader(
	# minst_data hold data
	# download auto
	# ToTensor carrier
	# Normalize regularization distribute the data evenly   nice
	# shuffle randomly scattered
	torchvision.datasets.MNIST('mnist_data', train=True, download=True,
							   transform=torchvision.transforms.Compose([
								   torchvision.transforms.ToTensor(),
								   torchvision.transforms.Normalize(
									   (0.1307,), (0.3081,)
								   )
							   ])),
	batch_size=batch_size, shuffle=True
)

test_loader = torch.utils.data.DataLoader(
	torchvision.datasets.MNIST('mnist_data/', train=False, download=True,
							   transform=torchvision.transforms.Compose([
								   torchvision.transforms.ToTensor(),
								   torchvision.transforms.Normalize(
									   (0.1307,), (0.3081,)
								   )
							   ])),
	batch_size=batch_size, shuffle=False
)

x, y = next(iter(train_loader))
print(x.shape, y.shape, x.min(), x.max())
plot_image(x, y, 'image sample')


# establish a network
class Net(nn.Module):

	def __init__(self):
		super(Net, self).__init__()

		# wx+b
		self.fc1 = nn.Linear(28 * 28, 256)
		self.fc2 = nn.Linear(256, 64)
		self.fc3 = nn.Linear(64, 10)

	# 28*28 10 are not empirically determined

	def forward(self, x):
		# x:[b,1,28,28]
		# h1=wx+b
		x = F.relu(self.fc1(x))  # non-linear variation
		x = F.relu(self.fc2(x))
		x = self.fc3(x)  # can not add

		return x


# train
net = Net()
# weight
# [w1,b1...]
# momentum optimizing strategy
optimizer = optim.SGD(net.parameters(), lr=0.01, momentum=0.9)

train_loss = []
for epoch in range(3):  # 3
	for batch_idx, (x, y) in enumerate(train_loader):  # 1

		# x:[b,1,28,28],y:[512]
		# [b,feature]  =>[b,784]
		x = x.view(x.size(0), 28 * 28)  # dimensionality reduction
		# [b,10] probability
		out = net(x)
		# approch
		y_onehot = one_hot(y)
		# loss=mes(out,y_onehot) mean square error
		loss = F.mse_loss(out, y_onehot)
		# gradient calculation
		# empty
		optimizer.zero_grad()
		loss.backward()

		# w'=w-lr*grad
		optimizer.step()
		# data visualization
		train_loss.append(loss.item())

		if batch_idx % 10 == 0:
			print(epoch, batch_idx, loss.item())

# we get optimal [w1,b1....]
plot_curve(train_loss)

# correction
total_correct = 0
for x, y in test_loader:
	x = x.view(x.size(0), 28 * 28)
	out = net(x)
	# location
	pred = out.argmax(dim=1)
	# right
	correct = pred.eq(y).sum().float().item()
	total_correct += correct
total_num = len(test_loader.dataset)
acc = total_correct / total_num
print('test acc :', acc)


#data visualization
x,y=next(iter(test_loader))
out=net(x.view(x.size(0),28*28))
pred = out.argmax(dim=1)
plot_image(x, pred, 'test')
import  torch
from    matplotlib import pyplot as plt


def plot_curve(data):
    fig = plt.figure()
    plt.plot(range(len(data)), data, color='blue')
    plt.legend(['value'], loc='upper right')
    plt.xlabel('step')
    plt.ylabel('value')
    plt.show()



def plot_image(img, label, name):

    fig = plt.figure()
    for i in range(6):
        plt.subplot(2, 3, i + 1)
        plt.tight_layout()
        plt.imshow(img[i][0]*0.3081+0.1307, cmap='gray', interpolation='none')
        plt.title("{}: {}".format(name, label[i].item()))
        plt.xticks([])
        plt.yticks([])
    plt.show()


def one_hot(label, depth=10):
    out = torch.zeros(label.size(0), depth)
    idx = torch.LongTensor(label).view(-1, 1)
    out.scatter_(dim=1, index=idx, value=1)
    return out

结果展示

在这里插入图片描述

  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值