CANN训练营第三季进阶班基于昇腾PyTorch框架的模型训练调优-数字识别
环境搭建
申请镜像和代金券到账情况如下：
使用镜像申请ECS服务器如下：
规格AI加速型 | ai1s.large.4 | 2vCPUs | 8GiB
| 共享镜像
版本：Ubuntu 18.04 server 64bit
登录ECS服务器
使用“xshell”，通过SSH到ECS上(root用户):
需要修改HwHiAiUser用户的默认shell为bash。用root用户，vi /etc/passwd，修改成如下：HwHiAiUser:x:1000:1000::/home/HwHiAiUser:/bin/bash
编译运行项目
MNIST数据集简介
MNIST数据集是一个公开的数据集，相当于深度学习的hello world，用来检验一个模型库框架是否有效的一个评价指标。
MNIST数据集是由0〜9手写数字图片和数字标签所组成的，由60000个训练样本和10000个测试样本组成，每个样本都是一张28 * 28像素的灰度手写数字图片。MNIST 数据集来自美国国家标准与技术研究所，整个训练集由250个不同人的手写数字组成，其中50%来自美国高中学生，50%来自人口普查的工作人员。
代码：
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torchvision import datasets,transforms
import torchvision
from torch.autograd import Variable
from torch.utils.data import DataLoader
import cv2
class LeNet(nn.Module):
def__init__(self):
super(LeNet, self).__init__()
self.conv1 = nn.Sequential(
nn.Conv2d(1, 6, 3, 1, 2),
nn.ReLU(),
nn.MaxPool2d(2, 2)
)
self.conv2 = nn.Sequential(
nn.Conv2d(6, 16, 5),
nn.ReLU(),
nn.MaxPool2d(2, 2)
)
self.fc1 = nn.Sequential(
nn.Linear(16 * 5 * 5, 120),
nn.BatchNorm1d(120),
nn.ReLU()
)
self.fc2 = nn.Sequential(
nn.Linear(120, 84),
nn.BatchNorm1d(84),#加快收敛速度的方法（注：批标准化一般放在全连接层后面，激活函数层的前面） nn.ReLU()
)
self.fc3 = nn.Linear(84, 10)
# self.sfx = nn.Softmax()def forward(self, x):
x = self.conv1(x)
x = self.conv2(x)
# print(x.shape)
x = x.view(x.size()[0], -1)
x = self.fc1(x)
x = self.fc2(x)
x = self.fc3(x)
# x = self.sfx(x)return x
device = torch.device('cuda'if torch.cuda.is_available() else'cpu')
batch_size = 64
LR = 0.001
Momentum = 0.9
#下载数据集
train_dataset = datasets.MNIST(root = './data/',
train=True,
transform = transforms.ToTensor(),
download=False)
test_dataset =datasets.MNIST(root = './data/',
train=False,
transform=transforms.ToTensor(),
download=False)
#建立一个数据迭代器
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)
#实现单张图片可视化
# images,labels = next(iter(train_loader))
# img = torchvision.utils.make_grid(images)
# img = img.numpy().transpose(1,2,0)
# # img.shape
# std = [0.5,0.5,0.5]
# mean = [0.5,0.5,0.5]
# img = img*std +mean
# cv2.imshow('win',img)
# key_pressed = cv2.waitKey(0)
net = LeNet().to(device)
criterion = nn.CrossEntropyLoss()#定义损失函数
optimizer = optim.SGD(net.parameters(),lr=LR,momentum=Momentum)
epoch = 1
if__name__ == '__main__':
for epoch in range(epoch):
sum_loss = 0.0
for i, data in enumerate(train_loader):
inputs, labels = data
inputs, labels = Variable(inputs).cuda(), Variable(labels).cuda()
optimizer.zero_grad()#将梯度归零
outputs = net(inputs)#将数据传入网络进行前向运算
loss = criterion(outputs, labels)#得到损失函数
loss.backward()#反向传播
optimizer.step()#通过梯度做一步参数更新# print(loss)
sum_loss += loss.item()
if i % 100 == 99:
print('[%d,%d] loss:%.03f' % (epoch + 1, i + 1, sum_loss / 100))
sum_loss = 0.0
#验证测试集
net.eval()#将模型变换为测试模式
correct = 0
total = 0
for data_test in test_loader:
images, labels = data_test
images, labels = Variable(images).cuda(), Variable(labels).cuda()
output_test = net(images)
# print("output_test:",output_test.shape)
_, predicted = torch.max(output_test, 1)#此处的predicted获取的是最大值的下标# print("predicted:",predicted.shape)
total += labels.size(0)
correct += (predicted == labels).sum()
print("correct1: ",correct)
print("Test acc: {0}".format(correct.item() / len(test_dataset)))#.cpu().numpy()
