编程宝库 - 技术改变世界

编程宝库

Search

Python编程技术

Python变量和数据类型和数据类型的转换

python中celery的基本使用详情

pytorch实现mnist手写彩色数字识别

前言

环境：

语言环境：Python3.6
编译器：jupyter lab
深度学习环境：pytorch1.10

要求：

学习如何编写一个完整的深度学习程序（✔）
手动推导卷积层与池化层的计算过程（✔）

一前期工作

环境：python3.6，1080ti，pytorch1.10（实验室服务器的环境）

1.设置GPU或者cpu

import torch
import torch.nn as nn
import matplotlib.pyplot as plt
import torchvision

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

device

2.导入数据

train_ds = torchvision.datasets.MNIST('data', 
                                    train=True, 
                                    transform=torchvision.transforms.ToTensor(), # 将数据类型转化为Tensor
                                    download=True)

test_ds  = torchvision.datasets.MNIST('data', 
                                    train=False, 
                                    transform=torchvision.transforms.ToTensor(), # 将数据类型转化为Tensor
                                    download=True)

二数据预处理

1.加载数据

设置数据尺寸

batch_size = 32

设置dataset

 
train_dl = torch.utils.data.DataLoader(train_ds, 
                                     batch_size=batch_size, 
                                     shuffle=True)

test_dl  = torch.utils.data.DataLoader(test_ds, 
                                     batch_size=batch_size)

2.可视化数据

打印部分图片：

import numpy as np

# 指定图片大小，图像大小为20宽、5高的绘图(单位为英寸inch)
plt.figure(figsize=(20, 5)) 
for i, imgs in enumerate(imgs[:20]):
  # 维度缩减
  npimg = imgs.numpy().transpose((1, 2, 0))
  # 将整个figure分成2行10列，绘制第i+1个子图。
  plt.subplot(2, 10, i+1)
  plt.imshow(npimg, cmap=plt.cm.binary)
  plt.axis('off')

3.再次检查数据

输出数据的尺寸：

# 取一个批次查看数据格式
# 数据的shape为：[batch_size, channel, height, weight]
# 其中batch_size为自己设定，channel，height和weight分别是图片的通道数，高度和宽度。
imgs, labels = next(iter(train_dl))
imgs.shape

三搭建网络

import torch
from torch import nn
from torch.nn import Conv2d, MaxPool2d, Flatten, Linear, Sequential,ReLU

num_classes = 10 

class Model(nn.Module):
  def __init__(self):
      super(Model,self).__init__()
      # 卷积层
      self.layers = Sequential(
          # 第一层
          Conv2d(3, 64, kernel_size=3),
          MaxPool2d(2),
          ReLU(),
          # 第二层
          Conv2d(64, 64, kernel_size=3),
          MaxPool2d(2),
          ReLU(),
          Conv2d(64, 128, kernel_size=3),
          MaxPool2d(2),
          ReLU(),
          Flatten(),
          Linear(512, 256,bias=True),
          ReLU(),
          Linear(256, 64,bias=True),
          ReLU(),
          Linear(64, num_classes,bias=True)
      )
  def forward(self, x):
      x = self.layers(x)
      return x

打印网络结构：

vgg16网络搭建：未修改尺寸

from torch import nn

vgg16=torchvision.models.vgg16(pretrained=True)#经过训练的
class Model(nn.Module):
  def __init__(self):
      super(Model,self).__init__()
      # 卷积层
      self.layers = Sequential(
          vgg16
      )
  def forward(self, x):
      x = self.layers(x)
      return x

vgg16网络搭建：修改尺寸

四训练模型

1.设置学习率

loss_fn    = nn.CrossEntropyLoss() # 创建损失函数
learn_rate = 1e-2 # 学习率
opt        = torch.optim.SGD(model.parameters(),lr=learn_rate)

2.模型训练

训练函数：

# 训练循环
def train(dataloader, model, loss_fn, optimizer):
  size = len(dataloader.dataset)  # 训练集的大小，一共60000张图片
  num_batches = len(dataloader)   # 批次数目，1875（60000/32）

  train_loss, train_acc = 0, 0  # 初始化训练损失和正确率

  for X, y in dataloader:  # 获取图片及其标签
      X, y = X.to(device), y.to(device)

      # 计算预测误差
      pred = model(X)          # 网络输出
      loss = loss_fn(pred, y)  # 计算网络输出和真实值之间的差距，targets为真实值，计算二者差值即为损失

      # 反向传播
      optimizer.zero_grad()  # grad属性归零
      loss.backward()        # 反向传播
      optimizer.step()       # 每一步自动更新

      # 记录acc与loss
      train_acc  += (pred.argmax(1) == y).type(torch.float).sum().item()
      train_loss += loss.item()

  train_acc  /= size
  train_loss /= num_batches

  return train_acc, train_loss

测试函数：

def test (dataloader, model, loss_fn):
  size        = len(dataloader.dataset)  # 测试集的大小，一共10000张图片
  num_batches = len(dataloader)          # 批次数目，313（10000/32=312.5，向上取整）
  test_loss, test_acc = 0, 0

  # 当不进行训练时，停止梯度更新，节省计算内存消耗
  with torch.no_grad():
      for imgs, target in dataloader:
          imgs, target = imgs.to(device), target.to(device)

          # 计算loss
          target_pred = model(imgs)
          loss        = loss_fn(target_pred, target)

          test_loss += loss.item()
          test_acc  += (target_pred.argmax(1) == target).type(torch.float).sum().item()

  test_acc  /= size
  test_loss /= num_batches

  return test_acc, test_loss

具体训练代码：

epochs     = 20
train_loss = []
train_acc  = []
test_loss  = []
test_acc   = []

for epoch in range(epochs):
  model.train()
  epoch_train_acc, epoch_train_loss = train(train_dl, model, loss_fn, opt)

  model.eval()
  epoch_test_acc, epoch_test_loss = test(test_dl, model, loss_fn)

  train_acc.append(epoch_train_acc)
  train_loss.append(epoch_train_loss)
  test_acc.append(epoch_test_acc)
  test_loss.append(epoch_test_loss)

  template = ('Epoch:{:2d}, Train_acc:{:.1f}%, Train_loss:{:.3f}, Test_acc:{:.1f}%，Test_loss:{:.3f}')
  print(template.format(epoch+1, epoch_train_acc*100, epoch_train_loss, epoch_test_acc*100, epoch_test_loss))
print('Done')