pytorch进阶一：创建数据集

CNN作为计算机视觉的一种方法，有自己的一套生态，必须从头到尾掌握数据集操作、预处理、网络搭建、训练、测试、优化等一整套环节，并应用到具体的检测场景中，才算是法尽其用。
选择pytorch框架并不是对比尝试之后的结果。由于之前动手编译过caffe，也用C++做过简单的手写体识别（极其简单，以至于现在已经说不出来个一二三了），caffe2去年集成到了pytorch里，这次也就用pytorch了。
环境是windows。

一、一些前期的环境准备

安装Anaconda、Pycharm这些都是最基本的东西，写详细步骤没什么意义，仅记录一些重要的步骤/命令。

1. 创建pytorch环境
   创建新环境仅仅是为了减少干扰。

conda create -n pytorch python=3.7

这个过程中会自动安装ca-certificates、pip、openssl、python、setuptools、sqlite、vc、vs2015_runtime、wheel和wincertstore等基础包/工具。中间因为网络原因断了没关系，重来会接着之前已经完成的继续。
2. 查看GPU算力和相关版本
https://developer.nvidia.com/cuda-gpus
查看GPU的驱动版本、CUDA版本

cd  C:\Program Files\NVIDIA Corporation\NVSMI
nvidia-smi  //查看软件版本
nvdebugdump  -l//查看硬件设备列表

3. 安装pytorch
   在线安装：

conda install pytorch torchvision cudatoolkit=x.x  -c pytorch // 10.2现在（2019.06.15）还不支持，10,0可以

离线包
https://pytorch.org/get-started/previous-versions/。 如果是离线安装，记得安装这些包中必要。

验证torch

python
import torch
torch.Tensor()

二、CIFAR10数据集测试

import torch
import torchvision
import torchvision.transforms as transforms
import matplotlib.pyplot as plt
import numpy as np
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
import time
import pdb

def showimg(img):
    img = img / 2 + 0.5
    npimg = img.numpy()
    plt.imshow(np.transpose(npimg, (1, 2, 0)))
    plt.show()

class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(3, 6, 5)
        self.pool = nn.MaxPool2d(2, 2)
        self.conv2 = nn.Conv2d(6, 16, 5)
        self.fc1 = nn.Linear(16 * 5 * 5, 120)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)

    def forward(self, x):
        x = self.pool(F.relu(self.conv1(x)))
        x = self.pool(F.relu(self.conv2(x)))
        x = x.view(-1, 16 * 5 * 5)
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x

if __name__ == '__main__':

    CUDA_VISIBLE_DEVICES = 1
    device = torch.device("cpu")
    print(device)
    transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])
    trainset = torchvision.datasets.CIFAR10(root='./data', train=True, download=False, transform=transform)
    trainloader = torch.utils.data.DataLoader(trainset, batch_size=4, shuffle=True,num_workers=2)
    testset = torchvision.datasets.CIFAR10(root='./data', train=False, download=False, transform=transform)
    testloader = torch.utils.data.DataLoader(testset, batch_size=4, shuffle=False, num_workers=2)

    classes = ('plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck')

# show image for test
    dataiter = iter(trainloader)
    images, labels = dataiter.next()
    showimg(torchvision.utils.make_grid(images))
    print(' '.join('%5s' % classes[labels[j]] for j in range(4)))

    #torch.cuda.synchronize()
    start = time.time()

#CNN
    net = Net()
    #net = nn.DataParallel(net)
    net.to(device)
    criterion = nn.CrossEntropyLoss()
    optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)
    for epoch in range(2):

        running_loss = 0.0
        for i, data in enumerate(trainloader, 0):
            inputs, labels = data
            inputs, labels = inputs.to(device), labels.to(device)
            optimizer.zero_grad()
            outputs = net(inputs)
            #print("Outside: input size", inputs.size(), "output_size", outputs)
            loss = criterion(outputs, labels)
            loss.backward()
            optimizer.step()
            running_loss += loss.item()
            if i % 2000 == 1999:
                print('[%d, %5d] loss: %.3f' % (epoch + 1, i + 1, running_loss/2000))
            running_loss = 0.0
    print("finished training")

    #torch.cuda.synchronize()
    end = time.time()
    print('Time spent %2d ms' % (end - start))

# 测试
    dataiter = iter(testloader)
    images, labels = dataiter.next()

    # print images
    images.cpu()
    showimg(torchvision.utils.make_grid(images))
    print('GroundTruth: ', ' '.join('%5s' % classes[labels[j]] for j in range(4)))
    images, labels = images.to(device), labels.to(device)

    outputs = net(images)
    _, predicted = torch.max(outputs, 1)
    print('Predicted: ', ' '.join('%5s' % classes[predicted[j]] for j in range(4)))

# 查看总体准确率
    correct = 0
    total = 0
    with torch.no_grad():
        for data in testloader:
            images, labels = data
            images, labels = images.to(device), labels.to(device)
            outputs = net(images)
            _, predicted = torch.max(outputs.data, 1)
            total += labels.size(0)
            correct += (predicted == labels).sum().item()

    print('Accuracy: %d %%' % (100 * correct/total))

# 查看十个类别每一类的总体准确率
    class_correct = list(0. for i in range(10))
    class_total = list(0. for i in range(10))
    with torch.no_grad():
        for data in testloader:
            images, labels = data
            images, labels = images.to(device), labels.to(device)
            outputs = net(images)
            _, predicted = torch.max(outputs, 1)
            c = (predicted==labels).squeeze()
            for i in range(4):
                label = labels[i]
                class_correct[label] += c[i].item()
                class_total[label] += 1
    for i in range(10):
        print('Accuracy of %5s : %2d %%' % (classes[i], 100 * class_correct[i]/class_total[i]))