如何跑一个PytorchDemo

* Pytorch Tensor的通道顺序：[batch, channel, height, width]

* 图像载入顺序：[height, width, channel]

* 长按ctrl，然后点击函数，可以查看函数内部定义

* ctrl+/  多行注释

经过卷积后的矩阵尺寸大小计算公式：

N=（W - F + 2P）/S + 1

1. 输入图片大小W*W

2. Filter大小F*F

3. 步长S

4. padding的像素数P

model.py

import torch.nn as nn
import torch.nn.functional as F


class LeNet(nn.Module):
    def __init__(self):
        super(LeNet, self).__init__()
        self.conv1 = nn.Conv2d(3, 16, 5)  # 通道数为3（R, G, B）,卷积核个数为16，卷积核尺寸5*5
        self.pool1 = nn.MaxPool2d(2, 2)
        self.conv2 = nn.Conv2d(16, 32, 5)
        self.pool2 = nn.MaxPool2d(2, 2)
        self.fc1 = nn.Linear(32 * 5 * 5, 120)  # 展平为一维向量， 120为设置的输出节点个数
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)  # 具有是个分类结果的分类任务，所以最后的输出为10

    def forward(self, x):
        x = F.relu(self.conv1(x))  # input(3, 32, 32) output(16, 28, 28)  [channels, height, width]
        x = self.pool1(x)  # output(16, 14, 14) 池化层只改变高度和宽度
        x = F.relu(self.conv2(x))  # output(32, 10, 10)
        x = self.pool2(x)  # output(32, 5, 5)
        x = x.view(-1, 32 * 5 * 5)  # output(32*5*5)
        x = F.relu(self.fc1(x))  # output(120)
        x = F.relu(self.fc2(x))  # output(84)
        x = self.fc3(x)  # output(10)
        return x

# import torch
# input1 = torch.rand([32, 3, 32, 32])
# model = LeNet()
# print(model)
# output = model(input1)

train.py

import torch
import torchvision
import torch.nn as nn
from model import LeNet
import torch.optim as optim
import torchvision.transforms as transforms
import numpy as np
import matplotlib.pyplot as plt

# def main():
transform = transforms.Compose(
    [transforms.ToTensor(),
     transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])

# 50000张训练图片
# 第一次使用时要将download设置为True才会自动去下载数据集
train_set = torchvision.datasets.CIFAR10(root='./data', train=True,
                                         download=True, transform=transform)  # transform对数据进行一个预处理
train_loader = torch.utils.data.DataLoader(train_set, batch_size=36,
                                           shuffle=True, num_workers=0)  # 一次处理36张图片

# 10000张验证图片
# 第一次使用时要将download设置为True才会自动去下载数据集
val_set = torchvision.datasets.CIFAR10(root='./data', train=False,
                                       download=False, transform=transform)
val_loader = torch.utils.data.DataLoader(val_set, batch_size=10000,
                                         shuffle=False, num_workers=0)
val_data_iter = iter(val_loader)  # 转换成可迭代的迭代器
val_image, val_label = next(val_data_iter)  # 通过next方法获取数据

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

# def imshow(img):
#     img = img / 2 + 0.5     # unnormalize, 还原图像
#     npimg = img.numpy()
#     plt.imshow(np.transpose(npimg, (1, 2, 0)))  # 还原载入图像时的shape
#     plt.show()
#
#
# # print labels
# print(' '.join(f'{classes[val_label[j]]:5s}' for j in range(4)))
# # show images
# imshow(torchvision.utils.make_grid(val_image))

net = LeNet()
loss_function = nn.CrossEntropyLoss()
optimizer = optim.Adam(net.parameters(), lr=0.001)

for epoch in range(5):  # loop over the dataset multiple times

    running_loss = 0.0
    for step, data in enumerate(train_loader, start=0):
        # get the inputs; data is a list of [inputs, labels]
        inputs, labels = data

        # zero the parameter gradients
        optimizer.zero_grad()  # 将历史损失函数清零
        # forward + backward + optimize
        outputs = net(inputs)
        loss = loss_function(outputs, labels)
        loss.backward()
        optimizer.step()

        # print statistics
        running_loss += loss.item()  # 累加的loss函数值
        if step % 500 == 499:  # print every 500 mini-batches
            with torch.no_grad():  # 不计算误差梯度
                outputs = net(val_image)  # [batch, 10]
                predict_y = torch.max(outputs, dim=1)[1]  # 在输出的第一个维度去寻找最大值 [1]代表索引
                accuracy = torch.eq(predict_y, val_label).sum().item() / val_label.size(0)

                print('[%d, %5d] train_loss: %.3f  test_accuracy: %.3f' %
                      (epoch + 1, step + 1, running_loss / 500, accuracy))
                running_loss = 0.0

print('Finished Training')

save_path = './Lenet.pth'
torch.save(net.state_dict(), save_path)

predict.py

import torch
import torchvision.transforms as transforms
from PIL import Image

from model import LeNet


def main():
    transform = transforms.Compose(
        [transforms.Resize((32, 32)),
         transforms.ToTensor(),
         transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])

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

    net = LeNet()
    net.load_state_dict(torch.load('Lenet.pth'))

    im = Image.open('1.jpg')
    im = transform(im)  # [C, H, W]
    im = torch.unsqueeze(im, dim=0)  # [N, C, H, W] 给数据增加一个新的维度，在最前面加0

    with torch.no_grad():
        outputs = net(im)
        predict = torch.max(outputs, dim=1)[1].numpy()
        # predictb= torch.softmax(outputs, dim=1) 输出预测概率
    print(classes[int(predict)])


if __name__ == '__main__':
    main()