* 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()