动画制作软件手机/网站优化的方法与技巧

参考链接

1. https://tangshusen.me/Dive-into-DL-PyTorch/#/chapter05_CNN/5.5_lenet

LeNet

LeNet分为卷积层块和全连接层块两个部分。

卷积层块里的基本单位是卷积层后接最大池化层：卷积层用来识别图像里的空间模式，如线条和物体局部，之后的最大池化层则用来降低卷积层对位置的敏感性。在卷积层块中，每个卷积层都使用5×5的窗口，并在输出上使用sigmoid激活函数。第一个卷积层输出通道数为6，第二个卷积层输出通道数则增加到16。这是因为第二个卷积层比第一个卷积层的输入的高和宽要小，所以增加输出通道使两个卷积层的参数尺寸类似。卷积层块的两个最大池化层的窗口形状均为2×2，且步幅为2。

加载数据

使用“Fashion-MNIST”数据集。

mnist_train = torchvision.datasets.FashionMNIST(root='~/Datasets/FashionMNIST', train=True, download=True, transform=transforms.ToTensor())
mnist_test = torchvision.datasets.FashionMNIST(root='~/Datasets/FashionMNIST', train=False, download=True, transform=transforms.ToTensor())def load_data_fashion_mnist(mnist_train, mnist_test, batch_size):if sys.platform.startswith('win'):num_workers = 0else:num_workers = 4train_iter = torch.utils.data.DataLoader(mnist_train, batch_size=batch_size, shuffle=True, num_workers=num_workers)test_iter = torch.utils.data.DataLoader(mnist_test, batch_size=batch_size, shuffle=False, num_workers=num_workers)return train_iter, test_iterbatch_size = 256
train_iter, test_iter = load_data_fashion_mnist(mnist_train, mnist_test, batch_size)

构建模型

class LeNet(nn.Module):def __init__(self):super(LeNet, self).__init__()self.conv = nn.Sequential(nn.Conv2d(1, 6, 5), # in_channels, out_channels, kernel_sizenn.Sigmoid(),nn.MaxPool2d(2, 2), # kernel_size, stridenn.Conv2d(6, 16, 5),nn.Sigmoid(),nn.MaxPool2d(2, 2))self.fc = nn.Sequential(nn.Linear(16*4*4, 120),nn.Sigmoid(),nn.Linear(120, 84),nn.Sigmoid(),nn.Linear(84, 10))def forward(self, img):feature = self.conv(img)output = self.fc(feature.view(img.shape[0], -1))return output

损失函数

损失函数使用交叉熵损失。

loss = torch.nn.CrossEntropyLoss()

优化方法

优化方法使用Adam算法。

optimizer = torch.optim.Adam(net.parameters(), lr=lr)

完整代码

import torch
from torch import nn
from torch.nn import init
import numpy as np
import sys
import torchvision
import torchvision.transforms as transforms
import timemnist_train = torchvision.datasets.FashionMNIST(root='~/Datasets/FashionMNIST', train=True, download=True, transform=transforms.ToTensor())
mnist_test = torchvision.datasets.FashionMNIST(root='~/Datasets/FashionMNIST', train=False, download=True, transform=transforms.ToTensor())def load_data_fashion_mnist(mnist_train, mnist_test, batch_size):if sys.platform.startswith('win'):num_workers = 0else:num_workers = 4train_iter = torch.utils.data.DataLoader(mnist_train, batch_size=batch_size, shuffle=True, num_workers=num_workers)test_iter = torch.utils.data.DataLoader(mnist_test, batch_size=batch_size, shuffle=False, num_workers=num_workers)return train_iter, test_iterbatch_size = 256
train_iter, test_iter = load_data_fashion_mnist(mnist_train, mnist_test, batch_size)device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')class LeNet(nn.Module):def __init__(self):super(LeNet, self).__init__()self.conv = nn.Sequential(nn.Conv2d(1, 6, 5), # in_channels, out_channels, kernel_sizenn.Sigmoid(),nn.MaxPool2d(2, 2), # kernel_size, stridenn.Conv2d(6, 16, 5),nn.Sigmoid(),nn.MaxPool2d(2, 2))self.fc = nn.Sequential(nn.Linear(16*4*4, 120),nn.Sigmoid(),nn.Linear(120, 84),nn.Sigmoid(),nn.Linear(84, 10))def forward(self, img):feature = self.conv(img)output = self.fc(feature.view(img.shape[0], -1))return outputnet = LeNet()def evaluate_accuracy(data_iter, net, device=None):if device is None and isinstance(net, torch.nn.Module):# 如果没指定device就使用net的devicedevice = list(net.parameters())[0].deviceacc_sum, n = 0.0, 0with torch.no_grad():for X, y in data_iter:net.eval() # 评估模式, 这会关闭dropoutacc_sum += (net(X.to(device)).argmax(dim=1) == y.to(device)).float().sum().cpu().item()net.train() # 改回训练模式n += y.shape[0]return acc_sum / ndef train(net, train_iter, test_iter, batch_size, optimizer, device, num_epochs):net = net.to(device)print("training on ", device)loss = torch.nn.CrossEntropyLoss()for epoch in range(num_epochs):train_l_sum, train_acc_sum, n, batch_count, start = 0.0, 0.0, 0, 0, time.time()for X, y in train_iter:X = X.to(device)y = y.to(device)y_hat = net(X)l = loss(y_hat, y)optimizer.zero_grad()l.backward()optimizer.step()train_l_sum += l.cpu().item()train_acc_sum += (y_hat.argmax(dim=1) == y).sum().cpu().item()n += y.shape[0]batch_count += 1test_acc = evaluate_accuracy(test_iter, net)print('epoch %d, loss %.4f, train acc %.3f, test acc %.3f, time %.1f sec'% (epoch + 1, train_l_sum / batch_count, train_acc_sum / n, test_acc, time.time() - start))lr, num_epochs = 0.001, 5
optimizer = torch.optim.Adam(net.parameters(), lr=lr)
train(net, train_iter, test_iter, batch_size, optimizer, device, num_epochs)