深度学习图像处理（二）

深度学习图像处理（一）

深度学习与图像处理（一）主要讲的是数据加载问题，二主要是介绍模型的调用与训练问题。本篇将会以ResNet18为例进行说明与演示，开发环境同一中所述

1、模型的定义
深度学习模型主要是通过nn.Module这个继承类来实现的，所以一般需要依赖torch.nn这个包，具体过程如下所示：

#*以ResNet18为例：*
import torch.nn as nn
import torch
import numpy as np

class BasicBlock(nn.Module):
    expansion = 1

    def __init__(self, in_channels, out_channels, stride=1):
        super().__init__()

        #residual function
        self.residual_function = nn.Sequential(
            nn.Conv2d(in_channels, out_channels, kernel_size=3, stride=stride, padding=1, bias=False),
            nn.BatchNorm2d(out_channels),
            nn.ReLU(inplace=True),
            nn.Conv2d(out_channels, out_channels * BasicBlock.expansion, kernel_size=3, padding=1, bias=False),
            nn.BatchNorm2d(out_channels * BasicBlock.expansion)
        )
        #shortcut
        self.shortcut = nn.Sequential()

        if stride != 1 or in_channels != BasicBlock.expansion * out_channels:
            self.shortcut = nn.Sequential(
                nn.Conv2d(in_channels, out_channels * BasicBlock.expansion, kernel_size=1, stride=stride, bias=False),
                nn.BatchNorm2d(out_channels * BasicBlock.expansion)
            )
    def forward(self, x):
        return nn.ReLU(inplace=True)(self.residual_function(x) + self.shortcut(x))


class ResNet(nn.Module):
    def __init__(self, block, num_block, num_classes=100):
        super().__init__()
        self.in_channels = 64
        self.conv1 = nn.Sequential(
            nn.Conv2d(3, 64, kernel_size=3, padding=1, bias=False),
            nn.BatchNorm2d(64),
            nn.ReLU(inplace=True))

        self.conv2_x = self._make_layer(block, 64, num_block[0], 1)
        self.conv3_x = self._make_layer(block, 128, num_block[1], 2)
        self.conv4_x = self._make_layer(block, 256, num_block[2], 2)
        self.conv5_x = self._make_layer(block, 512, num_block[3], 2)
        self.avg_pool = nn.AdaptiveAvgPool2d((1, 1))
        self.fc = nn.Linear(512 * block.expansion, num_classes)

    def _make_layer(self, block, out_channels, num_blocks, stride):
        strides = [stride] + [1] * (num_blocks - 1)
        layers = []
        for stride in strides:
            layers.append(block(self.in_channels, out_channels, stride))
            self.in_channels = out_channels * block.expansion
        return nn.Sequential(*layers)

    def forward(self, x):
        output = self.conv1(x)
        output = self.conv2_x(output)
        output = self.conv3_x(output)
        output = self.conv4_x(output)
        output = self.conv5_x(output)
        output = self.avg_pool(output)
        output = output.view(output.size(0), -1)
        output = self.fc(output)
        return output
#网络定义，由四个block构成，每个block由两个1x1的卷积构成
def resnet18():
    return ResNet(BasicBlock, [2, 2, 2, 2])

2、模型加载

#1、模型定义
import Network
net = Network.resnet18()

3、模型的训练及优化

def train(epoch):
    net.train()
    for batch_index, (images, labels) in enumerate(training_data):
        optimizer.zero_grad()
        outputs = net(images)
        loss = loss_function(outputs, labels)
        loss.backward()
        optimizer.step()
        n_iter = (epoch - 1) * len(training_data) + batch_index + 1
        last_layer = list(net.children())[-1]

        print('Training Epoch: {epoch} [{trained_samples}/{total_samples}]\tLoss: {:0.4f}\tLR: {:0.6f}'.format(
            loss.item(),
            optimizer.param_groups[0]['lr'],
            epoch=epoch,
            trained_samples=batch_index * args.batch + len(images),
            total_samples=len(training_data.dataset)
        ))

4、优化过程参数设置

parser = argparse.ArgumentParser()
parser.add_argument('-batch',type=int,default=16,help="plase input batch size type of input is 'int")
parser.add_argument('-lr',type=float,default=0.001,help="place input learning rate the type of input is float")
args = parser.parse_args()
loss_function = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=args.lr, momentum=0.9, weight_decay=5e-4)
train_scheduler = optim.lr_scheduler.MultiStepLR(optimizer, milestones=[60, 120, 160], gamma=0.2)

5、验证过程

def eval_training(epoch=0, tb=True):
    start = time.time()
    net.eval()
    test_loss = 0.0 # cost function error
    correct = 0.0

    for (images, labels) in testing_data:
        outputs = net(images)
        loss = loss_function(outputs, labels)

        test_loss += loss.item()
        _, preds = outputs.max(1)
        correct += preds.eq(labels).sum()

    finish = time.time()
    print('Evaluating Network.....')
    print('Test set: Epoch: {}, Average loss: {:.4f}, Accuracy: {:.4f}, Time consumed:{:.2f}s'.format(
        epoch,
        test_loss / len(testing_data),
        correct.float() / len(testing_data),
        finish - start
    ))
    return correct.float() / len(testing_data)