ResNet50

ResNet50，即Residual Network 50，是一种深度学习模型，特别设计用于解决深度神经网络中梯度消失或爆炸问题以及退化问题。它由Kaiming He、Xiangyu Zhang、Shaoqing Ren和Jian Sun在2015年提出，并在当年的ImageNet Large Scale Visual Recognition Challenge (ILSVRC)中赢得了冠军。ResNet50之所以命名，是因为它拥有50层的深度。

ResNet主体结构如下

1. 输入层：接收输入图像，通常是224x224像素的RGB图像。
2. 初始卷积层：使用7x7的卷积核进行卷积，步长为2，通常跟随后续的最大池化层。
3. 多个残差阶段：包含一系列残差块，每个阶段的残差块数量不同，具体为3个、4个、6个、3个残差块，分别对应stage1、stage2、stage3、stage4。
4. 全局平均池化层：将最后一个残差块的输出压缩成固定大小的向量。
5. 全连接层：将压缩后的向量连接到分类器，通常是一个softmax层，用于输出各个类别的概率。

本节使用一组图像数据来进行mindspore中的框架搭建：

1.首先，我们要先导入数据

from download import download

url = "https://mindspore-website.obs.cn-north-4.myhuaweicloud.com/notebook/datasets/cifar-10-binary.tar.gz"

download(url, "./datasets-cifar10-bin", kind="tar.gz", replace=True)

2.对导入数据进行处理：

import mindspore as ms
import mindspore.dataset as ds
import mindspore.dataset.vision as vision
import mindspore.dataset.transforms as transforms
from mindspore import dtype as mstype

data_dir = "./datasets-cifar10-bin/cifar-10-batches-bin"  # 数据集根目录
batch_size = 256  # 批量大小
image_size = 32  # 训练图像空间大小
workers = 4  # 并行线程个数
num_classes = 10  # 分类数量


def create_dataset_cifar10(dataset_dir, usage, resize, batch_size, workers):
    # 使用ds.Cifar10Dataset加载数据集，设置数据集用途、并行线程数和是否打乱数据。
    data_set = ds.Cifar10Dataset(dataset_dir=dataset_dir,
                                 usage=usage,
                                 num_parallel_workers=workers,
                                 shuffle=True)

    trans = []
    if usage == "train":
        trans += [
            vision.RandomCrop((32, 32), (4, 4, 4, 4)),
            vision.RandomHorizontalFlip(prob=0.5)
        ]
    # 定义图像转换操作，包括随机裁剪、水平翻转（仅训练集）、缩放、归一化、颜色通道转换等。
    trans += [
        vision.Resize(resize),
        vision.Rescale(1.0 / 255.0, 0.0),
        vision.Normalize([0.4914, 0.4822, 0.4465], [0.2023, 0.1994, 0.2010]),
        vision.HWC2CHW()
    ]

    target_trans = transforms.TypeCast(mstype.int32)

    # 数据映射操作
    data_set = data_set.map(operations=trans,
                            input_columns='image',
                            num_parallel_workers=workers)

    data_set = data_set.map(operations=target_trans,
                            input_columns='label',
                            num_parallel_workers=workers)

    # 批量操作
    data_set = data_set.batch(batch_size)

    return data_set


# 获取处理后的训练与测试数据集

dataset_train = create_dataset_cifar10(dataset_dir=data_dir,
                                       usage="train",
                                       resize=image_size,
                                       batch_size=batch_size,
                                       workers=workers)
step_size_train = dataset_train.get_dataset_size()

dataset_val = create_dataset_cifar10(dataset_dir=data_dir,
                                     usage="test",
                                     resize=image_size,
                                     batch_size=batch_size,
                                     workers=workers)
step_size_val = dataset_val.get_dataset_size()

3. 构建网络，ResNet使用残差网络显著减轻退化问题，实现更深的网络结构设计。 

残差网络结构主要由两种，一种是Building Block，另一种是Bottleneck

        BasicBlock是最简单的ResNet构建块，通常包含两个3x3的卷积层，每一层后跟一个批量归一化（Batch Normalization）层和激活函数（如ReLU）。如果需要调整通道数或步幅，通常会使用一个1x1的卷积层作为shortcut连接的一部分。

        Bottleneck block设计得更为复杂，旨在减少计算成本同时保持网络深度和宽度。它通常包含三个卷积层：

• 第一个1x1卷积层用来减少输入的通道数，称为“压缩”；
• 中间的3x3卷积层进行空间特征提取；
• 最后一个1x1卷积层恢复通道数至原始或更高，称为“扩张”。
• 每个卷积层后面通常跟着一个批量归一化层和激活函数。

from typing import Type, Union, List, Optional
import mindspore.nn as nn
from mindspore.common.initializer import Normal

# 初始化卷积层与BatchNorm的参数
weight_init = Normal(mean=0, sigma=0.02)
gamma_init = Normal(mean=1, sigma=0.02)

class ResidualBlockBase(nn.Cell):
    expansion: int = 1  # 最后一个卷积核数量与第一个卷积核数量相等

    def __init__(self, in_channel: int, out_channel: int,
                 stride: int = 1, norm: Optional[nn.Cell] = None,
                 down_sample: Optional[nn.Cell] = None) -> None:
        super(ResidualBlockBase, self).__init__()
        if not norm:
            self.norm = nn.BatchNorm2d(out_channel)
        else:
            self.norm = norm

        self.conv1 = nn.Conv2d(in_channel, out_channel,
                               kernel_size=3, stride=stride,
                               weight_init=weight_init)
        self.conv2 = nn.Conv2d(in_channel, out_channel,
                               kernel_size=3, weight_init=weight_init)
        self.relu = nn.ReLU()
        self.down_sample = down_sample

    def construct(self, x):
        """ResidualBlockBase construct."""
        identity = x  # shortcuts分支

        out = self.conv1(x)  # 主分支第一层：3*3卷积层
        out = self.norm(out)
        out = self.relu(out)
        out = self.conv2(out)  # 主分支第二层：3*3卷积层
        out = self.norm(out)

        if self.down_sample is not None:
            identity = self.down_sample(x)
        out += identity  # 输出为主分支与shortcuts之和
        out = self.relu(out)

        return out

ResNet50网络共有5个卷积结构，一个平均池化层，一个全连接层，以CIFAR-10数据集为例：

• conv1：输入图片大小为32×3232×32，输入channel为3。首先经过一个卷积核数量为64，卷积核大小为7×77×7，stride为2的卷积层；然后通过一个Batch Normalization层；最后通过Reul激活函数。该层输出feature map大小为16×1616×16，输出channel为64。
• conv2_x：输入feature map大小为16×1616×16，输入channel为64。首先经过一个卷积核大小为3×33×3，stride为2的最大下采样池化操作；然后堆叠3个[1×1，64；3×3，64；1×1，256][1×1，64；3×3，64；1×1，256]结构的Bottleneck。该层输出feature map大小为8×88×8，输出channel为256。
• conv3_x：输入feature map大小为8×88×8，输入channel为256。该层堆叠4个[1×1，128；3×3，128；1×1，512]结构的Bottleneck。该层输出feature map大小为4×44×4，输出channel为512。
• conv4_x：输入feature map大小为4×44×4，输入channel为512。该层堆叠6个[1×1，256；3×3，256；1×1，1024]结构的Bottleneck。该层输出feature map大小为2×22×2，输出channel为1024。
• conv5_x：输入feature map大小为2×22×2，输入channel为1024。该层堆叠3个[1×1，512；3×3，512；1×1，2048]结构的Bottleneck。该层输出feature map大小为1×11×1，输出channel为2048。
• average pool & fc：输入channel为2048，输出channel为分类的类别数。

from mindspore import load_checkpoint, load_param_into_net


class ResNet(nn.Cell):
    def __init__(self, block: Type[Union[ResidualBlockBase, ResidualBlock]],
                 layer_nums: List[int], num_classes: int, input_channel: int) -> None:
        super(ResNet, self).__init__()

        self.relu = nn.ReLU()
        # 第一个卷积层，输入channel为3（彩色图像），输出channel为64
        self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, weight_init=weight_init)
        self.norm = nn.BatchNorm2d(64)
        # 最大池化层，缩小图片的尺寸
        self.max_pool = nn.MaxPool2d(kernel_size=3, stride=2, pad_mode='same')
        # 各个残差网络结构块定义
        self.layer1 = make_layer(64, block, 64, layer_nums[0])
        self.layer2 = make_layer(64 * block.expansion, block, 128, layer_nums[1], stride=2)
        self.layer3 = make_layer(128 * block.expansion, block, 256, layer_nums[2], stride=2)
        self.layer4 = make_layer(256 * block.expansion, block, 512, layer_nums[3], stride=2)
        # 平均池化层
        self.avg_pool = nn.AvgPool2d()
        # flattern层
        self.flatten = nn.Flatten()
        # 全连接层
        self.fc = nn.Dense(in_channels=input_channel, out_channels=num_classes)

    def construct(self, x):

        x = self.conv1(x)
        x = self.norm(x)
        x = self.relu(x)
        x = self.max_pool(x)

        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        x = self.layer4(x)

        x = self.avg_pool(x)
        x = self.flatten(x)
        x = self.fc(x)

        return x

def _resnet(model_url: str, block: Type[Union[ResidualBlockBase, ResidualBlock]],
            layers: List[int], num_classes: int, pretrained: bool, pretrained_ckpt: str,
            input_channel: int):
    model = ResNet(block, layers, num_classes, input_channel)

    if pretrained:
        # 加载预训练模型
        download(url=model_url, path=pretrained_ckpt, replace=True)
        param_dict = load_checkpoint(pretrained_ckpt)
        load_param_into_net(model, param_dict)

    return model


def resnet50(num_classes: int = 1000, pretrained: bool = False):
    """ResNet50模型"""
    resnet50_url = "https://mindspore-website.obs.cn-north-4.myhuaweicloud.com/notebook/models/application/resnet50_224_new.ckpt"
    resnet50_ckpt = "./LoadPretrainedModel/resnet50_224_new.ckpt"
    return _resnet(resnet50_url, ResidualBlock, [3, 4, 6, 3], num_classes,
                   pretrained, resnet50_ckpt, 2048)

4.模型的训练与评估

# 定义ResNet50网络
network = resnet50(pretrained=True)

# 全连接层输入层的大小
in_channel = network.fc.in_channels
fc = nn.Dense(in_channels=in_channel, out_channels=10)
# 重置全连接层
network.fc = fc

# 设置学习率
num_epochs = 5
lr = nn.cosine_decay_lr(min_lr=0.00001, max_lr=0.001, total_step=step_size_train * num_epochs,
                        step_per_epoch=step_size_train, decay_epoch=num_epochs)
# 定义优化器和损失函数
opt = nn.Momentum(params=network.trainable_params(), learning_rate=lr, momentum=0.9)
loss_fn = nn.SoftmaxCrossEntropyWithLogits(sparse=True, reduction='mean')


def forward_fn(inputs, targets):
    logits = network(inputs)
    loss = loss_fn(logits, targets)
    return loss


grad_fn = ms.value_and_grad(forward_fn, None, opt.parameters)


def train_step(inputs, targets):
    loss, grads = grad_fn(inputs, targets)
    opt(grads)
    return loss

import os

# 创建迭代器
data_loader_train = dataset_train.create_tuple_iterator(num_epochs=num_epochs)
data_loader_val = dataset_val.create_tuple_iterator(num_epochs=num_epochs)

# 最佳模型存储路径
best_acc = 0
best_ckpt_dir = "./BestCheckpoint"
best_ckpt_path = "./BestCheckpoint/resnet50-best.ckpt"

if not os.path.exists(best_ckpt_dir):
    os.mkdir(best_ckpt_dir)


import mindspore.ops as ops


def train(data_loader, epoch):
    """模型训练"""
    losses = []
    network.set_train(True)

    for i, (images, labels) in enumerate(data_loader):
        loss = train_step(images, labels)
        if i % 100 == 0 or i == step_size_train - 1:
            print('Epoch: [%3d/%3d], Steps: [%3d/%3d], Train Loss: [%5.3f]' %
                  (epoch + 1, num_epochs, i + 1, step_size_train, loss))
        losses.append(loss)

    return sum(losses) / len(losses)


def evaluate(data_loader):
    """模型验证"""
    network.set_train(False)

    correct_num = 0.0  # 预测正确个数
    total_num = 0.0  # 预测总数

    for images, labels in data_loader:
        logits = network(images)
        pred = logits.argmax(axis=1)  # 预测结果
        correct = ops.equal(pred, labels).reshape((-1, ))
        correct_num += correct.sum().asnumpy()
        total_num += correct.shape[0]

    acc = correct_num / total_num  # 准确率

    return acc

# 开始循环训练
print("Start Training Loop ...")

for epoch in range(num_epochs):
    curr_loss = train(data_loader_train, epoch)
    curr_acc = evaluate(data_loader_val)

    print("-" * 50)
    print("Epoch: [%3d/%3d], Average Train Loss: [%5.3f], Accuracy: [%5.3f]" % (
        epoch+1, num_epochs, curr_loss, curr_acc
    ))
    print("-" * 50)

    # 保存当前预测准确率最高的模型
    if curr_acc > best_acc:
        best_acc = curr_acc
        ms.save_checkpoint(network, best_ckpt_path)

print("=" * 80)
print(f"End of validation the best Accuracy is: {best_acc: 5.3f}, "
      f"save the best ckpt file in {best_ckpt_path}", flush=True)

5.训练结束，测试训练成果

import matplotlib.pyplot as plt


def visualize_model(best_ckpt_path, dataset_val):
    num_class = 10  # 对狼和狗图像进行二分类
    net = resnet50(num_class)
    # 加载模型参数
    param_dict = ms.load_checkpoint(best_ckpt_path)
    ms.load_param_into_net(net, param_dict)
    # 加载验证集的数据进行验证
    data = next(dataset_val.create_dict_iterator())
    images = data["image"]
    labels = data["label"]
    # 预测图像类别
    output = net(data['image'])
    pred = np.argmax(output.asnumpy(), axis=1)

    # 图像分类
    classes = []

    with open(data_dir + "/batches.meta.txt", "r") as f:
        for line in f:
            line = line.rstrip()
            if line:
                classes.append(line)

    # 显示图像及图像的预测值
    plt.figure()
    for i in range(6):
        plt.subplot(2, 3, i + 1)
        # 若预测正确，显示为蓝色；若预测错误，显示为红色
        color = 'blue' if pred[i] == labels.asnumpy()[i] else 'red'
        plt.title('predict:{}'.format(classes[pred[i]]), color=color)
        picture_show = np.transpose(images.asnumpy()[i], (1, 2, 0))
        mean = np.array([0.4914, 0.4822, 0.4465])
        std = np.array([0.2023, 0.1994, 0.2010])
        picture_show = std * picture_show + mean
        picture_show = np.clip(picture_show, 0, 1)
        plt.imshow(picture_show)
        plt.axis('off')

    plt.show()


# 使用测试数据集进行验证
visualize_model(best_ckpt_path=best_ckpt_path, dataset_val=dataset_val)