mindspore ResNet50图像分类

ResNet网络介绍

ResNet50网络是2015年由微软实验室的何恺明提出，获得ILSVRC2015图像分类竞赛第一名。在ResNet网络提出之前，传统的卷积神经网络都是将一系列的卷积层和池化层堆叠得到的，但当网络堆叠到一定深度时，就会出现退化问题。ResNet网络提出了残差网络结构(Residual Network)来减轻退化问题，使用ResNet网络可以实现搭建较深的网络结构（突破1000层）。

环境安装

%%capture captured_output
# 实验环境已经预装了mindspore==2.2.14，如需更换mindspore版本，可更改下面mindspore的版本号
!pip uninstall mindspore -y
!pip install -i https://pypi.mirrors.ustc.edu.cn/simple mindspore==2.2.14

数据集准备与加载

CIFAR-10数据集共有60000张32*32的彩色图像，分为10个类别，每类有6000张图，数据集一共有50000张训练图片和10000张评估图片。首先，如下示例使用download接口下载并解压，目前仅支持解析二进制版本的CIFAR-10文件（CIFAR-10 binary version）。

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)

一样从华为obs下载。

然后，使用mindspore.dataset.Cifar10Dataset接口来加载数据集，并进行相关图像增强操作。

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):

    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)
        ]

    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()

对CIFAR-10训练数据集进行可视化。

import matplotlib.pyplot as plt
import numpy as np

data_iter = next(dataset_train.create_dict_iterator())

images = data_iter["image"].asnumpy()
labels = data_iter["label"].asnumpy()
print(f"Image shape: {images.shape}, Label shape: {labels.shape}")

# 训练数据集中，前六张图片所对应的标签
print(f"Labels: {labels[:6]}")

classes = []

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

# 训练数据集的前六张图片
plt.figure()
for i in range(6):
    plt.subplot(2, 3, i + 1)
    image_trans = np.transpose(images[i], (1, 2, 0))
    mean = np.array([0.4914, 0.4822, 0.4465])
    std = np.array([0.2023, 0.1994, 0.2010])
    image_trans = std * image_trans + mean
    image_trans = np.clip(image_trans, 0, 1)
    plt.title(f"{classes[labels[i]]}")
    plt.imshow(image_trans)
    plt.axis("off")
plt.show()

构建网络

残差网络结构主要由两种，一种是Building Block，适用于较浅的ResNet网络，如ResNet18和ResNet34；另一种是Bottleneck，适用于层数较深的ResNet网络，如ResNet50、ResNet101和ResNet152。

Building Block

如下代码定义ResidualBlockBase类实现Building Block结构。

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

Bottleneck

Bottleneck结构图如下图所示，在输入相同的情况下Bottleneck结构相对Building Block结构的参数数量更少，更适合层数较深的网络，ResNet50使用的残差结构就是Bottleneck。该结构的主分支有三层卷积结构，分别为1×11×1的卷积层、3×33×3卷积层和1×11×1的卷积层，其中1×11×1的卷积层分别起降维和升维的作用。

如下代码定义ResidualBlock类实现Bottleneck结构。

class ResidualBlock(nn.Cell):
    expansion = 4  # 最后一个卷积核的数量是第一个卷积核数量的4倍

    def __init__(self, in_channel: int, out_channel: int,
                 stride: int = 1, down_sample: Optional[nn.Cell] = None) -> None:
        super(ResidualBlock, self).__init__()

        self.conv1 = nn.Conv2d(in_channel, out_channel,
                               kernel_size=1, weight_init=weight_init)
        self.norm1 = nn.BatchNorm2d(out_channel)
        self.conv2 = nn.Conv2d(out_channel, out_channel,
                               kernel_size=3, stride=stride,
                               weight_init=weight_init)
        self.norm2 = nn.BatchNorm2d(out_channel)
        self.conv3 = nn.Conv2d(out_channel, out_channel * self.expansion,
                               kernel_size=1, weight_init=weight_init)
        self.norm3 = nn.BatchNorm2d(out_channel * self.expansion)

        self.relu = nn.ReLU()
        self.down_sample = down_sample

    def construct(self, x):

        identity = x  # shortscuts分支

        out = self.conv1(x)  # 主分支第一层：1*1卷积层
        out = self.norm1(out)
        out = self.relu(out)
        out = self.conv2(out)  # 主分支第二层：3*3卷积层
        out = self.norm2(out)
        out = self.relu(out)
        out = self.conv3(out)  # 主分支第三层：1*1卷积层
        out = self.norm3(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

 构建ResNet50网络

如下示例定义make_layer实现残差块的构建，其参数如下所示:

• last_out_channel：上一个残差网络输出的通道数。
• block：残差网络的类别，分别为ResidualBlockBase和ResidualBlock。
• channel：残差网络输入的通道数。
• block_nums：残差网络块堆叠的个数。
• stride：卷积移动的步幅。

def make_layer(last_out_channel, block: Type[Union[ResidualBlockBase, ResidualBlock]],
               channel: int, block_nums: int, stride: int = 1):
    down_sample = None  # shortcuts分支

    if stride != 1 or last_out_channel != channel * block.expansion:

        down_sample = nn.SequentialCell([
            nn.Conv2d(last_out_channel, channel * block.expansion,
                      kernel_size=1, stride=stride, weight_init=weight_init),
            nn.BatchNorm2d(channel * block.expansion, gamma_init=gamma_init)
        ])

    layers = []
    layers.append(block(last_out_channel, channel, stride=stride, down_sample=down_sample))

    in_channel = channel * block.expansion
    # 堆叠残差网络
    for _ in range(1, block_nums):

        layers.append(block(in_channel, channel))

    return nn.SequentialCell(layers)

 

如下示例代码实现ResNet50模型的构建，通过用调函数resnet50即可构建ResNet50模型，函数resnet50参数如下：

• num_classes：分类的类别数，默认类别数为1000。
• pretrained：下载对应的训练模型，并加载预训练模型中的参数到网络中。

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)

模型训练与评估

本节使用ResNet50预训练模型进行微调。调用resnet50构造ResNet50模型，并设置pretrained参数为True，将会自动下载ResNet50预训练模型，并加载预训练模型中的参数到网络中。然后定义优化器和损失函数，逐个epoch打印训练的损失值和评估精度，并保存评估精度最高的ckpt文件（resnet50-best.ckpt）到当前路径的./BestCheckPoint下。

由于预训练模型全连接层（fc）的输出大小（对应参数num_classes）为1000， 为了成功加载预训练权重，我们将模型的全连接输出大小设置为默认的1000。CIFAR10数据集共有10个分类，在使用该数据集进行训练时，需要将加载好预训练权重的模型全连接层输出大小重置为10。

此处我们展示了5个epochs的训练过程，如果想要达到理想的训练效果，建议训练80个epochs。

 

# 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)

 

 可视化模型预测

定义visualize_model函数，使用上述验证精度最高的模型对CIFAR-10测试数据集进行预测，并将预测结果可视化。若预测字体颜色为蓝色表示为预测正确，预测字体颜色为红色则表示预测错误。

由上面的结果可知，5个epochs下模型在验证数据集的预测准确率在70%左右，即一般情况下，6张图片中会有2张预测失败。如果想要达到理想的训练效果，建议训练80个epochs。

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)

 

最后随机采样几个，发现全部正确。

总结

本篇主要讲了用mindspore框架如何定义resnet网络用于图像的分类。resnet通过跳跃连接方式，保留了之前学习到的特征，可以构建更加深层的神经网络。当然后面的训练使用了预训练模型。一般来说，如果仅仅实现功能，就直接调用resnet预训练模型和api框架即可。如果要进行底层网络结构的修改，就定义网络，对其中模型进行修改，重新训练。