昇思25天学习打卡营第17天|ResNet50图像分类

        ResNet50网络是由微软实验室的何恺明在2015年提出，并在ILSVRC2015图像分类竞赛中获得第一名。传统的卷积神经网络在网络深度增加时会出现退化问题，而ResNet通过引入残差网络结构（Residual Network），有效减轻了退化问题，使得网络层数可以突破1000层。

        图像分类是最基础的计算机视觉应用，属于有监督学习类别，如给定一张图像(猫、狗、飞机、汽车等等)，判断图像所属的类别。本章将介绍使用ResNet50网络对CIFAR-10数据集进行分类。

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，数据集包含50000张训练图片和10000张评估图片。首先，使用下载接口下载并解压数据集。

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)

        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"
batch_size = 64
image_size = 32
workers = 1

def create_dataset_cifar10(dataset_dir, usage, resize, batch_size, workers):
    data_set = ds.Cifar10Dataset(dataset_dir=dataset_dir, usage=usage, num_samples=10000, 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)
    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)
    data_set = data_set.batch(batch_size)
    return data_set

dataset_train = create_dataset_cifar10(data_dir, "train", image_size, batch_size, workers)
dataset_val = create_dataset_cifar10(data_dir, "test", image_size, batch_size, workers)

模型构建

构建残差网络结构

import mindspore.nn as nn
from mindspore.common.initializer import Normal

weight_init = Normal(mean=0, sigma=0.02)
gamma_init = Normal(mean=1, sigma=0.02)

class ResidualBlock(nn.Cell):
    expansion = 4

    def __init__(self, in_channel, out_channel, stride=1, down_sample=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
        out = self.conv1(x)
        out = self.norm1(out)
        out = self.relu(out)
        out = self.conv2(out)
        out = self.norm2(out)
        out = self.relu(out)
        out = self.conv3(out)
        out = self.norm3(out)
        if self.down_sample is not None:
            identity = self.down_sample(x)
        out += identity
        out = self.relu(out)
        return out

构建ResNet50网络

from mindspore import load_checkpoint, load_param_into_net

def make_layer(last_out_channel, block, channel, block_nums, stride=1):
    down_sample = None
    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
    for _ in range(1, block_nums):
        layers.append(block(in_channel, channel))
    return nn.SequentialCell(layers)

class ResNet(nn.Cell):
    def __init__(self, block, layer_nums, num_classes, input_channel):
        super(ResNet, self).__init__()
        self.relu = nn.ReLU()
        self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, weight_init=weight_init)
        self.norm = nn.BatchNorm2d(64)
        self.max_pool = nn.MaxPool2d(kernel_size=3, stride=2, pad_mode='same')
        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)
        self.avg_pool = nn.AvgPool2d()
        self.flatten = nn.Flatten()
        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, block, layers, num_classes, pretrained, pretrained_ckpt, input_channel):
    model = ResNet(block, layers, num_classes, input_channel)
    if pretrained:
        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=1000, pretrained=False):
    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

        使用ResNet50预训练模型进行微调。首先调用resnet50构建ResNet50模型，并设置pretrained参数为True，下载并加载预训练模型参数。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。

# 定义ResNet50网络
network = resnet50(pretrained=True)
in_channel = network.fc.in_channels
fc = nn.Dense(in_channels=in_channel, out_channels=10)
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)
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

data_loader_train = dataset_train.create_tuple_iterator(num_epochs=num_epochs)
data_loader_val = dataset_val.create_tuple_iterator(num_epochs=num_epochs)

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):
    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):
    network.set_train(False)
    correct_num = 0.0
    total_num = 0.0
    for images, labels in data_loader:
        logits = network(images)
        pred = logits.argmax(axis=1)
        correct = ops.equal(pred, labels).reshape((-1, ))
        correct_num += correct.sum().asnumpy()
        total_num += correct.shape[0]
    acc = correct_num / total_num
    return acc

# 开始训练
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)
    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

模型可视化

        定义visualize_model函数，使用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预测正确，预测字体颜色为红色则表示预测错误。

import matplotlib.pyplot as plt

def visualize_model(best_ckpt_path, dataset_val):
    num_class = 10
    net = resnet50(num_class)
    param_dict = ms.load_checkpoint(best_ckpt_path)
    ms.load_param_into_net(net, param_dict)
    data = next(dataset_val.create_dict_iterator())
    images = data["image"]
    labels = data["label"]
    output = net(data['image'])
    pred = np.argmax(output.asnumpy(), axis=1)
    classes = []
    with open(data_dir + "/batches.meta.txt", "r") as f:
        for line in f:
            line = line.rstrip()
            if line:
                classes.append(line)
    plt.figure()
    for i in range(6):
        plt.subplot(2, 3, i + 1)
        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)

结果

学习心得：通过数据增强技术增加数据集的多样性，提高模型的泛化能力是关键。ResNet50使用Bottleneck模块，通过三层卷积的组合实现更高效的特征提取。学习率调度和优化器的选择对模型的训练效果影响巨大，使用预训练模型进行微调可以加速模型收敛并提高效果。定期评估模型性能并保存最佳模型，确保最终性能最优。通过可视化模型预测结果，可以直观地了解模型的分类能力和错误分类情况，有助于进一步优化和改进模型。

如果你觉得这篇博文对你有帮助，请点赞、收藏、关注我，并且可以打赏支持我！

欢迎关注我的后续博文，我将分享更多关于深度学习和计算机视觉的精彩内容。

谢谢大家的支持！