《昇思25天学习打卡营第6天|ResNet50图像分类》

写在前面

从本次开始，接触一些上层应用。
本次通过经典的模型，开始本次任务。这里开始学习resnet50网络模型，应该也会有resnet18，估计18的模型速度会更快一些。

resnet

通过对论文的结论进行展示，说明了模型的功能，解决了卷积网络层数加大后模型的退化问题。20层和56层相比，层数越大，模型效果越差，因此resnet主要解决这种问题。hekaiming是真的强呀。

基本流程

1. 整理模型数据
2. 构建模型网络核心逻辑（ResidualBlockBase/ResidualBlock）
3. 创建模型一层

构建网络的代码

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

创建模型一层

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)

创建模型

搭建一个4层的网络。

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

接下来，连接数据和模型网络，开始构建容易使用的网络。在这里设置了，模型残差的方法和每个block。

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)

模型训练和评估

并没有完全训练，使用了预训练的方法，下载了预训练的模型。

# 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

有了模型网络，接下来需要进行模型训练。训练的过程要设置学习率、优化器和损失函数。

# 设置学习率
num_epochs = 1
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

之后进行多个epoch的迭代，实现模型训练的目标。

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)

进行多轮训练之后，达到训练的目的，模型开始进行收敛，并且能够获取到最终的结果。

最后进行评估，这个并不复杂。

打开