昇思25天学习打卡营第17天|ResNet50迁移学习

最新推荐文章于 2024-08-03 21:32:51 发布

流淌_

最新推荐文章于 2024-08-03 21:32:51 发布

阅读量671

点赞数 29

文章标签：学习迁移学习深度学习

本文链接：https://blog.csdn.net/randomize0/article/details/140318219

版权

今天是参加昇思25天学习打卡营的第17天，今天打卡的课程是“ResNet50迁移学习”，这里做一个简单的分享。

1.简介

上节课的学习了ResNet50图像分类相关的内容，今天学习的内容是的"ResNet50迁移学习"相关的内容。

迁移学习就是把已训练好的模型参数迁移到新的模型来帮助新模型训练。在实际场景中的，由于训练数据集不足，所以很少会从头开始训练整个网络。普遍做法是，在一个大的数据集上训练得到一个预训练模型，然后使用该模型来初始化网络的权重参数或作为固定特征提取器应用于特定的任务中。

今天学习的内容是采用ResNet50模型进行迁移学习，将数据集中到的狼和狗的图像分类。

2.迁移学习实例

网络定义

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


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
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

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)
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, pretrianed_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=pretrianed_ckpt, replace=True)
        param_dict = load_checkpoint(pretrianed_ckpt)
        load_param_into_net(model, param_dict)

    return model

# 预训练模型
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)

固定特征训练

使用固定特征进行训练的时候，需要冻结除最后一层之外的所有网络层。通过设置 requires_grad == False 冻结参数，以便不在反向传播中计算梯度。

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, pretrianed_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=pretrianed_ckpt, replace=True)
        param_dict = load_checkpoint(pretrianed_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)

3.小结

迁移学习是机器学习里的重要内容。理解迁移学习不仅可以让我们理解学习到的特征而且让我们重新理解了神经网络”学习“的本质和方式。迁移学习的是一个很好的将模型落地到自身业务的方法，可以降低模型部署应用的成本和技术难度。当然迁移学习也需要考虑具体的应用场景，迁移学习的前提是业务场景功能近似，选择错误的基础模型会取得相反的结果。

以上是第17天的学习内容，附上今日打卡记录：
在这里插入图片描述

流淌_

关注

29
点赞
踩
4

收藏

觉得还不错? 一键收藏
0
评论
昇思25天学习打卡营第17天|ResNet50迁移学习

上节课的学习了ResNet50图像分类相关的内容，今天学习的内容是的"ResNet50迁移学习"相关的内容。迁移学习就是把已训练好的模型参数迁移到新的模型来帮助新模型训练。在实际场景中的，由于训练数据集不足，所以很少会从头开始训练整个网络。普遍做法是，在一个大的数据集上训练得到一个预训练模型，然后使用该模型来初始化网络的权重参数或作为固定特征提取器应用于特定的任务中。今天学习的内容是采用ResNet50模型进行迁移学习，将数据集中到的狼和狗的图像分类。
复制链接

扫一扫