昇思25天打卡营|Day15 ResNet50图像分类
发表于2024-07-16 23:00:51
0 查看
- 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）。
- 残差网络有2个分支构成：
- 主分支。通过堆叠一系列的卷积操作得到
- shortcuts。输入直接到输出
主分支输出的特征矩阵 F(x) 加上shortcuts输出的特征矩阵x得到F(x)+x，通过Relu激活函数后即为残差网络最后的输出。
- bottle neck 结构：该结构的主分支有三层卷积结构，分别为 1×1 的卷积层、 3×3 卷积层和 1×1 的卷积层，其中 1×1 的卷积层分别起降维和升维的作用。
使用ResNet做图片分类
- 加载数据集
- 数据增强
主要使用的是mindspore.dataset.vision
- 构建残差网络
3.1 实现building block结构
3.2 类实现Bottleneck结构
3.3 实现残差块构建
3.4 实现ResNet构建
- 也可以直接调用
resnet50来构建
- 模型训练与评估
点赞
收藏
回复
分享
举报
主分支输出的特征矩阵 F(x) 加上shortcuts输出的特征矩阵x得到F(x)+x，通过Relu激活函数后即为残差网络最后的输出。
使用ResNet做图片分类
import mindspore.dataset as ds data_set = ds.Cifar10Dataset(dataset_dir=dataset_dir, usage=usage, num_parallel_workers=workers, shuffle=True)主要使用的是
mindspore.dataset.vision3.1 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 out3.2 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 out3.3 实现残差块构建
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)3.4 实现ResNet构建
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 xresnet50来构建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)