[6기] 프로그래머스 인공지능 데브코스 56일차 TIL

1026

[10주차 - Day4] Deep Learning 기초

과제

과제에 넣을 예제 코드 업로드

import torch
import torch.nn as nn
from torch.hub import load_state_dict_from_url
from typing import Any


__all__ = ['AlexNet', 'alexnet']


model_urls = {
    'alexnet': 'https://download.pytorch.org/models/alexnet-owt-4df8aa71.pth',
}


class AlexNet(nn.Module):

    def __init__(self, num_classes: int = 1000) -> None:
        super(AlexNet, self).__init__()
        self.features = nn.Sequential(
            #Conv1
            #input channel : 3 , output channel : 64, kernel_size : 11, stride : 4, padding : 2
            nn.Conv2d(1, 64, kernel_size=11, stride=4, padding=2),
            nn.ReLU(inplace=True), # inplace=True 하면, inplace 연산을 수행함, inplace 연산은 결과값을 새로운 변수에 값을 저장하는 대신 기존의 데이터를 대체하는것을 의미
            #Max Pool1
            nn.MaxPool2d(kernel_size=3, stride=2),
            #Conv2
            nn.Conv2d(64, 192, kernel_size=5, padding=2),
            nn.ReLU(inplace=True),
            #Max Pool2
            nn.MaxPool2d(kernel_size=3, stride=2),
            #Conv3
            nn.Conv2d(192, 384, kernel_size=3, padding=1),
            nn.ReLU(inplace=True),
            ##Conv4
            nn.Conv2d(384, 256, kernel_size=3, padding=1),
            nn.ReLU(inplace=True),
            #Conv5
            nn.Conv2d(256, 256, kernel_size=3, padding=1),
            nn.ReLU(inplace=True),
            #Max Pool3
            nn.MaxPool2d(kernel_size=3, stride=2),
        )
        self.avgpool = nn.AdaptiveAvgPool2d((6, 6))
        self.classifier = nn.Sequential(
            #드롭아웃
            nn.Dropout(),
            nn.Linear(256 * 6 * 6, 4096),
            nn.ReLU(inplace=True),
            nn.Dropout(),
            nn.Linear(4096, 4096),
            nn.ReLU(inplace=True),
            nn.Linear(4096, num_classes),
        )

    def forward(self, x: torch.Tensor) -> torch.Tensor:
        #특징 추출 부분
        x = self.features(x)

        x = self.avgpool(x)
        #output shape : (batch size * 256(channel), 6, 6)
        #Flatten
        x = torch.flatten(x, 1)
        #output shape (batch_size, 256 * 6* 6)
        #분류 분류
        x = self.classifier(x)
        return x
def alexnet(pretrained: bool = False, progress: bool = True, **kwargs: Any) -> AlexNet:
    r"""AlexNet model architecture from the
    `"One weird trick..." <https://arxiv.org/abs/1404.5997>`_ paper.
    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
        progress (bool): If True, displays a progress bar of the download to stderr
    """
    model = AlexNet(**kwargs)
    if pretrained:
        state_dict = load_state_dict_from_url(model_urls['alexnet'],
                                              progress=progress)
        model.load_state_dict(state_dict)
    return model

net = alexnet()
print(net)