Source code for torchvision.models.alexnet
from typing import Any
import torch
import torch.nn as nn
from .._internally_replaced_utils import load_state_dict_from_url
from ..utils import _log_api_usage_once
__all__ = ["AlexNet", "alexnet"]
model_urls = {
"alexnet": "https://download.pytorch.org/models/alexnet-owt-7be5be79.pth",
}
class AlexNet(nn.Module):
def __init__(self, num_classes: int = 1000, dropout: float = 0.5) -> None:
super().__init__()
_log_api_usage_once(self)
self.features = nn.Sequential(
nn.Conv2d(3, 64, kernel_size=11, stride=4, padding=2),
nn.ReLU(inplace=True),
nn.MaxPool2d(kernel_size=3, stride=2),
nn.Conv2d(64, 192, kernel_size=5, padding=2),
nn.ReLU(inplace=True),
nn.MaxPool2d(kernel_size=3, stride=2),
nn.Conv2d(192, 384, kernel_size=3, padding=1),
nn.ReLU(inplace=True),
nn.Conv2d(384, 256, kernel_size=3, padding=1),
nn.ReLU(inplace=True),
nn.Conv2d(256, 256, kernel_size=3, padding=1),
nn.ReLU(inplace=True),
nn.MaxPool2d(kernel_size=3, stride=2),
)
self.avgpool = nn.AdaptiveAvgPool2d((6, 6))
self.classifier = nn.Sequential(
nn.Dropout(p=dropout),
nn.Linear(256 * 6 * 6, 4096),
nn.ReLU(inplace=True),
nn.Dropout(p=dropout),
nn.Linear(4096, 4096),
nn.ReLU(inplace=True),
nn.Linear(4096, num_classes),
)
def forward(self, x: torch.Tensor) -> torch.Tensor:
x = self.features(x)
x = self.avgpool(x)
x = torch.flatten(x, 1)
x = self.classifier(x)
return x
[docs]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.
The required minimum input size of the model is 63x63.
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