PyTorch: https://github.com/shanglianlm0525/PyTorch-Networks
进口火炬
进口火炬。神经网络是神经网络
进口torchvision
类AlexNet (nn.Module):
def __init__(自我,num_classes=1000):
超级(AlexNet自我). __init__ ()
自我。feature_extraction=nn.Sequential (
nn.Conv2d (in_channels=3, out_channels=96, kernel_size=11,跨步=4,填充=2,偏见=False),
nn.ReLU(原地=True),
nn.MaxPool2d (kernel_size=3,跨步=2,填充=0),
nn.Conv2d (in_channels=96, out_channels=192, kernel_size=5,跨步=1,填充=2,偏见=False),
nn.ReLU(原地=True),
nn.MaxPool2d (kernel_size=3,跨步=2,填充=0),
nn.Conv2d (in_channels=192, out_channels=384, kernel_size=3,跨步=1,填充=1,偏见=False),
nn.ReLU(原地=True),
nn.Conv2d (in_channels=384, out_channels=256, kernel_size=3,跨步=1,填充=1,偏见=False),
nn.ReLU(原地=True),
nn.Conv2d (in_channels=256, out_channels=256, kernel_size=3,跨步=1,填充=1,偏见=False),
nn.ReLU(原地=True),
神经网络。MaxPool2d (kernel_size=3,跨步=2,填充=0),
）
自我。分类器=nn.Sequential (
nn.Dropout (p=0.5),
nn.Linear (in_features=256 * 6 * 6, out_features=4096),
nn.ReLU(原地=True),
nn.Dropout (p=0.5),
神经网络。线性(in_features=4096, out_features=4096),
nn.ReLU(原地=True),
神经网络。线性(in_features=4096, out_features=num_classes),
）
def向前(自我,x):
x=self.feature_extraction (x)
x=x.view (x.size (0) 256 * 6 * 6)
x=self.classifier (x)
返回x
if __name__==癬_main__”:
#=torchvision.models.AlexNet模型()
模型=AlexNet ()
打印(模型)
输入=torch.randn (3224224)=模型(输入)
打印(out.shape)
之前
以上这篇PyTorch实现AlexNet示例就是小编分享给大家的全部内容了,希望能给大家一个参考,也希望大家多多支持。
