Implement a model with AlexNet

Davood_Kalami · August 18, 2017, 9:34am

I’m new to pytorch and i want to implement an example on Alextnet with pytorch , where can i find a good exmaple with all details which run an alextnet on a model ?
thanks

moskomule · August 18, 2017, 12:46pm

Hi torchvision includes AlexNet implementation. https://github.com/pytorch/vision/tree/master/torchvision/models

aspiringguru · June 2, 2018, 6:53am

I came here with similar question.
alexnet.py is an implenmentation

github.com

pytorch/vision/blob/master/torchvision/models/alexnet.py

import torch.nn as nn
import torch.utils.model_zoo as model_zoo


__all__ = ['AlexNet', 'alexnet']


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


class AlexNet(nn.Module):

    def __init__(self, num_classes=1000):
        super(AlexNet, self).__init__()
        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),

This file has been truncated. show original

some more explanation here.
https://pytorch.org/docs/master/torchvision/models.html

I was going to reimplement this example of squeezenet using alexnet.

http://blog.outcome.io/pytorch-quick-start-classifying-an-image/

but I haven’t worked out how to load the image file and transform it to suit alexnet.

ptrblck · June 2, 2018, 9:25am

The blog post you shared seems to explain the image loading and processing quite well. Where do you get stuck?