Training Techniques | Weight Decay, SGD with Momentum |
---|---|
Architecture | Convolution, Dropout, Dense Connections, ReLU, Max Pooling, Softmax |
ID | alexnet |
SHOW MORE |
AlexNet is a classic convolutional neural network architecture. It consists of convolutions, max pooling and dense layers as the basic building blocks
To load a pretrained model:
import torchvision.models as models
squeezenet = models.alexnet(pretrained=True)
Replace the model name with the variant you want to use, e.g. alexnet
. You can find the IDs in the model summaries at the top of this page.
To evaluate the model, use the image classification recipes from the library.
python train.py --test-only --model='<model_name>'
You can follow the torchvision recipe on GitHub for training a new model afresh.
@article{DBLP:journals/corr/Krizhevsky14,
author = {Alex Krizhevsky},
title = {One weird trick for parallelizing convolutional neural networks},
journal = {CoRR},
volume = {abs/1404.5997},
year = {2014},
url = {http://arxiv.org/abs/1404.5997},
archivePrefix = {arXiv},
eprint = {1404.5997},
timestamp = {Mon, 13 Aug 2018 16:48:41 +0200},
biburl = {https://dblp.org/rec/journals/corr/Krizhevsky14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
BENCHMARK | MODEL | METRIC NAME | METRIC VALUE | GLOBAL RANK |
---|---|---|---|---|
ImageNet | AlexNet | Top 1 Accuracy | 56.55% | # 306 |
Top 5 Accuracy | 79.09% | # 306 |