Skip to content

Latest commit

 

History

History
74 lines (44 loc) · 1.65 KB

README.md

File metadata and controls

74 lines (44 loc) · 1.65 KB

VGG-Implementation

"Very Deep Convolutional Networks for Large-Scale Image Recognition" by Karen Simonyan and Andrew Zisserman.

Paper: https://arxiv.org/pdf/1409.1556.pdf

Configuration

VGG Configurations

Architecture

VGG Architecture

Different day, same old story

GPU POOR !!!

Didn't train cause I don't have a powerful GPU. But the architecture is there for playing.

Info

Run script below to checkout the model informations

python info.py

VGG11 (A)

vgg11

VGG11_LRN (A-LRN)

vgg11_lrn

VGG13 (B)

vgg13

VGG16_1 (C)

vgg16_1

VGG16 (D)

vgg16

VGG19 (E)

vgg19

Usage

Before running the script, place your data directory location for both train and test data in root_dir="{DIR}" here at dataloader.py

python train.py --epochs 74 --vgg vgg16

Citation

@misc{simonyan2015deepconvolutionalnetworkslargescale,
      title={Very Deep Convolutional Networks for Large-Scale Image Recognition}, 
      author={Karen Simonyan and Andrew Zisserman},
      year={2015},
      eprint={1409.1556},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/1409.1556}, 
}