Need help with PNASNet.TF?
Click the “chat” button below for chat support from the developer who created it, or find similar developers for support.

About the developer

chenxi116
102 Stars 23 Forks Apache License 2.0 8 Commits 2 Opened issues

Description

TensorFlow implementation of PNASNet-5 on ImageNet

Services available

!
?

Need anything else?

Contributors list

# 112,547
Python
pytorch
deeplab
deeplab...
8 commits

PNASNet.TF

TensorFlow implementation of PNASNet-5. While completely compatible with the official implementation, this implementation focuses on simplicity and inference.

In particular, three files of 1200 lines in total (

nasnet.py
,
nasnet_utils.py
,
pnasnet.py
) are refactored into two files of 400 lines in total (
cell.py
,
pnasnet.py
). This code no longer supports
NCHW
data format, primarily because the released model was trained with
NHWC
. I tried to keep the rough structure and all functionalities of the official implementation when simplifying it.

If you use the code, please cite:

bash
@inproceedings{liu2018progressive,
  author    = {Chenxi Liu and
               Barret Zoph and
               Maxim Neumann and
               Jonathon Shlens and
               Wei Hua and
               Li{-}Jia Li and
               Li Fei{-}Fei and
               Alan L. Yuille and
               Jonathan Huang and
               Kevin Murphy},
  title     = {Progressive Neural Architecture Search},
  booktitle = {European Conference on Computer Vision},
  year      = {2018}
}

Requirements

  • TensorFlow 1.8.0
  • torchvision 0.2.1 (for dataset loading)

Data and Model Preparation

  • Download the ImageNet validation set and move images to labeled subfolders. To do the latter, you can use this script. Make sure the folder
    val
    is under
    data/
    .
  • Download the
    PNASNet-5_Large_331
    pretrained model:
    bash
    cd data
    wget https://storage.googleapis.com/download.tensorflow.org/models/pnasnet-5_large_2017_12_13.tar.gz
    tar xvf pnasnet-5_large_2017_12_13.tar.gz
    

Usage

python main.py

The last printed line should read:

bash
Test: [50000/50000] [email protected] 0.829    [email protected] 0.962

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.