Skip to content

AutoDeeplab / auto-deeplab / Hierarchical Neural Architecture Search implemented in Pytorch

Notifications You must be signed in to change notification settings

xalelax/AutoML

 
 

Repository files navigation

AutoML for Image Segmentation and Detection

This is an open-source project of AutoML for object detection & segmentation as well as semantic segmentation.

Currently this repo contains a pytorch implementation for Auto-Deeplab.

Following the popular trend of modern CNN architectures having a two level hierarchy. Auto-Deeplab forms a dual level search space, searching for optimal network and cell architecture. network and cell level search space

Auto-Deeplab acheives a better performance while minimizing the size of the final model. model results

Requirements

  • Pytorch version 1.1

  • Python 3

  • tensorboardX

  • torchvision

  • pycocotools

  • tqdm

  • numpy

  • pandas

Training

Start training

CUDA_VISIBLE_DEVICES=0 python train_autodeeplab.py --dataset cityscapes

Resume training

CUDA_VISIBLE_DEVICES=0 python train_autodeeplab.py --dataset cityscapes --resume /AutoDeeplabpath/checkpoint.pth.tar

Multi-GPU training

CUDA_VISIBLE_DEVICES=0,1 python train_autodeeplab.py --dataset cityscapes --batch_size 2

References

[1] : Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation

[2] : pytorch-deeplab-xception

[3] : Some code for the project was taken from here

About

AutoDeeplab / auto-deeplab / Hierarchical Neural Architecture Search implemented in Pytorch

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 99.7%
  • Shell 0.3%