AutoDeeplab / auto-deeplab / AutoML for semantic segmentation, implemented in Pytorch

Overview

AutoML for Image Semantic Segmentation

Currently this repo contains the only working open-source implementation of Auto-Deeplab which, by the way out-performs that of the original paper.

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

Our results:79.8 miou with Autodeeplab-M, train for 4000epochs and batch_size=16, about 800K iters

Our Search implementation currently achieves BETTER results than that of the authors in the original AutoDeeplab paper. Awesome!

Search results from the auto-deeplab paper which achieve 35% after 40 epochs of searching:
paper mIOU
VS our search results which acheive 37% after 40 epochs of searching:
our mIOU:


Training Proceedure

All together there are 3 stages:

  1. Architecture Search - Here you will train one large relaxed architecture that is meant to represent many discreet smaller architectures woven together.

  2. Decode - Once you've finished the architecture search, load your large relaxed architecture and decode it to find your optimal architecture.

  3. Re-train - Once you have a decoded and poses a final description of your optimal model, use it to build and train your new optimal model



Hardware Requirement

  • For architecture search, you need at least an 15G GPU, or two 11G gpus(in this way, global pooling in aspp is banned, not recommended)

  • For retraining autodeeplab-M or autodeeplab-S, you need at least n more than 11G gpus to re-train with batch size 2n without distributed

  • For retraining autodeeplab-L, you need at least n more than 11G gpus to re-train with batch size 2n with distributed

Architecture Search

Begin Architecture Search

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

Re-train

Now that you're done training the search algorithm, it's time to decode the search space and find your new optimal architecture. After that just build your new model and begin training it

Load and Decode

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

Retrain

Train without distributed

python train.py

Train with distributed

CUDA_VISIBLE_DEVICES=0,1,2,···,n python -m torch.distributed.launch --nproc_per_node=n train_distributed.py  

Result models

We provided models after search and retrain [baidu drive (passwd: xm9z)] [google drive]

Requirements

  • Pytorch version 1.1

  • Python 3

  • tensorboardX

  • torchvision

  • pycocotools

  • tqdm

  • numpy

  • pandas

  • apex

References

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

[2] : Thanks for jfzhang's deeplab v3+ implemention of pytorch

[3] : Thanks for MenghaoGuo's autodeeplab model implemention

[4] : Thanks for CoinCheung's deeplab v3+ implemention of pytorch

[5] : Thanks for chenxi's deeplab v3 implemention of pytorch

TODO

  • Retrain our search model

  • adding support for other datasets(e.g. VOC, ADE20K, COCO and so on.)

Owner
AI Necromancer
WeChat: BuffaloNoam; Line: buffalonoam; WhatsApp: +972524226459
AI Necromancer
Code for Ditto: Building Digital Twins of Articulated Objects from Interaction

Ditto: Building Digital Twins of Articulated Objects from Interaction Zhenyu Jiang, Cheng-Chun Hsu, Yuke Zhu CVPR 2022, Oral Project | arxiv News 2022

UT Robot Perception and Learning Lab 78 Dec 22, 2022
Task-based end-to-end model learning in stochastic optimization

Task-based End-to-end Model Learning in Stochastic Optimization This repository is by Priya L. Donti, Brandon Amos, and J. Zico Kolter and contains th

CMU Locus Lab 164 Dec 29, 2022
Training RNNs as Fast as CNNs

News SRU++, a new SRU variant, is released. [tech report] [blog] The experimental code and SRU++ implementation are available on the dev branch which

ASAPP Research 2.1k Jan 01, 2023
Numerai tournament example scripts using NN and optuna

numerai_NN_example Numerai tournament example scripts using pytorch NN, lightGBM and optuna https://numer.ai/tournament Performance of my model based

Takahiro Maeda 12 Oct 10, 2022
[ACL-IJCNLP 2021] "EarlyBERT: Efficient BERT Training via Early-bird Lottery Tickets"

EarlyBERT This is the official implementation for the paper in ACL-IJCNLP 2021 "EarlyBERT: Efficient BERT Training via Early-bird Lottery Tickets" by

VITA 13 May 11, 2022
MonoRCNN is a monocular 3D object detection method for automonous driving

MonoRCNN MonoRCNN is a monocular 3D object detection method for automonous driving, published at ICCV 2021. This project is an implementation of MonoR

87 Dec 27, 2022
Bling's Object detection tool

BriVL for Building Applications This repo is used for illustrating how to build applications by using BriVL model. This repo is re-implemented from fo

chuhaojin 47 Nov 01, 2022
Python inverse kinematics for your robot model based on Pinocchio.

Python inverse kinematics for your robot model based on Pinocchio.

Stéphane Caron 50 Dec 22, 2022
Finding all things on-prem Microsoft for password spraying and enumeration.

msprobe About Installing Usage Examples Coming Soon Acknowledgements About Finding all things on-prem Microsoft for password spraying and enumeration.

205 Jan 09, 2023
A forwarding MPI implementation that can use any other MPI implementation via an MPI ABI

MPItrampoline MPI wrapper library: MPI trampoline library: MPI integration tests: MPI is the de-facto standard for inter-node communication on HPC sys

Erik Schnetter 31 Dec 22, 2022
Complete U-net Implementation with keras

U Net Lowered with Keras Complete U-net Implementation with keras Original Paper Link : https://arxiv.org/abs/1505.04597 Special Implementations : The

Sagnik Roy 14 Oct 10, 2022
[Open Source]. The improved version of AnimeGAN. Landscape photos/videos to anime

[Open Source]. The improved version of AnimeGAN. Landscape photos/videos to anime

CC 4.4k Dec 27, 2022
Gif-caption - A straightforward GIF Captioner written in Python

Broksy's GIF Captioner Have you ever wanted to easily caption a GIF without havi

3 Apr 09, 2022
Very Deep Convolutional Networks for Large-Scale Image Recognition

pytorch-vgg Some scripts to convert the VGG-16 and VGG-19 models [1] from Caffe to PyTorch. The converted models can be used with the PyTorch model zo

Justin Johnson 217 Dec 05, 2022
Official Python implementation of the 'Sparse deconvolution'-v0.3.0

Sparse deconvolution Python v0.3.0 Official Python implementation of the 'Sparse deconvolution', and the CPU (NumPy) and GPU (CuPy) calculation backen

Weisong Zhao 23 Dec 28, 2022
Rainbow is all you need! A step-by-step tutorial from DQN to Rainbow

Do you want a RL agent nicely moving on Atari? Rainbow is all you need! This is a step-by-step tutorial from DQN to Rainbow. Every chapter contains bo

Jinwoo Park (Curt) 1.4k Dec 29, 2022
Simulation of Self Driving Car

In this repository, the code to use Udacity's self driving car simulator as a testbed for training an autonomous car are provided.

Shyam Das Shrestha 1 Nov 21, 2021
McGill Physics Hackathon 2021: Reaction-Diffusion Models for the Generation of Biological Patterns

DiffuseAnimals: Reaction-Diffusion Models for the Generation of Biological Patterns Introduction Reaction-diffusion equations can be utilized in order

Austin Szuminsky 2 Mar 07, 2022
Generate image analogies using neural matching and blending

neural image analogies This is basically an implementation of this "Image Analogies" paper, In our case, we use feature maps from VGG16. The patch mat

Adam Wentz 3.5k Jan 08, 2023