Mae segmentation - Reproduction of semantic segmentation using masked autoencoder (mae)

Last update: Dec 17, 2022

Overview

ADE20k Semantic segmentation with MAE

Getting started

Install the mmsegmentation library and some required packages.

pip install mmcv-full==1.3.0 mmsegmentation==0.11.0
pip install scipy timm==0.3.2

Install apex for mixed-precision training

git clone https://github.com/NVIDIA/apex
cd apex
pip install -v --disable-pip-version-check --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext" ./

Follow the guide in mmseg to prepare the ADE20k dataset.

Fine-tuning for Reproducing Results of MAE ViT-Base

Command:

tools/dist_train.sh configs/mae/upernet_mae_base_12_512_slide_160k_ade20k.py 8 --seed 0  --options model.pretrained=https://dl.fbaipublicfiles.com/mae/pretrain/mae_pretrain_vit_base.pth

Expected results log(paper results: 48.1 mIoU):

+--------+-------+-------+-------+
| Scope  | mIoU  | mAcc  | aAcc  |
+--------+-------+-------+-------+
| global | 48.15 | 58.99 | 83.05 |
+--------+-------+-------+-------+

Evaluation

Command format:

tools/dist_test.sh  <CONFIG_PATH> <CHECKPOINT_PATH> <NUM_GPUS> --eval mIoU

Acknowledgment

This code is built using the mmsegmentation library, Timm library, the Swin repository, XCiT, SETR, BEiT and the MAE repository.

Mae segmentation - Reproduction of semantic segmentation using masked autoencoder (mae)

Related tags

Overview

ADE20k Semantic segmentation with MAE

Getting started

Fine-tuning for Reproducing Results of MAE ViT-Base

Evaluation

Acknowledgment

Owner

Implementation of accepted AAAI 2021 paper: Deep Unsupervised Image Hashing by Maximizing Bit Entropy

[CVPR'20] TTSR: Learning Texture Transformer Network for Image Super-Resolution

Breaking the Dilemma of Medical Image-to-image Translation

g9.py - Torch interactive graphics

An integration of several popular automatic augmentation methods, including OHL (Online Hyper-Parameter Learning for Auto-Augmentation Strategy) and AWS (Improving Auto Augment via Augmentation Wise Weight Sharing) by Sensetime Research.

functorch is a prototype of JAX-like composable function transforms for PyTorch.

The source code of CVPR17 'Generative Face Completion'.

Official Repository for our ICCV2021 paper: Continual Learning on Noisy Data Streams via Self-Purified Replay

YOLOv5🚀 reproduction by Guo Quanhao using PaddlePaddle

An implementation of IMLE-Net: An Interpretable Multi-level Multi-channel Model for ECG Classification

Source code for Zalo AI 2021 submission

Elucidating Robust Learning with Uncertainty-Aware Corruption Pattern Estimation

The project is an official implementation of our CVPR2019 paper "Deep High-Resolution Representation Learning for Human Pose Estimation"

Code Release for Learning to Adapt to Evolving Domains

Price-Prediction-For-a-Dream-Home - A machine learning based linear regression trained model for house price prediction.

ICCV2021 Papers with Code

we propose EfficientDerain for high-efficiency single-image deraining

Python framework for Stochastic Differential Equations modeling

Training data extraction on GPT-2

RCD: Relation Map Driven Cognitive Diagnosis for Intelligent Education Systems