OrienMask: Real-time Instance Segmentation with Discriminative Orientation Maps

Last update: Dec 13, 2022

Related tags

Deep Learning OrienMask

Overview

OrienMask

This repository implements the framework OrienMask for real-time instance segmentation.

It achieves 34.8 mask AP on COCO test-dev at the speed of 42.7 FPS evaluated with a single RTX 2080Ti. (log)

Paper: Real-time Instance Segmentation with Discriminative Orientation Maps

Installation

Please see INSTALL.md to prepare the environment and dataset.

Usage

Place the pre-trained backbone (link) and trained model (link) as follows for convenience (otherwise update the corresponding path in configurations):

├── checkpoints
│   ├── pretrained
│   │   ├──pretrained_darknet53.pth
│   ├── OrienMaskAnchor4FPNPlus
│   │   ├──orienmask_yolo.pth

train

Three items should be noticed when deploying different number of GPUs: n_gpu, batch_size, accumulate. Keep in mind that the approximate batch size equals to n_gpu * batch_size * accumulate.

# multi-gpu train (n_gpu=2, batch_size=8, accumulate=1)
# if necessary, set MASTER_PORT to avoid port conflict
# if permission error, run `chmod +x dist_train.sh`
CUDA_VISIBLE_DEVICES=0,1 ./dist_train.sh \
    -c orienmask_yolo_coco_544_anchor4_fpn_plus

# single-gpu train (n_gpu=1, batch_size=8, accumulate=2)
CUDA_VISIBLE_DEVICES=0 ./dist_train.sh \
    -c orienmask_yolo_coco_544_anchor4_fpn_plus
# or
CUDA_VISIBLE_DEVICES=0 python train.py \
    -c orienmask_yolo_coco_544_anchor4_fpn_plus

test

Run the following command to obtain AP and AR metrics on val2017 split:

CUDA_VISIBLE_DEVICES=0 python test.py \
    -c orienmask_yolo_coco_544_anchor4_fpn_plus_test \
    -w checkpoints/OrienMaskAnchor4FPNPlus/orienmask_yolo.pth

infer

Please run python infer.py -h for more usages.

# infer on an image and save the visualized result
CUDA_VISIBLE_DEVICES=0 python infer.py \
    -c orienmask_yolo_coco_544_anchor4_fpn_plus_infer \
    -w checkpoints/OrienMaskAnchor4FPNPlus/orienmask_yolo.pth \
    -i assets/000000163126.jpg -v -o outputs

# infer on a list of images and save the visualized results
CUDA_VISIBLE_DEVICES=0 python infer.py \
    -c orienmask_yolo_coco_544_anchor4_fpn_plus_infer \
    -w checkpoints/OrienMaskAnchor4FPNPlus/orienmask_yolo.pth \
    -d coco/test2017 -l assets/test_dev_selected.txt -v -o outputs

logs

We provide two types of logs for monitoring the training process. The first is updated on the terminal which is also stored in a train.log file in the checkpoint directory. The other is the tensorboard whose statistics are kept in the checkpoint directory.

Citation

@article{du2021realtime,
  title={Real-time Instance Segmentation with Discriminative Orientation Maps}, 
  author={Du, Wentao and Xiang, Zhiyu and Chen, Shuya and Qiao, Chengyu and Chen, Yiman and Bai, Tingming},
  journal={arXiv preprint arXiv:2106.12204},
  year={2021}
}

OrienMask: Real-time Instance Segmentation with Discriminative Orientation Maps

Related tags

Overview

OrienMask

Installation

Usage

train

test

infer

logs

Citation

Owner

NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥

Server files for UltimateLabeling

Dynamics-aware Adversarial Attack of 3D Sparse Convolution Network

This is an example of a reproducible modelling project

General purpose Slater-Koster tight-binding code for electronic structure calculations

Orange Chicken: Data-driven Model Generalizability in Crosslinguistic Low-resource Morphological Segmentation

This repository is for our paper Exploiting Scene Graphs for Human-Object Interaction Detection accepted by ICCV 2021.

Marvis is Mastouri's Jarvis version of the AI-powered Python personal assistant.

CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images

[ICLR2021oral] Rethinking Architecture Selection in Differentiable NAS

implementation of the paper "MarginGAN: Adversarial Training in Semi-Supervised Learning"

This repository stores the code to reproduce the results published in "TiWS-iForest: Isolation Forest in Weakly Supervised and Tiny ML scenarios"

Official pytorch implementation of paper "Image-to-image Translation via Hierarchical Style Disentanglement".

Fusion-DHL: WiFi, IMU, and Floorplan Fusion for Dense History of Locations in Indoor Environments

Implementation of PyTorch-based multi-task pre-trained models

Part-Aware Data Augmentation for 3D Object Detection in Point Cloud

MAU: A Motion-Aware Unit for Video Prediction and Beyond, NeurIPS2021

Analysing poker data from home games with friends

This project is based on our SIGGRAPH 2021 paper, ROSEFusion: Random Optimization for Online DenSE Reconstruction under Fast Camera Motion .

Qimera: Data-free Quantization with Synthetic Boundary Supporting Samples