mmdetection version of TinyBenchmark.

Overview

introduction

This project is an mmdetection version of TinyBenchmark.

TODO list:

  • add TinyPerson dataset and evaluation
  • add crop and merge for image during inference
  • implement RetinaNet and Faster-FPN baseline on TinyPerson
  • add SM/MSM experiment support
  • add visDronePerson dataset support and baseline performance
  • add point localization task for TinyPerson
  • add point localization task for visDronePerson
  • add point localization task for COCO

install and setup

download project

git clone https://github.com/ucas-vg/TOV_mmdetection --recursive

install mmdetection

conda create -n open-mmlab python=3.7 -y
conda activate open-mmlab
conda install -c pytorch pytorch=1.5.0 cudatoolkit=10.2 torchvision -y  # (recommand)
# install latest pytorch prebuilt with the default prebuilt CUDA version (usually the latest)
# conda install -c pytorch pytorch torchvision -y

# install the latest mmcv
pip install mmcv-full --user
# install mmdetection
cd TOV_mmdetection
pip uninstall pycocotools
pip install -r requirements/build.txt
pip install -v -e . --user  # or "python setup.py develop"

For more detail, please refer mmdetection install to install mmdetecion.

Quickly Start

to train baseline of TinyPerson, download the mini_annotation of all annotation is enough, which can be downloaded as tiny_set/mini_annotations.tar.gz in Baidu Yun(password:pmcq) / Google Driver.

mkdir data
ln -s $Path of TinyPerson$ data/tiny_set
tar -zxvf data/tiny_set/mini_annotations.tar.gz && mv mini_annotations data/tiny_set/

# run experiment, for other config run, see exp/Baseline_TinyPerson.sh
export GPU=4 && LR=02 && CUDA_VISIBLE_DEVICES=0,1,2,3 PORT=10000 tools/dist_train.sh configs2/TinyPerson/base/faster_rcnn_r50_fpn_1x_TinyPerson640.py $GPU \
  --work-dir ../TOV_mmdetection_cache/work_dir/TinyPerson/Base/faster_rcnn_r50_fpn_1x_TinyPerson640/old640x512_lr0${LR}_1x_${GPU}g/ \
  --cfg-options optimizer.lr=0.${LR}

performance

All train and test on 2080Ti,

  • CUDA10.1/10.2
  • python3.7, cudatookit=10.2, pytorch=1.5, torchvision=0.6

for Faster-FPN, we think the gain compare to TinyBenchmark may come from the cut and merge during inference running time and multi-gpu training.

performance 43.80(2) where 2 means the performance is mean result of running such setting for 2 time.

detector num_gpu $AP_{50}^{tiny}$ script
Faster-FPN 4 48.63(1) exp/Baseline_TinyPerson.sh:exp1.1
Adap RetainaNet 1 43.80(2) exp/Baseline_TinyPerson.sh:exp2.1
Adap RetainaNet 4 44.94(1) exp/Baseline_TinyPerson.sh:exp2.2(clip grad)
RAMA: Rapid algorithm for multicut problem

RAMA: Rapid algorithm for multicut problem Solves multicut (correlation clustering) problems orders of magnitude faster than CPU based solvers without

Paul Swoboda 60 Dec 13, 2022
Autoregressive Predictive Coding: An unsupervised autoregressive model for speech representation learning

Autoregressive Predictive Coding This repository contains the official implementation (in PyTorch) of Autoregressive Predictive Coding (APC) proposed

iamyuanchung 173 Dec 18, 2022
Seg-Torch for Image Segmentation with Torch

Seg-Torch for Image Segmentation with Torch This work was sparked by my personal research on simple segmentation methods based on deep learning. It is

Eren Gölge 37 Dec 12, 2022
3D HourGlass Networks for Human Pose Estimation Through Videos

3D-HourGlass-Network 3D CNN Based Hourglass Network for Human Pose Estimation (3D Human Pose) from videos. This was my summer'18 research project. Dis

Naman Jain 51 Jan 02, 2023
Official repository for the paper "GN-Transformer: Fusing AST and Source Code information in Graph Networks".

GN-Transformer AST This is the official repository for the paper "GN-Transformer: Fusing AST and Source Code information in Graph Networks". Data Prep

Cheng Jun-Yan 10 Nov 26, 2022
Efficient Deep Learning Systems course

Efficient Deep Learning Systems This repository contains materials for the Efficient Deep Learning Systems course taught at the Faculty of Computer Sc

Max Ryabinin 173 Dec 29, 2022
A flexible and extensible framework for gait recognition.

A flexible and extensible framework for gait recognition. You can focus on designing your own models and comparing with state-of-the-arts easily with the help of OpenGait.

Shiqi Yu 335 Dec 22, 2022
PyTorch implementation of "A Simple Baseline for Low-Budget Active Learning".

A Simple Baseline for Low-Budget Active Learning This repository is the implementation of A Simple Baseline for Low-Budget Active Learning. In this pa

10 Nov 14, 2022
Using contrastive learning and OpenAI's CLIP to find good embeddings for images with lossy transformations

The official code for the paper "Inverse Problems Leveraging Pre-trained Contrastive Representations" (to appear in NeurIPS 2021).

Sriram Ravula 26 Dec 10, 2022
Code and experiments for "Deep Neural Networks for Rank Consistent Ordinal Regression based on Conditional Probabilities"

corn-ordinal-neuralnet This repository contains the orginal model code and experiment logs for the paper "Deep Neural Networks for Rank Consistent Ord

Raschka Research Group 14 Dec 27, 2022
Semantic Edge Detection with Diverse Deep Supervision

Semantic Edge Detection with Diverse Deep Supervision This repository contains the code for our IJCV paper: "Semantic Edge Detection with Diverse Deep

Yun Liu 12 Dec 31, 2022
Spatial Intention Maps for Multi-Agent Mobile Manipulation (ICRA 2021)

spatial-intention-maps This code release accompanies the following paper: Spatial Intention Maps for Multi-Agent Mobile Manipulation Jimmy Wu, Xingyua

Jimmy Wu 70 Jan 02, 2023
Equivariant layers for RC-complement symmetry in DNA sequence data

Equi-RC Equivariant layers for RC-complement symmetry in DNA sequence data This is a repository that implements the layers as described in "Reverse-Co

7 May 19, 2022
Official implementation of NeurIPS'2021 paper TransformerFusion

TransformerFusion: Monocular RGB Scene Reconstruction using Transformers Project Page | Paper | Video TransformerFusion: Monocular RGB Scene Reconstru

Aljaz Bozic 118 Dec 25, 2022
E-RAFT: Dense Optical Flow from Event Cameras

E-RAFT: Dense Optical Flow from Event Cameras This is the code for the paper E-RAFT: Dense Optical Flow from Event Cameras by Mathias Gehrig, Mario Mi

Robotics and Perception Group 71 Dec 12, 2022
Inteligência artificial criada para realizar interação social com idosos.

IA SONIA 4.0 A SONIA foi inspirada no assistente mais famoso do mundo e muito bem conhecido JARVIS. Todo mundo algum dia ja sonhou em ter o seu própri

Vinícius Azevedo 2 Oct 21, 2021
Learning to Simulate Dynamic Environments with GameGAN (CVPR 2020)

Learning to Simulate Dynamic Environments with GameGAN PyTorch code for GameGAN Learning to Simulate Dynamic Environments with GameGAN Seung Wook Kim,

199 Dec 26, 2022
novel deep learning research works with PaddlePaddle

Research 发布基于飞桨的前沿研究工作,包括CV、NLP、KG、STDM等领域的顶会论文和比赛冠军模型。 目录 计算机视觉(Computer Vision) 自然语言处理(Natrual Language Processing) 知识图谱(Knowledge Graph) 时空数据挖掘(Spa

1.5k Dec 29, 2022
AdaNet is a lightweight TensorFlow-based framework for automatically learning high-quality models with minimal expert intervention

AdaNet is a lightweight TensorFlow-based framework for automatically learning high-quality models with minimal expert intervention. AdaNet buil

3.4k Jan 07, 2023
Rethinking Transformer-based Set Prediction for Object Detection

Rethinking Transformer-based Set Prediction for Object Detection Here are the code for the ICCV paper. The code is adapted from Detectron2 and AdelaiD

Zhiqing Sun 62 Dec 03, 2022