Mmdet benchmark with python

Related tags

Deep Learningmmdet_benchmark
Overview

mmdet_benchmark

本项目是为了研究 mmdet 推断性能瓶颈，并且对其进行优化。

配置与环境

机器配置

CPU：Intel(R) Core(TM) i9-10900K CPU @ 3.70GHz
GPU：NVIDIA GeForce RTX 3080 10GB
内存：64G
硬盘：1TB NVME SSD

mmdet 环境

Python: 3.9.7 (default, Sep 16 2021, 13:09:58) [GCC 7.5.0]
CUDA available: True
GPU 0: NVIDIA GeForce RTX 3080
CUDA_HOME: /usr/local/cuda
NVCC: Build cuda_10.2_r440.TC440_70.29663091_0
GCC: gcc (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0
PyTorch: 1.9.1+cu111
PyTorch compiling details: PyTorch built with:
  - GCC 7.3
  - C++ Version: 201402
  - Intel(R) Math Kernel Library Version 2020.0.0 Product Build 20191122 for Intel(R) 64 architecture applications
  - Intel(R) MKL-DNN v2.1.2 (Git Hash 98be7e8afa711dc9b66c8ff3504129cb82013cdb)
  - OpenMP 201511 (a.k.a. OpenMP 4.5)
  - NNPACK is enabled
  - CPU capability usage: AVX2
  - CUDA Runtime 11.1
  - NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86
  - CuDNN 8.0.5
  - Magma 2.5.2
  - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.1, CUDNN_VERSION=8.0.5, CXX_COMPILER=/opt/rh/devtoolset-7/root/usr/bin/c++, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-variable -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.9.1, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON,

TorchVision: 0.10.1+cu111
OpenCV: 4.5.4
MMCV: 1.3.17
MMCV Compiler: GCC 7.3
MMCV CUDA Compiler: 11.1
MMDetection: 2.19.0+

时间分析

Mask R-CNN 的推断过程包含以下几个步骤，我们在一些可能是瓶颈的位置增加了时间统计：

注意：mask post-processing 的时间包含在 roi_head 里，所以减少 mask post-processing 的时间就是在减少 roi_head 的时间。

使用标准尺寸测试（1333x800）

测试图片：

stage pre-processing backbone rpn_head mask forward mask post-processing roi_head total
inference 13.45 24.87 10.16 3.84 15.74 23.49 72.3
inference_fp16 13.53 15.98 8.34 3.36 15.74 22.97 61.4
inference_fp16_preprocess 1.75 15.91 8.21 3.33 15.61 22.69 49.03
inference_raw_mask 1.65 15.93 8.34 3.36 1.74 8.89 33.45

使用较大尺寸测试（3840x2304）

stage pre-processing backbone rpn_head mask forward mask post-processing roi_head total
inference 128.44 187.24 69.96 6.01 173.72 183.95 569.92
inference_fp16 127.28 120.10 50.30 6.80 172.42 186.81 485.04
inference_fp16_preprocess 11.02 120.20 50.18 6.82 174.62 187.07 379.00
inference_raw_mask 11.03 120.26 50.46 6.81 2.99 15.34 197.69

可视化

mmdet 原版：

加速版：

目测没有显著差异。

总结

  • 使用 wrap_fp16_model 可以节省 backbone 的时间，但是不是所有情况下的 forward 都能节省时间；
  • 使用 torchvision.transforms.functional 去做图像预处理，可以极大提升推断速度；
  • 使用 FCNMaskHeadWithRawMask，避免对 mask 进行 resize，对越大的图像加速比越高，因为 resize 到原图大小的成本很高；
  • 后续优化，需要考虑 backbone 和 rpn_head 的优化，可以使用 TensorRT 进行加速。

原理分析

fp16

把一些支持 fp16 的层使用 fp16 来推断，可以充分利用显卡的 TensorCore，加速 forward 部分的速度。

参考链接：https://zhuanlan.zhihu.com/p/375224982

在 backbone 上，时间从 24.87 降到 15.93，在大图上从 187.24 降到 120.26，提升 35% 左右。

torchvision.transforms.functional

使用 pytorch 的 resize、pad、normalize，可以利用上 GPU 而不是 CPU。我们在推断过程中，CPU 利用率始终是最高的，而 GPU 利用率几乎没有满过，所以只要能够把 CPU 的事情交给 GPU 做，就能解决瓶颈问题，减少推断时间。

由于整个过程都可以使用 GPU，所以时间从 13.45 降低到 1.65，在大图上从 128.44 降低到 11.03，提升 10 倍左右。

FCNMaskHeadWithRawMask

首先我们看看 mmdet 处理的结果格式：

可以看到，有多少个 bbox，就有多少个 segm，每个 segm 都是原图尺寸。不管是 CPU，还是内存，都需要大量的时间去处理。

然后再看看 FCNMaskHeadWithRawMask 处理的格式：

每个结果都是 28x28 的，这也是模型原始输出，所以信息量和上面是一样的。

唯一的区别是，我们在拿到结果之后，如果要可视化，需要 resize 到 bbox 的大小，参考 detect/utils_visualize.py#L36-L40

使用 FCNMaskHeadWithRawMask 可以从 15.74 降到 1.74，大图可以从 173.72 降到 2.99，也就是说，图越大，这个加速比越大。

You might also like...
OpenMMLab Semantic Segmentation Toolbox and Benchmark.
OpenMMLab Semantic Segmentation Toolbox and Benchmark.

Documentation: https://mmsegmentation.readthedocs.io/ English | 简体中文 Introduction MMSegmentation is an open source semantic segmentation toolbox based

OpenMMLab 5k Dec 31, 2022
OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark
OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

Introduction English | 简体中文 MMAction2 is an open-source toolbox for video understanding based on PyTorch. It is a part of the OpenMMLab project. The m

OpenMMLab 2.7k Jan 7, 2023
OpenMMLab Pose Estimation Toolbox and Benchmark.
OpenMMLab Pose Estimation Toolbox and Benchmark.

Introduction English | 简体中文 MMPose is an open-source toolbox for pose estimation based on PyTorch. It is a part of the OpenMMLab project. The master b

OpenMMLab 2.8k Dec 31, 2022
[CVPR 2021 Oral] ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysis
[CVPR 2021 Oral] ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysis

ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysis ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysis [arxiv|pdf|v

Yinan He 78 Dec 22, 2022
A Research-oriented Federated Learning Library and Benchmark Platform for Graph Neural Networks. Accepted to ICLR'2021 - DPML and MLSys'21 - GNNSys workshops.

FedGraphNN: A Federated Learning System and Benchmark for Graph Neural Networks A Research-oriented Federated Learning Library and Benchmark Platform

FedML-AI 175 Dec 1, 2022
RoboDesk A Multi-Task Reinforcement Learning Benchmark
RoboDesk A Multi-Task Reinforcement Learning Benchmark

RoboDesk A Multi-Task Reinforcement Learning Benchmark If you find this open source release useful, please reference in your paper: @misc{kannan2021ro

Google Research 66 Oct 7, 2022
[CVPR2021] UAV-Human: A Large Benchmark for Human Behavior Understanding with Unmanned Aerial Vehicles

UAV-Human Official repository for CVPR2021: UAV-Human: A Large Benchmark for Human Behavior Understanding with Unmanned Aerial Vehicle Paper arXiv Res

null 129 Jan 4, 2023
3D AffordanceNet is a 3D point cloud benchmark consisting of 23k shapes from 23 semantic object categories, annotated with 56k affordance annotations and covering 18 visual affordance categories.
3D AffordanceNet is a 3D point cloud benchmark consisting of 23k shapes from 23 semantic object categories, annotated with 56k affordance annotations and covering 18 visual affordance categories.

3D AffordanceNet This repository is the official experiment implementation of 3D AffordanceNet benchmark. 3D AffordanceNet is a 3D point cloud benchma

null 49 Dec 1, 2022
NAS Benchmark in
NAS Benchmark in "Prioritized Architecture Sampling with Monto-Carlo Tree Search", CVPR2021

NAS-Bench-Macro This repository includes the benchmark and code for NAS-Bench-Macro in paper "Prioritized Architecture Sampling with Monto-Carlo Tree

null 35 Jan 3, 2023
Releases(v0.2.1)
Owner
杨培文 (Yang Peiwen)
杨培文 (Yang Peiwen)
GitHub Repository
Neural network for stock price prediction

neural_network_for_stock_price_prediction Neural networks for stock price predic

2 Feb 04, 2022
Explanatory Learning: Beyond Empiricism in Neural Networks

Explanatory Learning This is the official repository for "Explanatory Learning: Beyond Empiricism in Neural Networks". Datasets Download the datasets

GLADIA Research Group 10 Dec 06, 2022
Source codes of CenterTrack++ in 2021 ICME Workshop on Big Surveillance Data Processing and Analysis

MOT Tracked object bounding box association (CenterTrack++) New association method based on CenterTrack. Two new branches (Tracked Size and IOU) are a

36 Oct 04, 2022
An essential implementation of BYOL in PyTorch + PyTorch Lightning

Essential BYOL A simple and complete implementation of Bootstrap your own latent: A new approach to self-supervised Learning in PyTorch + PyTorch Ligh

Enrico Fini 48 Sep 27, 2022
A modified version of DeepMind's Alphafold2 to divide CPU part (MSA and template searching) and GPU part (prediction model)

ParallelFold Author: Bozitao Zhong This is a modified version of DeepMind's Alphafold2 to divide CPU part (MSA and template searching) and GPU part (p

Bozitao Zhong 77 Dec 22, 2022
Cooperative Driving Dataset: a dataset for multi-agent driving scenarios

Cooperative Driving Dataset (CODD) The Cooperative Driving dataset is a synthetic dataset generated using CARLA that contains lidar data from multiple

Eduardo Henrique Arnold 124 Dec 28, 2022
This repository will be a summary and outlook on all our open, medical, AI advancements.

medical by LAION This repository will be a summary and outlook on all our open, medical, AI advancements. See the medical-general channel in the medic

LAION AI 18 Dec 30, 2022
Code and data for ACL2021 paper Cross-Lingual Abstractive Summarization with Limited Parallel Resources.

Multi-Task Framework for Cross-Lingual Abstractive Summarization (MCLAS) The code for ACL2021 paper Cross-Lingual Abstractive Summarization with Limit

Yu Bai 43 Nov 07, 2022
MicRank is a Learning to Rank neural channel selection framework where a DNN is trained to rank microphone channels.

MicRank: Learning to Rank Microphones for Distant Speech Recognition Application Scenario Many applications nowadays envision the presence of multiple

Samuele Cornell 20 Nov 10, 2022
A Python module for the generation and training of an entry-level feedforward neural network.

ff-neural-network A Python module for the generation and training of an entry-level feedforward neural network. This repository serves as a repurposin

Riadh 2 Jan 31, 2022
WSDM2022 "A Simple but Effective Bidirectional Extraction Framework for Relational Triple Extraction"

BiRTE WSDM2022 "A Simple but Effective Bidirectional Extraction Framework for Relational Triple Extraction" Requirements The main requirements are: py

9 Dec 27, 2022
This is the official implementation of "One Question Answering Model for Many Languages with Cross-lingual Dense Passage Retrieval".

CORA This is the official implementation of the following paper: Akari Asai, Xinyan Yu, Jungo Kasai and Hannaneh Hajishirzi. One Question Answering Mo

Akari Asai 59 Dec 28, 2022
A modular, research-friendly framework for high-performance and inference of sequence models at many scales

T5X T5X is a modular, composable, research-friendly framework for high-performance, configurable, self-service training, evaluation, and inference of

Google Research 1.1k Jan 08, 2023
An implementation of an abstract algebra for music tones (pitches).

nbdev template Use this template to more easily create your nbdev project. If you are using an older version of this template, and want to upgrade to

Open Music Kit 0 Oct 10, 2022
Fedlearn支持前沿算法研发的Python工具库 | Fedlearn algorithm toolkit for researchers

FedLearn-algo Installation Development Environment Checklist python3 (3.6 or 3.7) is required. To configure and check the development environment is c

89 Nov 14, 2022
SciFive: a text-text transformer model for biomedical literature

SciFive SciFive provided a Text-Text framework for biomedical language and natural language in NLP. Under the T5's framework and desrbibed in the pape

Long Phan 54 Dec 24, 2022
Rotary Transformer

[中文|English] Rotary Transformer Rotary Transformer is an MLM pre-trained language model with rotary position embedding (RoPE). The RoPE is a relative

325 Jan 03, 2023
Make differentially private training of transformers easy for everyone

private-transformers This codebase facilitates fast experimentation of differentially private training of Hugging Face transformers. What is this? Why

Xuechen Li 73 Dec 28, 2022
Simple tutorials on Pytorch DDP training

pytorch-distributed-training Distribute Dataparallel (DDP) Training on Pytorch Features Easy to study DDP training You can directly copy this code for

Ren Tianhe 188 Jan 06, 2023
Code for WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models.

WECHSEL Code for WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models. arXiv: https://arx

Institute of Computational Perception 45 Dec 29, 2022