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
CMT: Convolutional Neural Networks Meet Vision Transformers

CMT: Convolutional Neural Networks Meet Vision Transformers [arxiv] 1. Introduction This repo is the CMT model which impelement with pytorch, no refer

FlyEgle 83 Dec 30, 2022
"Neural Turing Machine" in Tensorflow

Neural Turing Machine in Tensorflow Tensorflow implementation of Neural Turing Machine. This implementation uses an LSTM controller. NTM models with m

Taehoon Kim 1k Dec 06, 2022
Examples of using f2py to get high-speed Fortran integrated with Python easily

f2py Examples Simple examples of using f2py to get high-speed Fortran integrated with Python easily. These examples are also useful to troubleshoot pr

Michael 35 Aug 21, 2022
This program can detect your face and add an Christams hat on the top of your head

Auto_Christmas This program can detect your face and add a Christmas hat to the top of your head. just run the Auto_Christmas.py, then you can see the

3 Dec 22, 2021
DeepStruc is a Conditional Variational Autoencoder which can predict the mono-metallic nanoparticle from a Pair Distribution Function.

ChemRxiv | [Paper] XXX DeepStruc Welcome to DeepStruc, a Deep Generative Model (DGM) that learns the relation between PDF and atomic structure and the

Emil Thyge Skaaning Kjær 13 Aug 01, 2022
Python based framework for Automatic AI for Regression and Classification over numerical data.

Python based framework for Automatic AI for Regression and Classification over numerical data. Performs model search, hyper-parameter tuning, and high-quality Jupyter Notebook code generation.

BlobCity, Inc 141 Dec 21, 2022
Source code of the paper PatchGraph: In-hand tactile tracking with learned surface normals.

PatchGraph This repository contains the source code of the paper PatchGraph: In-hand tactile tracking with learned surface normals. Installation Creat

Paloma Sodhi 11 Dec 15, 2022
FedTorch is an open-source Python package for distributed and federated training of machine learning models using PyTorch distributed API

FedTorch is a generic repository for benchmarking different federated and distributed learning algorithms using PyTorch Distributed API.

Machine Learning and Optimization Lab @PennState 136 Dec 23, 2022
This is the official repository for our paper: ''Pruning Self-attentions into Convolutional Layers in Single Path''.

Pruning Self-attentions into Convolutional Layers in Single Path This is the official repository for our paper: Pruning Self-attentions into Convoluti

Zhuang AI Group 77 Dec 26, 2022
A simple editor for captions in .SRT file extension

WaySRT A simple editor for captions in .SRT file extension The program doesn't use any external dependecies, just run: python way_srt.py {file_name.sr

Gustavo Lopes 3 Nov 16, 2022
[NeurIPS-2021] Mosaicking to Distill: Knowledge Distillation from Out-of-Domain Data

MosaicKD Code for NeurIPS-21 paper "Mosaicking to Distill: Knowledge Distillation from Out-of-Domain Data" 1. Motivation Natural images share common l

ZJU-VIPA 37 Nov 10, 2022
PyTorch implementation of ''Background Activation Suppression for Weakly Supervised Object Localization''.

Background Activation Suppression for Weakly Supervised Object Localization PyTorch implementation of ''Background Activation Suppression for Weakly S

35 Jan 06, 2023
CVPR 2021: "Generating Diverse Structure for Image Inpainting With Hierarchical VQ-VAE"

Diverse Structure Inpainting ArXiv | Papar | Supplementary Material | BibTex This repository is for the CVPR 2021 paper, "Generating Diverse Structure

152 Nov 04, 2022
Source code of article "Towards Toxic and Narcotic Medication Detection with Rotated Object Detector"

Towards Toxic and Narcotic Medication Detection with Rotated Object Detector Introduction This is the source code of article: Towards Toxic and Narcot

Woody. Wang 3 Oct 29, 2022
The official implementation of "Rethink Dilated Convolution for Real-time Semantic Segmentation"

RegSeg The official implementation of "Rethink Dilated Convolution for Real-time Semantic Segmentation" Paper: arxiv D block Decoder Setup Install the

Roland 61 Dec 27, 2022
For auto aligning, cropping, and scaling HR and LR images for training image based neural networks

ImgAlign For auto aligning, cropping, and scaling HR and LR images for training image based neural networks Usage Make sure OpenCV is installed, 'pip

15 Dec 04, 2022
Code for "Multi-View Multi-Person 3D Pose Estimation with Plane Sweep Stereo"

Multi-View Multi-Person 3D Pose Estimation with Plane Sweep Stereo This repository includes the source code for our CVPR 2021 paper on multi-view mult

Jiahao Lin 66 Jan 04, 2023
Pytorch implementation of "ARM: Any-Time Super-Resolution Method"

ARM-Net Dependencies Python 3.6 Pytorch 1.7 Results Train Data preprocessing cd data_scripts python extract_subimages_test.py python data_augmentation

Bohong Chen 55 Nov 24, 2022
Implementation of a Transformer that Ponders, using the scheme from the PonderNet paper

Ponder(ing) Transformer Implementation of a Transformer that learns to adapt the number of computational steps it takes depending on the difficulty of

Phil Wang 65 Oct 04, 2022
MM1 and MMC Queue Simulation using python - Results and parameters in excel and csv files

implementation of MM1 and MMC Queue on randomly generated data and evaluate simulation results then compare with analytical results and draw a plot curve for them, simulate some integrals and compare

Mohamadreza Rezaei 1 Jan 19, 2022