PyVideoResearch:视频研究常用方法、数据集和任务汇总

栏目: Python · 发布时间: 5年前

内容简介:List of implemented methods:List of supported datasets:List of supported tasks:

PyVideoResearch

  • A repositsory of common methods, datasets, and tasks for video research

  • Please note that this repository is in the process of being released to the public. Please bear with us as we standardize the API and streamline the code.

  • Some of the baselines were run with an older version of the codebase (but the git commit hash is available for each experiment) and might need to be updated.

  • We encourage you to submit a Pull Request to help us document and incorporate as many baselines and datasets as possible to this codebase

  • We hope this project will be of value to the community and everyone will consider adding their methods to this codebase

List of implemented methods:

  • I3D
  • 3D ResNet
  • Asynchronous Temporal Fields
  • Actor Observer Network
  • Temporal Segment Networks
  • Temporal Relational Networks
  • Non-local neural networks
  • Two-Stream Networks
  • I3D Mask-RCNN
  • 3D ResNet Video Autoencoder

List of supported datasets:

  • Charades
  • CharadesEgo
  • Kinetics
  • AVA
  • ActivityNet
  • Something Something
  • Jester

List of supported tasks:

  • Action classification
  • Action localization
  • Spatial Action localization
  • Inpainting
  • Video Alignment
  • Triplet Classification

Contributor: Gunnar Atli Sigurdsson

  • If this code helps your research, please consider citing:
@inproceedings{sigurdsson2018pyvideoresearch,
author = {Gunnar A. Sigurdsson and Abhinav Gupta},
title = {PyVideoResearch},
year={2018},
code = {https://github.com/gsig/PyVideoResearch},
}

Installation Instructions

Requirements:

  • Python 2.7 or Python 3.6
  • PyTorch 0.4 or PyTorch 1.0

Python packages:

  • numpy
  • ffmpeg-python
  • PIL
  • cv2
  • torchvision

See external libraries under external/ for requirements if using their corresponding baselines.

Run the following to get both this repository and the remote repositories under external/

git clone git@github.com:gsig/PyVideoResearch.git
git submodule update --init --recursive

Steps to train your own network:

  1. Download the corresponding dataset
  2. Duplicate and edit one of the experiment files under exp/ with appropriate parameters. For additional parameters, see opts.py
  3. Run an experiment by calling python exp/rgbnet.py where rgbnet.py is your experiment file. See baseline_exp/ for a variety of baselines.
  4. The checkpoints/logfiles/outputs are stored in your specified cache directory.
  5. Build of the code, cite our papers, and say hi to us at CVPR.

Good luck!

Pretrained networks:

We are in the process of preparing and releasing the pre-trained models. If anything is missing, please let us know. The names correspond to experiments under "baseline_exp". While we standardize the names, please be aware that some of the model may have names listed after "original name" in the experiment file. We also provide the generated log.txt file for each experiment as name.txt

The models are stored here: https://www.dropbox.com/sh/duodxydolzz5qfl/AAC0i70lv8ssVRWg4ux5Vv9pa?dl=0

  • ResNet50 pre-trained on Charades

    • resnet50_rgb.pth.tar
    • resnet50_rgb_python3.pth.tar
  • ResNet1010 pre-trained on Charades

    • resnet101_rgb.pth.tar
    • resnet101_rgb_python3.pth.tar
  • I3D pre-trained on ImageNet (courtesy of https://github.com/piergiaj )

    • aj_rgb_imagenet.pth
  • I3D pre-trained on ImageNet+Kinetics (courtesy of https://github.com/piergiaj )

    • aj_rgb_kinetics.pth
  • actor_observer_3d_charades_ego.py

  • actor_observer_charades_ego.py

  • actor_observer_classification_charades_ego.py

  • async_tf_i3d_charades.py

    • async__par1.pth.tar
    • async__par1.txt
  • i3d_ava.py

  • i3d_mask_rcnn_ava.py

  • i3d_something_something.py

  • inpainting.py

  • nonlocal_resnet50_3d_charades.py

  • nonlocal_resnet50_3d_kinetics.py

    • i3d8l.pth.tar
    • i3d8l.txt
  • resnet50_3d_charades.py

    • i3d12b2.pth.tar
    • i3d12b2.txt
  • resnet50_3d_kinetics.py

    • i3d8k.pth.tar
    • i3d8k.txt
  • temporal_relational_networks_charades.py

  • temporal_relational_networks_something_something.py

    • trn4b.pth.tar
    • trn4b.txt
  • temporal_segment_networks_activity_net.py

  • temporal_segment_networks_charades.py

    • trn2f3b.pth.tar
    • trn2f3b.txt
  • two_stream_kinetics.py

  • two_stream_networks_activity_net.py

    • anet2.pth.tar
    • anet2.txt

以上就是本文的全部内容,希望本文的内容对大家的学习或者工作能带来一定的帮助,也希望大家多多支持 码农网

查看所有标签

猜你喜欢:

本站部分资源来源于网络,本站转载出于传递更多信息之目的,版权归原作者或者来源机构所有,如转载稿涉及版权问题,请联系我们

x86汇编语言

x86汇编语言

李忠、王晓波、余洁 / 电子工业出版社 / 2013-1 / 56.00元

《x86汇编语言:从实模式到保护模式》采用开源的NASM汇编语言编译器和VirtualBox虚拟机软件,以个人计算机广泛采用的Intel处理器为基础,详细讲解了Intel处理器的指令系统和工作模式,以大量的代码演示了16/32/64位软件的开发方法,介绍了处理器的16位实模式和32位保护模式,以及基本的指令系统。 《x86汇编语言:从实模式到保护模式》是一本有趣的书,它没有把篇幅花在计算一......一起来看看 《x86汇编语言》 这本书的介绍吧!

JSON 在线解析
JSON 在线解析

在线 JSON 格式化工具

URL 编码/解码
URL 编码/解码

URL 编码/解码

html转js在线工具
html转js在线工具

html转js在线工具