mmaction2 | OpenMMLab 's Next Generation Video Understanding Toolbox | Video Utils library

by open-mmlab Python Version: 1.2.0 License: Apache-2.0

X-Ray Key Features Code Snippets(3)Community Discussions(2)Vulnerabilities Install Support

kandi X-RAY | mmaction2 Summary

mmaction2 is a Python library typically used in Video, Video Utils, Pytorch applications. mmaction2 has no bugs, it has no vulnerabilities, it has build file available, it has a Permissive License and it has medium support. You can install using 'pip install mmaction2' or download it from GitHub, PyPI.

MMAction2 is an open-source toolbox for video understanding based on PyTorch. It is a part of the OpenMMLab project. The master branch works with PyTorch 1.3+.

Support

Quality

Security

License

Reuse

Support

mmaction2 has a medium active ecosystem.

It has 3175 star(s) with 1029 fork(s). There are 47 watchers for this library.

It had no major release in the last 12 months.

There are 136 open issues and 1047 have been closed. On average issues are closed in 16 days. There are 37 open pull requests and 0 closed requests.

It has a neutral sentiment in the developer community.

The latest version of mmaction2 is 1.2.0

Quality

mmaction2 has 0 bugs and 0 code smells.

Security

mmaction2 has no vulnerabilities reported, and its dependent libraries have no vulnerabilities reported.

mmaction2 code analysis shows 0 unresolved vulnerabilities.

There are 0 security hotspots that need review.

License

mmaction2 is licensed under the Apache-2.0 License. This license is Permissive.

Permissive licenses have the least restrictions, and you can use them in most projects.

Reuse

mmaction2 releases are available to install and integrate.

Deployable package is available in PyPI.

Build file is available. You can build the component from source.

Installation instructions, examples and code snippets are available.

mmaction2 saves you 19531 person hours of effort in developing the same functionality from scratch.

It has 53705 lines of code, 1546 functions and 557 files.

It has medium code complexity. Code complexity directly impacts maintainability of the code.

Top functions reviewed by kandi - BETA

kandi has reviewed mmaction2 and discovered the below as its top functions. This is intended to give you an instant insight into mmaction2 implemented functionality, and help decide if they suit your requirements.

Train a model
Build a daloader
Build an MLDistributedData object
Build a dataset from a CFG
Wrapper for inference_recognizer
Parse command line arguments
Adds a parser to subparsers
Adds the parser for the time parser
Wrapper for skeleton_stdetection
Build a model
Generates a list of trainframes
Runs a gendata
Parse the HMDB50 split of the HMDB51 split into a dict
Calculate RGB STDetector
Get output from a video
Parse phonetic splits
Visualize a video
Parse requirements from a requirements file
Build the RGB and Flow file list
Add a single detected image
Show action recognition results
Evaluate the ground truth test
Generate a list of POSIX processes
Convert a list of lines to a dict
Extracts a dense flow from a video
Forward computation

Get all kandi verified functions for this library.

mmaction2 Key Features

No Key Features are available at this moment for mmaction2.

mmaction2 Examples and Code Snippets

K-centered Patch Sampling for Efficient Video Recognition,Preparing datasets

Python

Lines of Code : 58

License : Permissive (Apache-2.0)

Copy

import ffmpeg
import numpy as np
import imageio as iio

(
    probe = ffmpeg.probe(video_file)
    stream_dict = probe['streams'][0]
    width, height = stream_dict['width'], stream_dict['height']
    
    out, _ = ffmpeg
    .input('filename.webm')

Installation Steps

Python

Lines of Code : 8

License : Permissive (Apache-2.0)

Copy

conda create -n mmaction python=3.7 -y
conda activate mmaction

conda install pytorch=1.7.1 cudatoolkit=11.0 torchvision=0.8.2 -c pytorch

pip install mmcv-full==1.2.1 -f https://download.openmmlab.com/mmcv/dist/cu110/torch1.7.1/index.html

git clone

致谢

Python

Lines of Code : 8

License : Permissive (Apache-2.0)

Copy

@misc{feichtenhofer2020x3d,
      title={X3D: Expanding Architectures for Efficient Video Recognition}, 
      author={Christoph Feichtenhofer},
      year={2020},
      eprint={2004.04730},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

Community Discussions

Trending Discussions on mmaction2

Docker shared memory size out of bounds or unhandled system error, NCCL version 2.7.8

TypeError: can't pickle coroutine objects when i am using asyncio loop.run_in_executor()

QUESTION

Docker shared memory size out of bounds or unhandled system error, NCCL version 2.7.8

Asked 2021-Apr-13 at 05:55

The following error(s) and solution go for deploying a stack through YAML in portainer but they can surely be applied to docker otherwise.

Environment:

...

ANSWER

Answered 2021-Apr-13 at 05:55

It seems that by default, the size of the shared memory is limited to 64mb. The solution to this error therefore, as shown in this issue is to increase the size of shared memory.

Hence, the first idea that comes to mind would be simply defining something like shm_size: 9gb in the YAML file of the stack. However, this might not work as shown for e.g in this issue.

Therefore, in the end, I had to use the following workaround (also described here, but poorly documented):

Source https://stackoverflow.com/questions/67056737

QUESTION

TypeError: can't pickle coroutine objects when i am using asyncio loop.run_in_executor()

Asked 2021-Jan-04 at 09:50

I am referring to this repo to adapt mmaction2 grad-cam demo from short video offline inference to long video online inference. The script is shown below:

Note: to make this script can be easily reproduce, i comment out some codes that needs many dependencies.

...

ANSWER

Answered 2021-Jan-04 at 09:50

If you use run_in_executor, target function should not be async. You need to remove async keyword before def inference().

Source https://stackoverflow.com/questions/65557258

Community Discussions, Code Snippets contain sources that include Stack Exchange Network

Vulnerabilities

No vulnerabilities reported

Install mmaction2

Please refer to install.md for installation.
Please see getting_started.md for the basic usage of MMAction2. There are also tutorials:. A Colab tutorial is also provided. You may preview the notebook here or directly run on Colab.
learn about configs
finetuning models
adding new dataset
designing data pipeline
adding new modules
exporting model to onnx
customizing runtime settings

Support

Results and models are available in the README.md of each method's config directory. A summary can be found on the model zoo page. We will keep up with the latest progress of the community and support more popular algorithms and frameworks. If you have any feature requests, please feel free to leave a comment in Issues.

Find more information at: