Skip to main content

Advanced pipelines for video datasets

Project description

Bumblebee

PyPI Downloads
Bumblebee image

Bumblebee provides high level components to construct training pipelines for videos conveniently.

Install

pip install eyecu_bumblebee

Motivation

Everything should be made as simple as possible, but no simpler. - Albert Einstein

Our Websites

EyeCU Vision
EyeCU Future

Examples

A pipeline with basic elements

from bumblebee import *


if __name__ == "__main__":
    
    video_path = "/path/to/video.mp4"

    # Create a source
    file_stream = sources.FileStream(video_path)

    # Add an effect
    goto = effects.GoTo(file_stream)

    END_OF_VIDEO = file_stream.get_duration()
    goto(END_OF_VIDEO)

    # Create a dataset
    single_frame = datasets.Single(file_stream)

    last_frame = single_frame.read()

Using Manager API

from bumblebee import *


if __name__ == "__main__":
    
    # Create a training manager
    manager = managers.BinaryClassification(
        ["path/to/video_dir","path/to/another_dir"],
        ["path/to/labels"]
    )

    number_of_epochs = 300
    
    for epoch,(frame_no,frame,prob) in manager(number_of_epochs):
        # Use data stuff
        ...    

Read limited section of video

from bumblebee import *


if __name__ == "__main__":
  
    video_path = "/path/to/video.mp4"
    start_frame = 35
    end_frame = 40
    
    file_stream = sources.FileStream(video_path)
    
    limited_stream = effects.Start(file_stream,start_frame)
    limited_stream = effects.End(limited_stream,end_frame)

    single_frame = datasets.Single(file_stream)

    for frame in single_frame:
        ...  

Iterate frames with frame numbers

from bumblebee import *


if __name__ == "__main__":
  
    video_path = "/path/to/video.mp4"
    
    file_stream = sources.FileStream(video_path)
    
    single_frame = datasets.Single(file_stream)
    current_frame = effects.CurrentFrame(file_stream)
    
    
    for frame_ind,frame in zip(current_frame,single_frame):
        ...  

Iterate frames in batches

from bumblebee import *


if __name__ == "__main__":
  
    video_path = "/path/to/video.mp4"
    batch_size = 64
    
    file_stream = sources.FileStream(video_path)
    
    batch = datasets.Batch(file_stream)
    
    for frames in batch:
        ...  

Team

This project is currently developed and maintained by ovuruska.

License

Bumblebee has MIT license. You can find further details in LICENSE.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Files for eyecu-bumblebee, version 0.5.6
Filename, size File type Python version Upload date Hashes
Filename, size eyecu_bumblebee-0.5.6-py3-none-any.whl (16.0 kB) File type Wheel Python version py3 Upload date Hashes View
Filename, size eyecu-bumblebee-0.5.6.tar.gz (11.8 kB) File type Source Python version None Upload date Hashes View

Supported by

Pingdom Pingdom Monitoring Google Google Object Storage and Download Analytics Sentry Sentry Error logging AWS AWS Cloud computing DataDog DataDog Monitoring Fastly Fastly CDN DigiCert DigiCert EV certificate StatusPage StatusPage Status page