MegaDetector

Deep learning tools that accelerate the review of motion-triggered wildlife camera images.
https://github.com/microsoft/CameraTraps

Category: Biosphere
Sub Category: Terrestrial Wildlife

Keywords

camera-traps computer-vision conservation machine-learning megadetector pytorch pytorch-wildlife wildlife

Keywords from Contributors

ecology cameratraps aiforearth measurement transformers observability web-map distributed sustainable conversation

Last synced: about 2 hours ago
JSON representation

Repository metadata

PyTorch Wildlife: a Collaborative Deep Learning Framework for Conservation.

• Host: GitHub
• URL: https://github.com/microsoft/CameraTraps
• Owner: microsoft
• License: mit
• Created: 2018-10-11T18:02:42.000Z (over 6 years ago)
• Default Branch: main
• Last Pushed: 2025-05-16T20:20:04.000Z (1 day ago)
• Last Synced: 2025-05-16T21:27:52.653Z (1 day ago)
• Topics: camera-traps, computer-vision, conservation, machine-learning, megadetector, pytorch, pytorch-wildlife, wildlife
• Language: Python
• Homepage: https://microsoft.github.io/CameraTraps/
• Size: 486 MB
• Stars: 885
• Watchers: 51
• Forks: 263
• Open Issues: 15
• Releases: 9
• Metadata Files:
  • Readme: README.md
  • License: LICENSE.md
  • Security: SECURITY.md

README.md

import numpy as np
from PytorchWildlife.models import detection as pw_detection
from PytorchWildlife.models import classification as pw_classification

img = np.random.randn(3, 1280, 1280)

# Detection
detection_model = pw_detection.MegaDetectorV6() # Model weights are automatically downloaded.
detection_result = detection_model.single_image_detection(img)

#Classification
classification_model = pw_classification.AI4GAmazonRainforest() # Model weights are automatically downloaded.
classification_results = classification_model.single_image_classification(img)

pip install PytorchWildlife

@misc{hernandez2024pytorchwildlife,
      title={Pytorch-Wildlife: A Collaborative Deep Learning Framework for Conservation}, 
      author={Andres Hernandez and Zhongqi Miao and Luisa Vargas and Sara Beery and Rahul Dodhia and Juan Lavista},
      year={2024},
      eprint={2405.12930},
      archivePrefix={arXiv},
}

@misc{beery2019efficient,
      title={Efficient Pipeline for Camera Trap Image Review},
      author={Sara Beery and Dan Morris and Siyu Yang},
      year={2019}
      eprint={1907.06772},
      archivePrefix={arXiv},
}

Citation (https://github.com/microsoft/CameraTraps/blob/main/)

cff-version: 1.2.0
title: Efficient Pipeline for Camera Trap Image Review
message: >-
  If you use this software, please cite it using the
  metadata from this file.
type: software
authors:
  - given-names: Sara
    family-names: Beery
  - given-names: Dan
    family-names: Morris
    email: [email protected]
  - given-names: Siyu
    family-names: Yang
identifiers:
  - type: url
    value: 'https://arxiv.org/abs/1907.06772'
    description: 'arXiv preprint, 1907.06772, 2019'
repository-code: 'http://github.com/ecologize/CameraTraps'
keywords:
  - Camera traps
  - Conservation
  - Computer vision
license: MIT

Owner metadata

• Name: Microsoft
• Login: microsoft
• Email: [email protected]
• Kind: organization
• Description: Open source projects and samples from Microsoft
• Website: https://opensource.microsoft.com
• Location: Redmond, WA
• Twitter: OpenAtMicrosoft
• Company:
• Icon url: https://avatars.githubusercontent.com/u/6154722?v=4
• Repositories: 7031
• Last ynced at: 2025-05-15T00:05:38.321Z
• Profile URL: https://github.com/microsoft

GitHub Events

Total

• Create event: 15
• Release event: 3
• Issues event: 40
• Watch event: 112
• Delete event: 14
• Member event: 3
• Issue comment event: 49
• Push event: 128
• Pull request review comment event: 4
• Pull request review event: 16
• Pull request event: 62
• Fork event: 28

Last Year

• Create event: 15
• Release event: 3
• Issues event: 40
• Watch event: 112
• Delete event: 14
• Member event: 3
• Issue comment event: 49
• Push event: 128
• Pull request review comment event: 4
• Pull request review event: 16
• Pull request event: 62
• Fork event: 28

Committers metadata

Last synced: 9 days ago

Committer domains:

• microsoft.com: 1

Issue and Pull Request metadata

Last synced: 1 day ago

Package metadata

• Total packages: 1
• Total downloads:
  • pypi: 1,297 last-month
• Total dependent packages: 0
• Total dependent repositories: 0
• Total versions: 29
• Total maintainers: 2

Dependencies

Score: 13.97174477999491