CameraTraps

A Collaborative Deep Learning Framework for Conservation

🐾 Introduction

At the core of our mission is the desire to create a harmonious space where conservation scientists from all over the globe can unite. Where they’re able to share, grow, use datasets and deep learning architectures for wildlife conservation. We’ve been inspired by the potential and capabilities of Megadetector, and we deeply value its contributions to the community. As we forge ahead with Pytorch-Wildlife, under which Megadetector now resides, please know that we remain committed to supporting, maintaining, and developing Megadetector, ensuring its continued relevance, expansion, and utility.

Pytorch-Wildlife is pip installable:

pip install PytorchWildlife

To use the newest version of MegaDetector with all the existing functionalities, you can use our Hugging Face interface or simply load the model with Pytorch-Wildlife. The weights will be automatically downloaded:

from PytorchWildlife.models import detection as pw_detection
detection_model = pw_detection.MegaDetectorV6()

For those interested in accessing the previous MegaDetector repository, which utilizes the same MegaDetectorV5 model weights and was primarily developed by Dan Morris during his time at Microsoft, please visit the archive directory, or you can visit this forked repository that Dan Morris is actively maintaining.

[!TIP] If you have any questions regarding MegaDetector and Pytorch-Wildlife, please email us or join us in our discord channel:

📣 Announcements

SpeciesNet is available in Pytorch-Wildlife for testing!

Please refer to this document for more details!

Pytorch-Wildlife Version 1.2.0

In this version of Pytorch-Wildlife, we are happy to release our detection fine-tuning module, with which users can fine-tune their own detection model from any released pre-trained MegaDetectorV6 models. Besides, this module also has functionalities that help users to prepare their datasets for the fine-tuning, just as our classification fine-tuning modules. For more details, please check the readme. Currently the fine-tuning is based on Ultralytics with AGPL. We will release MIT versions in the future. Here is the release page.
We have also released additional MegaDetectorV6 models based on Yolo-v10 and RtDetr. We have skipped Yolo-v11 models because of limited performance and architectural gains. Most of the MIT and Apache versions have also finished training but are waiting for internal review before they can be released.
We have also updated our AI4G-Amazon model with bigger datasets and it has a better performance compared to previous iterations. Please feel free to test it or fine-tune on it.
We will also make a new roadmap for 2025 in the next couple of updates.
Special thanks to José Díaz for his great cross-platform app, BoquilaHUB, that is even working on ios and android! Please check his repo out! In the future, we will create a project gallery showcasing projects that use or are build upon Pytorch-Wildlife. If you want your projects to be included, please feel free to reach out to us on

animal_det_1

:racing_car::dash::dash: MegaDetectorV6: SMALLER, FASTER, BETTER!

We have officially released our 6th version of MegaDetector, MegaDetectorV6! In the next generation of MegaDetector, we are focusing on computational efficiency, performance, modernizing of model architectures, and licensing. We have trained multiple new models using different model architectures, including Yolo-v9, Yolo-v10, and RT-Detr for maximum user flexibility. We have a rolling release schedule for different versions of MegaDetectorV6.

[!NOTE]

Following our initial release, we’ve been delighted to see so many people explore our new models. We’d like to extend our heartfelt thanks to everyone who has shown interest in our latest models—your support means a great deal to us!

That said, we’ve received a number of feedback comments highlighting a discrepancy between the reported performance (particularly MDV5) and the actual performance observed. We are actively investigating this issue and have identified a potential error or corruption in the validation data we used. For the time being, we’ll remove our current performance numbers from the model zoo for now to avoid confusion.

We sincerely apologize for any confusion or inconvenience this may have caused. Our team is working diligently to address this matter, and we will update our experiments—and potentially retrain the model if data corruption is confirmed—as soon as possible. Thank you for your patience and understanding!

MegaDetectorV6 models are based on architectures optimized for performance and low-budget devices. For example, the MegaDetectorV6-Ultralytics-YoloV10-Compact (MDV6-yolov10-c) model only have 2% of the parameters of the previous MegaDetectorV5 and still exhibits comparable animal recall on our validation datasets.

:bangbang: Model licensing

The Pytorch-Wildlife package is under MIT, however some of the models in the model zoo are not. For example, MegaDetectorV5, which is trained using the Ultralytics package, a package under AGPL-3.0, and is not for closed-source commercial uses if they are using updated ‘ultralytics’ packages.

There may be a confusion because YOLOv5 was initially released before the establishment of the AGPL-3.0 license. According to the official Ultralytics-Yolov5 package, it is under AGPL-3.0 now, and the maintainers have discussed how their licensing policy has evolved over time in their issues section.

We want to make Pytorch-Wildlife a platform where different models with different licenses can be hosted and want to enable different use cases. To reduce user confusions, in our model zoo section, we list all existing and planed future models in our model zoo, their corresponding license, and release schedules.

In addition, since the Pytorch-Wildlife package is under MIT, all the utility functions, including data pre-/post-processing functions and model fine-tuning functions in this packages are under MIT as well.

:mag: Model Zoo and Release Schedules

MegaDetectors

[!TIP] We are specifically reporting Animal Recall as our primary performance metric, even though it is not commonly used in traditional object detection studies, which typically focus on balancing overall model performance. For MegaDetector, our goal is to optimize for animal recall—in other words, minimizing false negative detections of animals or, more simply, ensuring our model misses as few animals as possible. While this may result in a higher false positive rate, we rely on downstream classification models to further filter the detected objects. We believe this approach is more practical for real-world animal monitoring scenarios.

Other detection models

Classification models

|Models|Version Names|Licence|Release| |—|—|—|—| |AI4G-Oppossum|-|MIT|Released| |AI4G-Amazon-V1|v1|MIT|Released| |AI4G-Amazon-V2|v2|MIT|Released| |AI4G-Serengeti|-|MIT|Released|

[!TIP] Some models, such as MegaDetectorV6, HerdNet, and AI4G-Amazon, have different versions, and they are loaded by their corresponding version names. Here is an example: detection_model = pw_detection.MegaDetectorV6(version="MDV6-yolov10-e").

👋 Welcome to Pytorch-Wildlife

PyTorch-Wildlife is a platform to create, modify, and share powerful AI conservation models. These models can be used for a variety of applications, including camera trap images, overhead images, underwater images, or bioacoustics. Your engagement with our work is greatly appreciated, and we eagerly await any feedback you may have.

The Pytorch-Wildlife library allows users to directly load the MegaDetector model weights for animal detection. We’ve fully refactored our codebase, prioritizing ease of use in model deployment and expansion. In addition to MegaDetector, Pytorch-Wildlife also accommodates a range of classification weights, such as those derived from the Amazon Rainforest dataset and the Opossum classification dataset. Explore the codebase and functionalities of Pytorch-Wildlife through our interactive HuggingFace web app or local demos and notebooks, designed to showcase the practical applications of our enhancements at PyTorchWildlife. You can find more information in our documentation.

👇 Here is a brief example on how to perform detection and classification on a single image using PyTorch-wildlife

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)

⚙️ Install Pytorch-Wildlife

pip install PytorchWildlife

Please refer to our installation guide for more installation information.

🕵️ Explore Pytorch-Wildlife and MegaDetector with our Demo User Interface

If you want to directly try Pytorch-Wildlife with the AI models available, including MegaDetector, you can use our Gradio interface. This interface allows users to directly load the MegaDetector model weights for animal detection. In addition, Pytorch-Wildlife also has two classification models in our initial version. One is trained from an Amazon Rainforest camera trap dataset and the other from a Galapagos opossum classification dataset (more details of these datasets will be published soon). To start, please follow the installation instructions on how to run the Gradio interface! We also provide multiple Jupyter notebooks for demonstration.

🛠️ Core Features

What are the core components of Pytorch-Wildlife? Pytorch-core-diagram

🌐 Unified Framework:

Pytorch-Wildlife integrates four pivotal elements:

▪ Machine Learning Models
▪ Pre-trained Weights
▪ Datasets
▪ Utilities

👷 Our work:

In the provided graph, boxes outlined in red represent elements that will be added and remained fixed, while those in blue will be part of our development.

🚀 Inaugural Model:

We’re kickstarting with YOLO as our first available model, complemented by pre-trained weights from MegaDetector. We have MegaDetectorV5, which is the same MegaDetectorV5 model from the previous repository, and many different versions of MegaDetectorV6 for different usecases.

📚 Expandable Repository:

As we move forward, our platform will welcome new models and pre-trained weights for camera traps and bioacoustic analysis. We’re excited to host contributions from global researchers through a dedicated submission platform.

📊 Datasets from LILA:

Pytorch-Wildlife will also incorporate the vast datasets hosted on LILA, making it a treasure trove for conservation research.

🧰 Versatile Utilities:

Our set of utilities spans from visualization tools to task-specific utilities, many inherited from Megadetector.

💻 User Interface Flexibility:

While we provide a foundational user interface, our platform is designed to inspire. We encourage researchers to craft and share their unique interfaces, and we’ll list both existing and new UIs from other collaborators for the community’s benefit.

Let’s shape the future of wildlife research, together! 🙌

🖼️ Examples

Image detection using `MegaDetector`

animal_det_1
Credits to Universidad de los Andes, Colombia.

Image classification with `MegaDetector` and `AI4GAmazonRainforest`

animal_clas_1
Credits to Universidad de los Andes, Colombia.

Opossum ID with `MegaDetector` and `AI4GOpossum`

opossum_det
Credits to the Agency for Regulation and Control of Biosecurity and Quarantine for Galápagos (ABG), Ecuador.

🤜🤛 Collaboration with AddaxAI (formerly EcoAssist)!

We are thrilled to announce our collaboration with AddaxAI—a powerful user interface software that enables users to directly load models from the PyTorch-Wildlife model zoo for image analysis on local computers. With AddaxAI, you can now utilize MegaDetectorV5 and the classification models—AI4GAmazonRainforest and AI4GOpossum—for automatic animal detection and identification, alongside a comprehensive suite of pre- and post-processing tools. This partnership aims to enhance the overall user experience with PyTorch-Wildlife models for a general audience. We will work closely to bring more features together for more efficient and effective wildlife analysis in the future.

:fountain_pen: Cite us!

We have recently published a summary paper on Pytorch-Wildlife. The paper has been accepted as an oral presentation at the CV4Animals workshop at this CVPR 2024. Please feel free to cite us!

@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},
}

Also, don’t forget to cite our original paper for MegaDetector:

@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},
}

🤝 Contributing

This project is open to your ideas and contributions. If you want to submit a pull request, we’ll have some guidelines available soon.

We have adopted the Microsoft Open Source Code of Conduct. For more information see the Code of Conduct FAQ or contact us with any additional questions or comments.

License

This repository is licensed with the MIT license.

👥 Existing Collaborators

The extensive collaborative efforts of Megadetector have genuinely inspired us, and we deeply value its significant contributions to the community. As we continue to advance with Pytorch-Wildlife, our commitment to delivering technical support to our existing partners on MegaDetector remains the same.

Here we list a few of the organizations that have used MegaDetector. We’re only listing organizations who have given us permission to refer to them here or have posted publicly about their use of MegaDetector.

👉 Full list of organizations

(Newly Added) [TerrOïko](https://www.terroiko.fr/) ([OCAPI platform](https://www.terroiko.fr/ocapi)) [Arizona Department of Environmental Quality](http://azdeq.gov/) [Blackbird Environmental](https://blackbirdenv.com/) [Camelot](https://camelotproject.org/) [Canadian Parks and Wilderness Society (CPAWS) Northern Alberta Chapter](https://cpawsnab.org/) [Conservation X Labs](https://conservationxlabs.com/) [Czech University of Life Sciences Prague](https://www.czu.cz/en) [EcoLogic Consultants Ltd.](https://www.consult-ecologic.com/) [Estación Biológica de Doñana](http://www.ebd.csic.es/inicio) [Idaho Department of Fish and Game](https://idfg.idaho.gov/) [Island Conservation](https://www.islandconservation.org/) [Myall Lakes Dingo Project](https://carnivorecoexistence.info/myall-lakes-dingo-project/) [Point No Point Treaty Council](https://pnptc.org/) [Ramat Hanadiv Nature Park](https://www.ramat-hanadiv.org.il/en/) [SPEA (Portuguese Society for the Study of Birds)](https://spea.pt/en/) [Synthetaic](https://www.synthetaic.com/) [Taronga Conservation Society](https://taronga.org.au/) [The Nature Conservancy in Wyoming](https://www.nature.org/en-us/about-us/where-we-work/united-states/wyoming/) [TrapTagger](https://wildeyeconservation.org/trap-tagger-about/) [Upper Yellowstone Watershed Group](https://www.upperyellowstone.org/) [Applied Conservation Macro Ecology Lab](http://www.acmelab.ca/), University of Victoria [Banff National Park Resource Conservation](https://www.pc.gc.ca/en/pn-np/ab/banff/nature/conservation), Parks Canada(https://www.pc.gc.ca/en/pn-np/ab/banff/nature/conservation) [Blumstein Lab](https://blumsteinlab.eeb.ucla.edu/), UCLA [Borderlands Research Institute](https://bri.sulross.edu/), Sul Ross State University [Capitol Reef National Park](https://www.nps.gov/care/index.htm) / Utah Valley University [Center for Biodiversity and Conservation](https://www.amnh.org/research/center-for-biodiversity-conservation), American Museum of Natural History [Centre for Ecosystem Science](https://www.unsw.edu.au/research/), UNSW Sydney [Cross-Cultural Ecology Lab](https://crossculturalecology.net/), Macquarie University [DC Cat Count](https://hub.dccatcount.org/), led by the Humane Rescue Alliance [Department of Fish and Wildlife Sciences](https://www.uidaho.edu/cnr/departments/fish-and-wildlife-sciences), University of Idaho [Department of Wildlife Ecology and Conservation](https://wec.ifas.ufl.edu/), University of Florida [Ecology and Conservation of Amazonian Vertebrates Research Group](https://www.researchgate.net/lab/Fernanda-Michalski-Lab-4), Federal University of Amapá [Gola Forest Programma](https://www.rspb.org.uk/our-work/conservation/projects/scientific-support-for-the-gola-forest-programme/), Royal Society for the Protection of Birds (RSPB) [Graeme Shannon's Research Group](https://wildliferesearch.co.uk/group-1), Bangor University [Hamaarag](https://hamaarag.org.il/), The Steinhardt Museum of Natural History, Tel Aviv University [Institut des Science de la Forêt Tempérée (ISFORT)](https://isfort.uqo.ca/), Université du Québec en Outaouais [Lab of Dr. Bilal Habib](https://bhlab.in/about), the Wildlife Institute of India [Mammal Spatial Ecology and Conservation Lab](https://labs.wsu.edu/dthornton/), Washington State University [McLoughlin Lab in Population Ecology](http://mcloughlinlab.ca/lab/), University of Saskatchewan [National Wildlife Refuge System, Southwest Region](https://www.fws.gov/about/region/southwest), U.S. Fish & Wildlife Service [Northern Great Plains Program](https://nationalzoo.si.edu/news/restoring-americas-prairie), Smithsonian [Quantitative Ecology Lab](https://depts.washington.edu/sefsqel/), University of Washington [Santa Monica Mountains Recreation Area](https://www.nps.gov/samo/index.htm), National Park Service [Seattle Urban Carnivore Project](https://www.zoo.org/seattlecarnivores), Woodland Park Zoo [Serra dos Órgãos National Park](https://www.icmbio.gov.br/parnaserradosorgaos/), ICMBio [Snapshot USA](https://emammal.si.edu/snapshot-usa), Smithsonian [Wildlife Coexistence Lab](https://wildlife.forestry.ubc.ca/), University of British Columbia [Wildlife Research](https://www.dfw.state.or.us/wildlife/research/index.asp), Oregon Department of Fish and Wildlife [Wildlife Division](https://www.michigan.gov/dnr/about/contact/wildlife), Michigan Department of Natural Resources Department of Ecology, TU Berlin Ghost Cat Analytics Protected Areas Unit, Canadian Wildlife Service [School of Natural Sciences](https://www.utas.edu.au/natural-sciences), University of Tasmania [(story)](https://www.utas.edu.au/about/news-and-stories/articles/2022/1204-innovative-camera-network-keeps-close-eye-on-tassie-wildlife) [Kenai National Wildlife Refuge](https://www.fws.gov/refuge/kenai), U.S. Fish & Wildlife Service [(story)](https://www.peninsulaclarion.com/sports/refuge-notebook-new-technology-increases-efficiency-of-refuge-cameras/) [Australian Wildlife Conservancy](https://www.australianwildlife.org/) [(blog](https://www.australianwildlife.org/cutting-edge-technology-delivering-efficiency-gains-in-conservation/), [blog)](https://www.australianwildlife.org/efficiency-gains-at-the-cutting-edge-of-technology/) [Felidae Conservation Fund](https://felidaefund.org/) [(WildePod platform)](https://wildepod.org/) [(blog post)](https://abhaykashyap.com/blog/ai-powered-camera-trap-image-annotation-system/) [Alberta Biodiversity Monitoring Institute (ABMI)](https://www.abmi.ca/home.html) [(WildTrax platform)](https://www.wildtrax.ca/) [(blog post)](https://wildcams.ca/blog/the-abmi-visits-the-zoo/) [Shan Shui Conservation Center](http://en.shanshui.org/) [(blog post)](https://mp.weixin.qq.com/s/iOIQF3ckj0-rEG4yJgerYw?fbclid=IwAR0alwiWbe3udIcFvqqwm7y5qgr9hZpjr871FZIa-ErGUukZ7yJ3ZhgCevs) [(translated blog post)](https://mp-weixin-qq-com.translate.goog/s/iOIQF3ckj0-rEG4yJgerYw?fbclid=IwAR0alwiWbe3udIcFvqqwm7y5qgr9hZpjr871FZIa-ErGUukZ7yJ3ZhgCevs&_x_tr_sl=auto&_x_tr_tl=en&_x_tr_hl=en&_x_tr_pto=wapp) [Irvine Ranch Conservancy](http://www.irconservancy.org/) [(story)](https://www.ocregister.com/2022/03/30/ai-software-is-helping-researchers-focus-on-learning-about-ocs-wild-animals/) [Wildlife Protection Solutions](https://wildlifeprotectionsolutions.org/) [(story](https://customers.microsoft.com/en-us/story/1384184517929343083-wildlife-protection-solutions-nonprofit-ai-for-earth), [story)](https://www.enterpriseai.news/2023/02/20/ai-helps-wildlife-protection-solutions-safeguard-endangered-species/) [Road Ecology Center](https://roadecology.ucdavis.edu/), University of California, Davis [(Wildlife Observer Network platform)](https://wildlifeobserver.net/) [The Nature Conservancy in California](https://www.nature.org/en-us/about-us/where-we-work/united-states/california/) [(Animl platform)](https://github.com/tnc-ca-geo/animl-frontend) [San Diego Zoo Wildlife Alliance](https://science.sandiegozoo.org/) [(Animl R package)](https://github.com/conservationtechlab/animl)

[!IMPORTANT] If you would like to be added to this list or have any questions regarding MegaDetector and Pytorch-Wildlife, please email us or join us in our Discord channel:

This site is open source. Improve this page.