Overview

Biodiversity banner showing animals monitored by AI — camera traps, bioacoustics, and aerial detection — powered by PyTorch-Wildlife and MegaDetector

Open-source AI for camera traps, bioacoustics, and wildlife monitoring

👋 Welcome to PyTorch-Wildlife¶

PyTorch-Wildlife is an AI platform designed for the AI for Conservation community to create, modify, and share powerful AI conservation models. It allows users to directly load a variety of models including MegaDetector, DeepFaune, and HerdNet from our ever expanding model zoo for both animal detection and classification.

Our scope now spans well beyond camera-trap imagery — we have active work in MegaDetector-Acoustic for bioacoustic species identification, MegaDetector-Overhead for aerial wildlife detection, and edge computing for remote field deployments.

Coming from an older version? OWL is now MegaDetector-Overhead, the bioacoustics module is now MegaDetector-Acoustic, and the repo has moved from microsoft/CameraTraps to microsoft/Biodiversity (old links redirect automatically). See the full naming changes in the v1.3.0 release notes.

🚀 Quick Start¶

👇 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.

🖼️ Examples¶

Image detection using `MegaDetector`¶

Camera trap photo with MegaDetector bounding box detecting an animal
Credits to Universidad de los Andes, Colombia.

Image classification with `MegaDetector` and `AI4GAmazonRainforest`¶

MegaDetector detection with AI4GAmazonRainforest species classification overlay
Credits to Universidad de los Andes, Colombia.

Opossum ID with `MegaDetector` and `AI4GOpossum`¶

Opossum identified using MegaDetector and AI4GOpossum classification model
Credits to the Agency for Regulation and Control of Biosecurity and Quarantine for Galápagos (ABG), Ecuador.