https://github.com/bencevans/megadetector-contained
Docker image for running the MegaDetector v4 camera-trap object detection model.
https://github.com/bencevans/megadetector-contained
camera-traps cameratrap megadetector object-detection
Last synced: 2 months ago
JSON representation
Docker image for running the MegaDetector v4 camera-trap object detection model.
- Host: GitHub
- URL: https://github.com/bencevans/megadetector-contained
- Owner: bencevans
- Created: 2021-01-10T18:28:55.000Z (over 4 years ago)
- Default Branch: main
- Last Pushed: 2022-05-24T12:57:15.000Z (almost 3 years ago)
- Last Synced: 2025-01-12T04:29:15.334Z (4 months ago)
- Topics: camera-traps, cameratrap, megadetector, object-detection
- Language: Dockerfile
- Homepage:
- Size: 1.95 KB
- Stars: 3
- Watchers: 2
- Forks: 9
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# MegaDetector Contained
> Docker image for running the [MegaDetector](https://github.com/microsoft/CameraTraps/blob/master/megadetector.md) camera-trap object detection model.
## Requirements
- CUDA 11.0 (adjustable by changing base image)
- docker
- nvidia-docker (`sudo apt install nvidia-docker2` on Ubuntu 20.04.1)
## Building
```bash
docker build -t bencevans/megadetector .
```
## Batch Detection
```bash
nvidia-docker run --rm -it -v "$(pwd)":/dataset bencevans/megadetector \
python detection/run_tf_detector_batch.py \
--recursive --output_relative_filenames --checkpoint_frequency 10000 \
/workspace/blobs/4.1.0.pb /dataset/ /dataset/md.4.1.0.json
```