https://github.com/lromul/argus-birdsong
https://github.com/lromul/argus-birdsong
Last synced: 4 days ago
JSON representation
- Host: GitHub
- URL: https://github.com/lromul/argus-birdsong
- Owner: lRomul
- License: mit
- Created: 2020-07-25T21:44:29.000Z (about 5 years ago)
- Default Branch: master
- Last Pushed: 2020-09-29T17:12:55.000Z (about 5 years ago)
- Last Synced: 2025-10-12T23:53:12.877Z (4 days ago)
- Language: Python
- Size: 99.6 KB
- Stars: 1
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Cornell Birdcall Identification
Source code of solution for [Cornell Birdcall Identification](https://www.kaggle.com/c/birdsong-recognition) competition.
## Solution
Key points:
* Log-scaled mel-spectrograms
* CNN models
* Low public/private score :)
## Quick setup and start
### Requirements
* Nvidia drivers, CUDA >= 10.2, cuDNN >= 7
* [Docker](https://www.docker.com/), [nvidia-docker](https://github.com/NVIDIA/nvidia-docker)
The provided Dockerfile is supplied to build an image with CUDA support and cuDNN.
### Preparations
* Clone the repo, build docker image.
```bash
git clone https://github.com/lRomul/argus-birdsong.git
cd argus-birdsong
make build
```
* Download and extract [dataset](https://www.kaggle.com/c/birdsong-recognition/data) to `data` folder.
### Run
* Run docker container
```bash
make
```
* Create folds split
```bash
python make_folds.py
```
* Train model
```bash
python train.py --experiment train_001
```