Skip to content

black-mold/carcrash-sed-mivia

Repository files navigation

Advancing Sound Event Detection: Knowledge Distillation Applied to CRNN Models

  • This repository is an official implemtation of Advancing Sound Event Detection: Knowledge Distillation Applied to CRNN Models
  • 참고: 구글드라이브링크

Introduction

Dataset

참고 Dataset(여기선 사용 X)

Model

Loss

  • binary cross entropy

Evaluation

Getting Started

1. train

# supervised learning
CUDA_VISIBLE_DEVICES=0 python main.py --config ./configs/mivia_server.yaml --mode train
  • (참고)
# Knowledge distillation
CUDA_VISIBLE_DEVICES=0 python main_kd.py --config ./configs/mivia_kd.yaml --mode train

2. test

  • Test 하기 전에 yaml 파일의 resum_checkpoint 위치에 모델 학습 결과를 입력할 것
    • 예시:
    • image
CUDA_VISIBLE_DEVICES=0 python main.py --config ./configs/mivia_server.yaml --mode test

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published