Skip to content

Mxnet implementation of EfficientDet object detection

Notifications You must be signed in to change notification settings

VinceJnz/efficientdet-mxnet

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

38 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

EfficientDet-MXNet

MXNet implementation of EfficientDet object detection as described in EfficientDet: Scalable and Efficient Object Detection by Mingxing Tan, Ruoming Pang and Quoc V. Le.

Prerequisites

  • Python 3.6+
  • MXNet 1.5.1+
  • gluoncv 0.6.0

Dataset

Pretrained Model

  • Will be provided

Training EfficientDet

  • COCO Dataset:
 sh train_efficientdet_coco.sh

Testing EfficientDet

  • COCO Dataset
python demo_efficientdet.py

Notes

Training script

I am using the training shell script as follows: Changed gpus from

  • --gpus 0,1,2,3 to
  • --gpus 0

python environment

To activate a python environment use the following bash command: source activate

where

  • activate is the activate comand in the Scripts subfolder for the python environment

See: https://docs.python.org/3/tutorial/venv.html

gluoncv

Was gluoncv==0.8.0 downgraded to gluoncv==0.6.0

python date/time

from datetime import datetime

# current date and time
now = datetime.now()

timestamp = datetime.timestamp(now)
print(timestamp + ": reduction.py dump "+"file="+file+", protocol="+protocol)

About

Mxnet implementation of EfficientDet object detection

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 62.1%
  • Jupyter Notebook 36.6%
  • Shell 1.3%