MXNet implementation of EfficientDet object detection as described in EfficientDet: Scalable and Efficient Object Detection by Mingxing Tan, Ruoming Pang and Quoc V. Le.
- Python 3.6+
- MXNet 1.5.1+
- gluoncv 0.6.0
- run mscoco.py to download coco2017 dataset.
- run pascal_voc.py to download voc dataset.
- Will be provided
- COCO Dataset:
sh train_efficientdet_coco.sh
- COCO Dataset
python demo_efficientdet.py
I am using the training shell script as follows: Changed gpus from
- --gpus 0,1,2,3 to
- --gpus 0
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
Was gluoncv==0.8.0 downgraded to gluoncv==0.6.0
from datetime import datetime
# current date and time
now = datetime.now()
timestamp = datetime.timestamp(now)
print(timestamp + ": reduction.py dump "+"file="+file+", protocol="+protocol)