The train_net.py
script reproduces the object detection experiments on Pascal VOC and COCO.
-
Install detectron2.
-
Convert a pre-trained MoCo model to detectron2's format:
python3 convert-pretrain-to-detectron2.py input.pth.tar output.pkl
-
Put dataset under "./datasets" directory, following the directory structure requried by detectron2.
-
Run training:
python train_net.py --config-file configs/pascal_voc_R_50_C4_24k_moco.yaml \ --num-gpus 8 MODEL.WEIGHTS ./output.pkl
Please refer to our paper.