Skip to content

Latest commit

 

History

History
27 lines (18 loc) · 812 Bytes

File metadata and controls

27 lines (18 loc) · 812 Bytes

Un-Mix with MoCo: Transferring to Detection

The train_net.py script reproduces the object detection experiments on Pascal VOC and COCO.

Instruction

  1. Install detectron2.

  2. Convert a pre-trained MoCo model to detectron2's format:

    python3 convert-pretrain-to-detectron2.py input.pth.tar output.pkl
    
  3. Put dataset under "./datasets" directory, following the directory structure requried by detectron2.

  4. Run training:

    python train_net.py --config-file configs/pascal_voc_R_50_C4_24k_moco.yaml \
     --num-gpus 8 MODEL.WEIGHTS ./output.pkl
    

Results

Please refer to our paper.