Clone the repo:
git clone https://github.com/fanq15/FSOD-code.git
Tested under python3.
- python packages
- pytorch==0.4.1
- torchvision>=0.2.0
- cython
- matplotlib
- numpy
- scipy
- opencv
- pyyaml
- packaging
- pycocotools — for COCO dataset, also available from pip.
- tensorboardX — for logging the losses in Tensorboard
- An NVIDAI GPU and CUDA 8.0 or higher. Some operations only have gpu implementation.
- NOTICE: different versions of Pytorch package have different memory usages.
Compile the CUDA code:
cd lib # please change to this directory
sh make.sh
If your are using Volta GPUs, uncomment this line in lib/mask.sh
and remember to postpend a backslash at the line above. CUDA_PATH
defaults to /usr/loca/cuda
. If you want to use a CUDA library on different path, change this line accordingly.
It will compile all the modules you need, including NMS, ROI_Pooing, ROI_Crop and ROI_Align. (Actually gpu nms is never used ...)
Note that, If you use CUDA_VISIBLE_DEVICES
to set gpus, make sure at least one gpu is visible when compile the code.
Please add data
in the fsod
directory and the structure is :
YOUR_PATH
└── fsod
├── code files
└── data
├──── fsod
| ├── annotations
│ │ ├── fsod_train.json
│ │ └── fsod_test.json
│ └── images
│ ├── part_1
│ └── part_2
│
└──── pretrained_model
└── model_final.pkl (from detectron model zoo: End-to-End Faster & Mask R-CNN Baselines R-50-C4 Faster 2x model)
You can download the model_final.pkl from here: Model link
CUDA_VISIBLE_DEVICES=0,1,2,3 python3 tools/train_net_step.py --save_dir $SAVE_DIR --dataset fsod --cfg configs/fsod/voc_e2e_faster_rcnn_R-50-C4_1x_old_1.yaml --bs 4 --iter_size 2 --nw 4 --load_detectron data/pretrained_model/model_final.pkl
CUDA_VISIBLE_DEVICES=0,1,2,3 python3 tools/test_net.py --multi-gpu-testing --dataset fsod --cfg configs/fsod/voc_e2e_faster_rcnn_R-50-C4_1x_old_1.yaml --load_ckpt Outputs/$SAVE_DIR/ckpt/model_step59999.pth
The default setting is on 4 GPUs. If you want to change GPU numbers, please change bs
in the training script and make sure bs=#GPU
. If you want to use the default training setting on 4 GPUs, you can directly run sh all.sh
to train and evaluate the model.
Please note that this repository is only for episode training and evaluation on FSOD dataset. Other expriments on different datasets are in different evaluation settings and I will gradually merge them. Currently, the code only supports 1 image on 1 GPU for both training and evaluation.
This repository is originally built on roytseng-tw/Detectron.pytorch. You can reference it for more implementation details.
If you use this dataset in your research, please cite this paper.
@inproceedings{fan2020fsod,
title={Few-Shot Object Detection with Attention-RPN and Multi-Relation Detector},
author={Fan, Qi and Zhuo, Wei and Tang, Chi-Keung and Tai, Yu-Wing},
booktitle={CVPR},
year={2020}
}