/FS3C

Primary LanguagePython

Few-Shot Object Detection with Self-Supervising and Cooperative Classifier (Fs3c)

Table of Contents

Installation

Fs3c is built on FsDet.

Requirements

  • Linux with Python >= 3.6
  • PyTorch >= 1.3
  • torchvision that matches the PyTorch installation
  • Dependencies: pip install -r requirements.txt
  • pycocotools: pip install cython; pip install 'git+https://github.com/cocodataset/cocoapi.git#subdirectory=PythonAPI'
  • fvcore: pip install 'git+https://github.com/facebookresearch/fvcore'
  • OpenCV, optional, needed by demo and visualization pip install opencv-python
  • GCC >= 4.9

Build Fs3c

python setup.py build develop

Note: you may need to rebuild Fs3c after reinstalling a different build of PyTorch.

Data Preparation

See datasets/README.md for more details.

Getting Started

###Training & Evaluation For more detailed instructions on the training procedure, see TRAIN_INST.md. To evaluate the trained models, run

python tools/test_net.py --num-gpus 8 \
        --config-file configs/PascalVOC-detection/split1/faster_rcnn_R_101_FPN_ft_all1_1shot.yaml \
        --eval-only

Multiple Runs

You can use tools/run_experiments.py to do the training and evaluation. For example, to experiment on 30 seeds of the first split of PascalVOC on all shots, run

python tools/run_experiments.py --num-gpus 8 \
        --shots 1 2 3 5 10 --seeds 0 30 --split 1

After training and evaluation, you can use tools/aggregate_seeds.py to aggregate the results over all the seeds to obtain one set of numbers. To aggregate the 3-shot results of the above command, run

python tools/aggregate_seeds.py --shots 3 --seeds 30 --split 1 \
        --print --plot