This branch (fsc) is for CAC task

This branch provides baseline code for few-shot object counting task.

VGG16Trans model is adopted for counting.

FSC147 dataset is released by LearningToCountEverything.

For more related works about class-agnostic counting(CAC), please refer this repository Awesome-Class-Agnostic-Counting

to run

fork or clone this repository
pip install -r requirements.txt
download dataset, then put images_384_VarV2 and gt_density_map_adaptive_384_VarV2 in ./datasets/FSC
sh run.sh

MAE/MSE	FSC-test	FSC-val
FamNet	22.08/99.54	23.75/69.07
VGG16Trans without examplar (baseline)	17.51/132.62	19.21/77.43

Name		Name	Last commit message	Last commit date
Latest commit History 16 Commits
datasets		datasets
imgs		imgs
losses		losses
models		models
preprocess		preprocess
utils		utils
.gitignore		.gitignore
README.md		README.md
requirements.txt		requirements.txt
run.sh		run.sh
train.py		train.py
visualizer.ipynb		visualizer.ipynb