Official PyTorch implementation of HCCNet: Efficient Semantic Matching with Hypercolumn Correlation (WACV '24 Oral, Best paper finalist (top 0.6%))
| Project Page | Paper(Arxiv)|
conda create -n mbm python=3.10
conda activate mbm
# xformer 0.0.25 is compatible with pytorch 2.2.1
pip3 install torch==2.2.1 torchvision --index-url https://download.pytorch.org/whl/cu118
# lightning
pip3 install lightning
pip install torchmetrics
# logging
pip3 install wandb
#formatting
pip install black
pip install einops
pip install -U albumentations
pip install pandas
conda install scipy
Change the dataset you want to train with from configs/config.yaml
, from pfpascal
or spair
. Then run the following:
python train.py
The training / validation will be logged on WandB by default, under the project name "HCCNet".
-
Release training code - Release training script per dataset
- Release test code per dataset
- Release pre-trained weights