HCF-Net is a framework for Infrared Small Object Segmentation
If you want to train on custom datasets you should paper dataset as following structure:
|-SIRST
|-trainval
|-images
|-xxx.png
|-masks
|-xxx.png
|-test
|-images
|-xxx.png
|-masks
|-xxx.png
To train the model, run this command:
python train.py --opt ./options/train.yaml
To evaluate pretrained model, run:
python test.py --opt ./options/test.yaml
You can download pretrained models (we also provide the whole training logs) here:
Model name | IoU | nIoU |
---|---|---|
UCF Net | 80.09 | 78.31 |