FR-UNet

Prerequisites

Download our repo:

Datasets processing

Choose a path to create a folder with the dataset name and download datasets DRIVE,CHASEDB1,STARE,CHUAC, and DCA1. Type this in terminal to run the data_process.py file

python data_process.py -dp DATASET_PATH -dn DATASET_NAME

Training

Type this in terminal to run the train.py file

python train.py -dp DATASET_PATH

Test

Type this in terminal to run the test.py file

python test.py -dp DATASET_PATH -wp WEIGHT_FILE_PATH (--sliding -ps 48 --stride 44)

We have prepared the pre-trained models for both datasets in the folder 'pretrained_weights'. To replicate the results in the paper, directly run the following commands

python test.py -dp DATASET_PATH -wp pretrained_weights/DATASET_NAME

Export

python onnx_export.py --export_path outputs/onnx/frunet_fp_test_quan.onnx

quan export

License