training on novel dataset
PolarBean opened this issue · comments
Harry Carey commented
Hey, great paper! any advice on how to train IAST on a new dataset?
Wenqi Tang commented
Sorry for the late reply, thank you for your attention to our paper.
For training IAST on a new dataset, please follow the following steps:
- Generate a JSON file where each item should contain
image_name
andmask_name
, which indicate the relative path of image and label. For more details, please see the JSON files inIAST/data
. - Implement a dataset class that inherits the
BaseDataset
, just like theMsCityscapesDataset
, and overwrite thetransform_mask(self, label)
for specific label transformation andaug(self, image, label)
for the augmentation. Last but not least, please register your dataset with a customized name by using@DATASET.register("your_dataset_name")
.
IAST/code/sseg/datasets/loader/cityscapes_dataset.py
Lines 17 to 25 in 24db991
I hope this can help you, I close this issue, if you have any other questions, please comment and I will reopen it.