Q.Liu

> 改成这样，就没问题了 parser.add_argument_group(title="pl.Trainer args") parser = Trainer.add_argparse_args(parser)

Hahaa, I will if I could manage to it -)

Hi, 1) you can manually stop the training (ctr+c), I did so when I observe there is no better val-acc / m-F1 (e.g, 20-epochs), or you can simply change the...

Hi, thank you for your valuable comments. I also agree with your point on the val loss and overfitting issue, I did not pay much attention to it though I...

Hi, I am not allowed privately to share the data without official permission. But It will be very easy for you to officially apply for downloading the dataset from the...

you have to set ignore-index=255 for ce loss, because the GT file contains 255 as invalid region, refer to this implementation https://github.com/samleoqh/DDCM-Semantic-Segmentation-PyTorch/blob/master/models/loss_functions/ce_loss.py

The model for IJRS2020 can be easily bulit based on `/lib/net/scg_gcn.py` , like as below, and the training pipeline for Vaihingen dataset almost same as [DDCM-Net](https://github.com/samleoqh/DDCM-Semantic-Segmentation-PyTorch). ``` from lib.net.scg_gcn import...

it sounds like the the diagonal entries of A (adj matrix) are very small numbers in your case, then its `mean` value will be close to zero, thus the gama...

You can change `kf, k_folder, `in `train_args` for cross-validation training e.g., you can set `kf=0, k_folder=5`, means you use 5-folder for validation, the current training loop using folder` 0`, Note...

This split is specially designed for agriculture-vision dataset, that only split the offcial val-set by kfolders, not split the training set. If you want only split train set into train...