Patrik Sabol
Patrik Sabol
Will it be possible to use for training data with 4 channels or multi-channel in the future?
### Issue How to download NAIP imagery for Chesapeak13? Labels for Chesapeake13 are downloaded automatically, but there is no information, how to download correspond NAIP imagery. In [tutorial](https://torchgeo.readthedocs.io/en/latest/tutorials/getting_started.html), there is...
### Description When training on Chesapeake13 with num_classes=14 and ignore_index=0, an assertion error ‘t >= 0 && t < n_classes’ occurs. This indicates that there are more class indices in...
### Is your feature request related to a problem? Please describe. This is resolved [issue](https://github.com/wandb/wandb/issues/1173) in WandB. Citing: "I'm using PyTorch Lightning with WandB. PyTorch Lightning's training loop catches SIGINT...
Hi, thanks for great framework! However there is huge fundamental bug in FrameField approach. First [here](https://github.com/dsgoficial/pytorch_segmentation_models_trainer/blob/7e4839273c4744b47ca47c4c8c6c44c736c6dfca/pytorch_segmentation_models_trainer/dataset_loader/dataset.py#L417) crossfield is treated as mask during loading, thus, in [here](https://github.com/dsgoficial/pytorch_segmentation_models_trainer/blob/7e4839273c4744b47ca47c4c8c6c44c736c6dfca/pytorch_segmentation_models_trainer/dataset_loader/dataset.py#L155) all anglefield are vanished...
There is bug in class_freq computation, more specifically, reading value of class_freq from generated csv dataset. In [here](https://github.com/dsgoficial/pytorch_segmentation_models_trainer/blob/7e4839273c4744b47ca47c4c8c6c44c736c6dfca/pytorch_segmentation_models_trainer/dataset_loader/dataset.py#L507), the value of class freq for segmentation mask is read from df.columns,...
I have deployed the Triton Inference Server to Google Cloud Platform and I am using a Horizontal Pod Autoscaler (HPA). During normal operation with one or three pods running, the...
Hello, Are there any best practices or guidelines for selecting feature maps from the intermediate layers (out of the 12 available)? Specifically, what do these feature maps represent, and in...
Hi, Can this approach also vectorize joined buildings—that is, two buildings that share a common edge? Has this scenario been tested? If so, are there any limitations or particular considerations...
It would be great to add another languages, such as sk and cz.