RuntimeError: expected scalar type Long but found Int

[skylning]

RuntimeError: expected scalar type Long but found Int

[AdeelH]

This should have been fixed (#1954) in the 0.21.3 release. Can you make sure you're using the latest version of Raster Vision?

[skylning]

yes ,i run the pip list and check the Raster Vision, it is 0.21.3

[AdeelH]

That's strange. Please share your code.

[skylning]

I run the train.ipynb,and change the train_image_uri 、train_label_uri、val_image_uri、val_label_uri as my local data path and get the error,and my torch is 2.1.0+cu121

[AdeelH]

I am not able to reproduce the error using version 0.21.3 and running the code in train.ipynb. Are you able to run the notebook successfully without changing the URIs?

[chrisjkuch]

I ran into this issue as well and found that, in my dataset, adding an albumentations transform like transform=A.resize(chip_sz, chip_sz) solves the problem. Perhaps albumentations performs the necessary conversion to the right data type?

[skylning]

I am not able to reproduce the error using version 0.21.3 and running the code in train.ipynb. Are you able to run the notebook successfully without changing the URIs?

Same issue without change the URLs.

[skylning]

I ran into this issue as well and found that, in my dataset, adding an albumentations transform like transform=A.resize(chip_sz, chip_sz) solves the problem. Perhaps albumentations performs the necessary conversion to the right data type?

How to add transfom,can you share you code snipe?thanks

[chrisjkuch]

See this discussion for an example

[skylning]

I change the OS to ubuntu 22.04,and no issue happen,it works well.