-
Notifications
You must be signed in to change notification settings - Fork 308
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Datamodule for SpaceNet1 #965
Conversation
I'm guessing U-Nets require 1) square patches, and 2) patch sizes that are multiples of 32? |
They just need patch sizes that are multiples of 32. There are 5 downsampling operations by default (going down the left side of the "U") which reduces the spatial resolution of the input by a factor of 32. If the input isn't evenly divisible by 32, then there will be some rounding, and in the upsample part of the "U", the spatial dimensions of the features in the skip connections won't match. |
This is good to go pending the question in the above comment about larger test images vs. epsilon in the percentile normalization. |
* Add SpaceNet1 datamodule * Running black and isort * version added * Fix docs * SpaceNet1 tests * Testing spacenet datamodule with trainers * no loveda * black * doc fix * Removing direct datamodule test * Make sure percent normalization doesn't divide by zero * Speed up preprocessing Co-authored-by: Adam J. Stewart <ajstewart426@gmail.com>
Some things to note:
data.py
to generate 3 samples by default so that we can test train/val/test (@ashnair1)I can confirm that this is working with
train.py
, here's a shot from TensorBoard