Open AxMM opened 2 years ago
I figure it out, is because of this line: https://github.com/NVIDIA/semantic-segmentation/blob/7726b144c2cc0b8e09c67eabb78f027efdf3f0fa/datasets/uniform.py#L304
I don't understand why you are doing the step 1. Why?
I propose to write that line of code here, because it means class_uniform_pct = 0.0
https://github.com/NVIDIA/semantic-segmentation/blob/7726b144c2cc0b8e09c67eabb78f027efdf3f0fa/datasets/uniform.py#L317-L318
Maybe I am wrong, but what you think about that?
Thank you.
Hello, Thank you for your work.
I am trying to figure out if there is a problem with RandomSizeAndCrop and centroids, because in
__getitem__
of thebase_loader
some images centroid isNone
. I can't figure out why because all image have at least 1 centroid.My dataset have 1024x1024 images with 3 classes (0-background, 1 - class_1, 2- class_2). I just have 300 images. class_1 and class_2 are very small (all the masks have at least 1 of the classes and majority of the image is background), so I have a class imbalance problem. I am
build_centroids
with 512x512 tile, I check the json file and looks fine (all the images have at least 1 centroid for 1 of the classes). I just didcentroids.pop(0)
(insidebuild_centroids
, whencfg.GLOBAL_RANK=0
) I don't need background centroids, because I want data augmentation in class_1 and class_2.My
mydataset_cv0_tile512.json
looks fine, at least 1 centroid per image, belonging to class_1 or class_2. I diddump_augmentation_images
to take a look at the augmentation images. So I have some images without my class_1 or class_2, that is not good because i am adding an image without any class just background class. When I check themydataset_cv0_tile512.json
that image have centroid but__getitem__
of thebase_loader
is saying centroid isNone
. Can you help me on this? Thanks.mydataset_cv0_tile512.json
short example:This is my script: