Can you also check instance segmentation?

FYI I confirmed no issues with OD on my 4 channel dataset

OK, whilst the error is resolved, the loss for OD models I train is always zero. Is there a validated results I can reproduce? Note this might just be my datasets which I recently updated for the new format

OK, whilst the error is resolved, the loss for OD models I train is always zero. Is there a validated results I can reproduce? Note this might just be my datasets which I recently updated for the new format

This by default was resizing all imagery to a min of 800. What transforms are you using to preprocess your imagery?

@adamjstewart fixed the instance segmentation task. It had the same issue.

@isaaccorley can you elaborate on This by default was resizing all imagery to a min of 800?
Example transforms:

        self.train_aug = Ka.AugmentationSequential(    
                Ka.Normalize(mean=self.mean, std=self.std),
                Ka.Resize(self.chip_size),
                Ka.RandomHorizontalFlip(p=0.5),
                Ka.RandomVerticalFlip(p=0.5),
                Ka.RandomRotation(degrees=(90.0, 90.0), p=0.25),
                data_keys=None,
                keepdim=True,
        )

        test_transforms: List[Ka.AugmentationBase2D] = [
            Ka.Normalize(mean=self.mean, std=self.std),
            Ka.Resize(self.chip_size),
        ]

where typically chip_size = 224

@isaaccorley can you elaborate on This by default was resizing all imagery to a min of 800?

Example transforms:

        self.train_aug = Ka.AugmentationSequential(    

                Ka.Normalize(mean=self.mean, std=self.std),

                Ka.Resize(self.chip_size),

                Ka.RandomHorizontalFlip(p=0.5),

                Ka.RandomVerticalFlip(p=0.5),

                Ka.RandomRotation(degrees=(90.0, 90.0), p=0.25),

                data_keys=None,

                keepdim=True,

        )



        test_transforms: List[Ka.AugmentationBase2D] = [

            Ka.Normalize(mean=self.mean, std=self.std),

            Ka.Resize(self.chip_size),

        ]

where typically chip_size = 224

Torchvision Faster-RCNN and MaskRCNN has a GeneralizedRCNNTransform transform module inside the model itself that will perform normalize + resizing to a minimum image size of 800. So any image you pass in <800 will be resized to 800. See the code here.

One trick that works well for object detection in remote sensing is to simply resize your small patches to be larger. This may be why you're getting poor performance.

@isaaccorley good to know! Perhaps we should document this?

@isaaccorley good to know! Perhaps we should document this?

This PR basically removes this transform, so a user can decide which normalize and resize Kornia transform they want to do themselves.

I've ruled out issues with my dataset and the remaining differences I see beween my legacy implementation and this implementation are details such as the anchor sizes I've utilised. I suggest we merge this approach and then as a follow up (and pending a suitable test dataset) work on further optimisations in another PR

Except for the tests...