I am trying to build Datablock a kaggle dataset.
salt-identification
salt_block = DataBlock(blocks=(ImageBlock, MaskBlock),
get_items= images_list,
get_y = get_y_fn,
batch_tfms=[*aug_transforms(size=size), Normalize.from_stats(*imagenet_stats)])
Getting the following error:
RuntimeError: CUDA error: device-side assert triggered
CUDA kernel errors might be asynchronously reported at some other API call,so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1.
It runs fine is i do not use the Normalise operation
salt_block = DataBlock(blocks=(ImageBlock, MaskBlock),
get_items= images_list,
get_y = get_y_fn,
batch_tfms=[*aug_transforms(size=size)])
Is there a way to get this working with Normalise operation.