Assertion `input_val >= zero && input_val <= one` failed

I'm training a YOLOX model for object detection using a dataset that includes:

• Annotated images (positive samples)
• Unannotated images (negative samples, i.e., no bounding boxes)

When I include negative images in the training dataset (images with no annotations), I consistently encounter the following CUDA error:

Assertion input_val >= zero && input_val <= one failed

From this trace:

../aten/src/ATen/native/cuda/Loss.cu:94: operator(): block: [0,0,0], thread: [0,0,0]
Assertion input_val >= zero && input_val <= one failed.
...
terminate called after throwing an instance of 'c10::DistBackendError'
what(): Process group watchdog thread terminated with exception: CUDA error: device-side assert triggered

The unannotated images in the .json file are only in the images section; they do not appear in the annotations section.

Is happening in the epoch 3 or later.

How can I safely include negative samples (images without annotations) in YOLOX training without triggering the CUDA assert?

The report provides a YOLOX dataset layout and a CUDA Loss.cu assertion, but names no source file or test. Start by reproducing training with images present only in the JSON images section, then trace how empty annotations reach the training loss. Done means negative samples train without the CUDA assert and the behavior is covered by a reproducible test or documented dataset case.