[Bug fix ]Update pixel_samplers.py, tensor on different device, unpredictable behavior at assignment

[Goulustis]

"indices" and "batch["image_idx"]" can be on different devices. The assignment between them, though will allow the model to converge correctly, have unpredictable behaviors. Namely, indices[:, 0] - batch["image_idx"][c].cpu() != 0. Putting them on the same device to have correct behavior.

It is a mystery to me why nerfstudio can work correctly with this unpredictable behavior.