predictor access of coordinates in `sliding_window_inference`

[wyli]

Is your feature request related to a problem? Please describe.

MONAI/monai/inferers/utils.py

Lines 219 to 223 in 5feb353

	if sw_batch_size > 1:
	win_data = torch.cat([inputs[win_slice] for win_slice in unravel_slice]).to(sw_device)
	else:
	win_data = inputs[unravel_slice[0]].to(sw_device)
	seg_prob_out = predictor(win_data, *args, **kwargs) # batched patch

predictor currently takes a batch of image windows as the primary input, it has no access to the relative position information of the windows with respect to the input whole volume. would be great to add an option to send unravel_slice to predictor.

cc @heyufan1995