Fixed issue in torchvision_tutorial.rst (#2537)

Forgot to update image_id in rst but using correct type in complete code:
https://github.com/pytorch/tutorials/blob/6b31dd0da52178c21170217680370d4430bd1b54/_static/tv-training-code.py#L52

Author: vfdev-5

intermediate_source/torchvision_tutorial.rst

@@ -151,7 +151,7 @@ As datapoints are :class:`torch.Tensor` subclasses, wrapped objects are also ten
            # there is only one class
            labels = torch.ones((num_objs,), dtype=torch.int64)
 
-           image_id = torch.tensor([idx])
+           image_id = idx
            area = (boxes[:, 3] - boxes[:, 1]) * (boxes[:, 2] - boxes[:, 0])
            # suppose all instances are not crowd
            iscrowd = torch.zeros((num_objs,), dtype=torch.int64)