Handle empty (size=0) tensor in Inspector (#2998) (#3192)

Summary:
Pull Request resolved: #2998

Empty tensors are not handled so they throw errors.
 {F1484412951}

Reviewed By: tarun292

Differential Revision: D56027102

fbshipit-source-id: a8dab52d9ba7eb0784a72493e9888cf63aefbb76
(cherry picked from commit f14dc83)

Co-authored-by: Olivia Liu <[email protected]>

Author: pytorchbot

sdk/inspector/_inspector_utils.py

@@ -103,6 +103,9 @@ def get_scalar_type_size(scalar_type: ScalarType) -> Tuple[torch.dtype, int]:
         return torch.zeros(tensor.sizes, dtype=torch_dtype)
 
     tensor_bytes_size = math.prod(tensor.sizes) * dtype_size
+    if tensor_bytes_size == 0:
+        # Empty tensor. Return empty tensor.
+        return torch.zeros(tensor.sizes, dtype=torch_dtype)
 
     if tensor.offset is None:
         raise ValueError("Tensor offset cannot be None")