Iteration over 0d tensor

[justinchuby]

PyTorch ONNX Conversion Error Report

✅ Obtain model graph with `torch.export.export`
❌ Translate the graph into ONNX
⚪ Run `onnx.checker` on the ONNX model
⚪ Execute the model with ONNX Runtime
⚪ Validate model output accuracy

Error message:

Traceback (most recent call last):
  File "/Users/justinc/Documents/GitHub/torch-onnx/src/torch_onnx/_core.py", line 490, in _add_nodes
    _handle_call_function_node_with_lowering(
  File "/Users/justinc/Documents/GitHub/torch-onnx/src/torch_onnx/_core.py", line 422, in _handle_call_function_node_with_lowering
    _set_shape_types(outputs, node.meta["val"], complex_to_float=True)
  File "/Users/justinc/Documents/GitHub/torch-onnx/src/torch_onnx/_core.py", line 109, in _set_shape_types
    for value, meta_val in zip(values, meta_vals):
                           ^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/justinc/Documents/GitHub/torch-onnx/venv/lib/python3.11/site-packages/torch/_tensor.py", line 1047, in __iter__
    raise TypeError("iteration over a 0-d tensor")
TypeError: iteration over a 0-d tensor

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "/Users/justinc/Documents/GitHub/torch-onnx/src/torch_onnx/_patch.py", line 222, in _torch_onnx_export
    ir_model = torch_onnx.exported_program_to_ir(program)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/justinc/Documents/GitHub/torch-onnx/src/torch_onnx/_core.py", line 626, in exported_program_to_ir
    values = _add_nodes(exported_program, model, lower=lower, registry=registry)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/justinc/Documents/GitHub/torch-onnx/src/torch_onnx/_core.py", line 501, in _add_nodes
    raise RuntimeError(
RuntimeError: Error when translating node %zeros : [num_users=1] = call_function[target=torch.ops.aten.zeros.default](args = ([],), kwargs = {device: cpu, pin_memory: False}). See the stack trace for more information.

Exported program:

ExportedProgram:
    class GraphModule(torch.nn.Module):
        def forward(self, arg0_1: "f32[]"):
            # File: /Users/justinc/Documents/GitHub/torch-onnx/tests/torch_tests/torch_onnx_test.py:3217 in forward, code: y = torch.zeros(())
            zeros: "f32[]" = torch.ops.aten.zeros.default([], device = device(type='cpu'), pin_memory = False)

            # File: /Users/justinc/Documents/GitHub/torch-onnx/tests/torch_tests/torch_onnx_test.py:3218 in forward, code: y += x
            add: "f32[]" = torch.ops.aten.add.Tensor(zeros, arg0_1);  zeros = arg0_1 = None
            return (add,)

Graph signature: ExportGraphSignature(input_specs=[InputSpec(kind=<InputKind.USER_INPUT: 1>, arg=TensorArgument(name='arg0_1'), target=None, persistent=None)], output_specs=[OutputSpec(kind=<OutputKind.USER_OUTPUT: 1>, arg=TensorArgument(name='add'), target=None)])
Range constraints: {}

Analysis

PyTorch ONNX Conversion Analysis

Model Information

The model has 0 parameters and 0 buffers (non-trainable parameters). Number of parameters per dtype:

defaultdict(<class 'int'>, {})

Number of buffers per dtype:

defaultdict(<class 'int'>, {})

Inputs:

• arg0_1: TensorMetadata(shape=torch.Size([]), dtype=torch.float32, requires_grad=False, stride=(), memory_format=torch.contiguous_format, is_quantized=False, qparams={})

Outputs:

• add: TensorMetadata(shape=torch.Size([]), dtype=torch.float32, requires_grad=False, stride=(), memory_format=torch.contiguous_format, is_quantized=False, qparams={})

The FX graph has 4 nodes in total. Number of FX nodes per op:

• placeholder: 1
• call_function: 2
• output: 1

Of the call_function nodes, the counts of operators used are:

• aten.zeros.default: 1
• aten.add.Tensor: 1

ONNX Conversion Information

All operators in the model have registered ONNX decompositions.