Forums - Onnx2Dlc: Incorrect output shape inference of Expand

Hello,

I'm converting Onnx to Dlc using snpe1.64 and I found a strange behavior of output shape inference of Expand operation.

In the file snpe-1.64.0.3605/lib/python/qti/aisw/converters/onnx/data_translations.py at the class OnnxExpandTranslation, your logic to find output shape is not always correct. 

# ------------------------------------------------------------------------------

# Expand

# ------------------------------------------------------------------------------

class OnnxExpandTranslation(OnnxTranslationBase):

def __init__(self):

OnnxTranslationBase.__init__(self)

self.register_op_schema('Expand', [8, 13])

def extract_parameters(self, src_op, converter_context):

graph = converter_context.ir_graph

src_input_names = list(map(str, src_op.input))

shape_constant_op = self.fetch_constant_op(src_input_names[1], converter_context, dtype=np.int32, fail_if_not_found=True)

log_debug1(code_to_message.get_debugging_message("DEBUG_STATIC_OP")(src_input_names[1]))

output_shape = [int(dim_size) for dim_size in shape_constant_op.tensor]

return op_adapter.ExpandOp(src_op.name,

output_shape)

def extract_input_names(self, src_op, converter_context):

return [str(src_op.input[0])]

In this code, you use the value of constant tensor in Expand Operation as the output shape, but according to documentation of Onnx (https://github.com/onnx/onnx/blob/main/docs/Operators.md#Expand), the output shape should also follow broadcast rule.

For exemple:

If you  have an input with shape (3, 1), and your constant tensor is (2, 1, 6), you should have output shape equal to (2, 3, 6) instead of (2, 1, 6) in your implementation. You can read the example in Onnx documentation for more information.