I get error when converted onnx model to tvm relay IR. I found an op named ‘Loop’ in onnx model which exported from pytorch. How can I solve the problem.
Traceback (most recent call last):
File "quantized_onnx.py", line 172, in <module>
mod, params = relay.frontend.from_onnx(onnx_model, shape_dict)
File "/home/tvm/python/tvm/relay/frontend/onnx.py", line 4049, in from_onnx
mod, params = g.from_onnx(graph, opset)
File "/home/tvm/python/tvm/relay/frontend/onnx.py", line 3813, in from_onnx
op = self._convert_operator(op_name, inputs, attr, opset)
File "/home/tvm/python/tvm/relay/frontend/onnx.py", line 3942, in _convert_operator
sym = convert_map[op_name](inputs, attrs, self._params)
File "/home/tvm/python/tvm/relay/frontend/onnx.py", line 2747, in _impl_v11
loop_deps = inputs[2:]
File "/home/tvm/python/tvm/relay/frontend/onnx.py", line 71, in __getitem__
indices = list(range(item.stop)[item])
TypeError: 'NoneType' object cannot be interpreted as an integer