Two inputs for compilation

I have been using a model which has multiple inputs:- 0 : (1,3,480,640) and 1: (1,3,480,640)

Below is the format of code:

input_name = [‘0’, ‘1’]

shape_dict = {‘0’:(1,3,480,640), ‘1’:(1,3,480,640)}

mod, params = relay.frontend.from_onnx(onnx_model, shape_dict)

with tvm.transform.PassContext(opt_level=3):

lib= relay.build(mod, target=target, params=params)

Below is the error being faced: TVMError:

An error occurred during the execution of TVM. For more information, please see: Handle TVM Errors — tvm 0.11.dev0 documentation

Check failed: (false) is false: [17:02:44] /home/apache_tvm/apache-tvm-src-v0.9.0/src/relay/op/tensor/transform.cc:3045:

An error occurred during the execution of TVM. For more information, please see: Handle TVM Errors — tvm 0.11.dev0 documentation

Check failed: (reporter->Assert(begin < data->shape[axis])) is false: The sum of sections must match the input.shape[axis]

Any suggestions on giving two inputs for compiling the model. Thank you