KeyError: '498' W_shape = graph.shape_dict[W_name]

[fcqfcq]

🐞Describe the bug

A clear and brief description of what the bug is.

Trace

If applicable, please paste the error trace.

---------------------------------------------------------------------------
KeyError                                  Traceback (most recent call last)
<ipython-input-14-f3ca1d2728f9> in <module>
      1 
----> 2 cml = onnx_coreml.convert(model,minimum_ios_deployment_target='13')
      3 cml.save('stylegan2.mlmodel')
      4 

/usr/local/miniconda3/envs/dl/lib/python3.6/site-packages/onnx_coreml/converter.py in convert(model, mode, image_input_names, preprocessing_args, image_output_names, deprocessing_args, class_labels, predicted_feature_name, add_custom_layers, custom_conversion_functions, onnx_coreml_input_shape_map, minimum_ios_deployment_target)
    624         print("%d/%d: Converting Node Type %s" %(i+1, len(graph.nodes), node.op_type))
    625         if disable_coreml_rank5_mapping:
--> 626             _convert_node_nd(builder, node, graph, err)
    627         else:
    628             _add_const_inputs_if_required(builder, node, graph, err)

/usr/local/miniconda3/envs/dl/lib/python3.6/site-packages/onnx_coreml/_operators_nd.py in _convert_node_nd(builder, node, graph, err)
   2385 def _convert_node_nd(builder, node, graph, err):  # type: (NeuralNetworkBuilder, Node, Graph, ErrorHandling) -> None
   2386     converter_fn = _get_node_converter_fn(builder, node, err)
-> 2387     return converter_fn(builder, node, graph, err)
   2388 

/usr/local/miniconda3/envs/dl/lib/python3.6/site-packages/onnx_coreml/_operators_nd.py in _convert_conv(builder, node, graph, err)
    487         # Expected CoreML Format: H x W x KC x OC
    488         W_name = node.inputs[1]
--> 489         W_shape = graph.shape_dict[W_name]
    490         W_rank  = len(W_shape)
    491 

KeyError: '498'    W_shape = graph.shape_dict[W_name]

To Reproduce

• If a python script can reproduce the error, please paste the code snippet

from onnx_coreml import convert
cml = onnx_coreml.convert(model,minimum_ios_deployment_target='13')

# Paste code snippet here

• If applicable, please attach ONNX model
  • If model cannot be shared publicly, please attach it via filing a bug report at https://developer.apple.com/bug-reporting/
• If model conversion succeeds, however, there is numerical mismatch between the original and the coreml model, please paste python script used for comparison (pytorch code, onnx runtime code etc.) pytorch->onnx

System environment (please complete the following information):

• coremltools version (e.g., 3.0b5):3.3.0
• onnx-coreml version (e.g. 1.0b2):1.2
• OS (e.g., MacOS, Linux):linux
• macOS version (if applicable):
• How you install python (anaconda, virtualenv, system):anaconda
• python version (e.g. 3.7):3.6
• any other relevant information:

Additional context

Add any other context about the problem here.

[bhushan23]

@fcqfcq looks like shape information is not available for input weights.
Can you share onnx model?