run torchvision_test， got KeyError: 'Shape not implemented yet'

[yangji307]

env as below：
python 3.7
numpy 1.21.6
onnx 1.12.0
onnx-simplifier 0.4.19
onnxruntime 1.14.1
opencv-python 4.7.0.72
protobuf 3.19.0
pytest 7.2.2
tensorboard 2.11.2
tensorboard-data-server 0.6.1
tensorboard-plugin-wit 1.8.1
tensorflow 2.11.0
tensorflow-estimator 2.11.0
tensorflow-intel 2.11.0
tensorflow-io-gcs-filesystem 0.31.0
torch 1.9.0
torchvision 0.10.0+cu102

fail to run test_deeplabv3, and got the fllowing error msg:

`
torchvison_test.py::test_deeplabv3 FAILED [100%]
torchvison_test.py:31 (test_deeplabv3)
@pytest.mark.filterwarnings('ignore::UserWarning')
@pytest.mark.filterwarnings('ignore::DeprecationWarning')
def test_deeplabv3():
model = torchvision.models.segmentation.deeplabv3_resnet50(False)
onnx_model_path = os.path.join(MODEL_ROOT, "deeplabv3_resnet50.onnx")
torch.onnx.export(model, torch.randn(1, 3, 512, 1024), onnx_model_path, opset_version=13)

  error = onnx_converter(onnx_model_path, need_simplify = False, output_path = MODEL_ROOT, target_formats = ['tflite'])

torchvison_test.py:38:

---

converter.py:21: in onnx_converter
keras_model = keras_builder(model_proto, native_groupconv)

---

onnx_model = ir_version: 6
producer_name: "pytorch"
producer_version: "1.9"
graph {
node {
input: "input.1"
output: "363"...im {
dim_param: "Resize600_dim_3"
}
}
}
}
}
}
opset_import {
version: 13
}

native_groupconv = False

def keras_builder(onnx_model, native_groupconv:bool=False):

    conv_layers.USE_NATIVE_GROUP_CONV = native_groupconv

    model_graph = onnx_model.graph

    '''
        init onnx model's build-in tensors
    '''
    onnx_weights = dict()
    for initializer in model_graph.initializer:
        onnx_weights[initializer.name] = numpy_helper.to_array(initializer)

    '''
        build input nodes
    '''
    tf_tensor, input_shape = {}, []
    for inp in model_graph.input:
        input_shape = [x.dim_value for x in inp.type.tensor_type.shape.dim]
        if input_shape == []:
            continue
        batch_size = 1 if input_shape[0] <= 0 else input_shape[0]
        input_shape = input_shape[2:] + input_shape[1:2]
        tf_tensor[inp.name] = keras.Input(shape=input_shape, batch_size=batch_size)

    '''
        build model inline node by iterate onnx nodes.
    '''
    for node in model_graph.node:
        op_name, node_inputs, node_outputs = node.op_type, node.input, node.output
        op_attr = decode_node_attribute(node)

        tf_operator = OPERATOR.get(op_name)
        if tf_operator is None:

          raise KeyError(f"{op_name} not implemented yet")

E KeyError: 'Shape not implemented yet'

utils\builder.py:75: KeyError

`

[MPolaris]

please make need_simplify = True and try again.

[yangji307]

please make need_simplify = True and try again.

i have tried, but got the same error. T_T

[MPolaris]

make sure onnx-simplifier has installed correctly.
check it by:

python -c 'import onnxsim'

[yangji307]

make sure onnx-simplifier has installed correctly. check it by:

python -c 'import onnxsim'

i debug the code, and find something wrong while simplifying the onnx model, is there any problem with my environment?

[MPolaris]

make sure onnx-simplifier has installed correctly. check it by:

python -c 'import onnxsim'

i debug the code, and find something wrong while simplifying the onnx model, is there any problem with my environment?

I cannot reproduce the error.
It seems onnx model is invaild model, please use netron check it.
And, you can try that using onnx and 'onnxruntime' to load model by yourself.
onnxsim is rely on onnxruntime

[MPolaris]

fixed, please pull latest code and try again