Label binariser converter doesn't work on 2-D data

[prabhat00155]

X1 = np.array([[0, 1, 1], [1, 0, 0]])
model = LabelBinarizer().fit(X1)
print(model.transform(X1))

onnx_fs = convert_sklearn(model, 'lb', [('float_input', Int64TensorType(X1.shape))])
onnxmltools.utils.save_model(onnx_fs, 'lb.onnx')
sess = InferenceSession('lb.onnx')
res = sess.run('', input_feed={'float_input': X1.astype(np.int64)})
res

[[0 1 1]
[1 0 0]]

RuntimeError Traceback (most recent call last)
in
5 onnx_fs = convert_sklearn(model, 'lb', [('float_input', Int64TensorType(X1.shape))])
6 onnxmltools.utils.save_model(onnx_fs, 'lb.onnx')
----> 7 sess = InferenceSession('lb.onnx')
8 res = sess.run('', input_feed={'float_input': X1.astype(np.int64)})
9 res

~/Documents/MachineLearning/onnx_projects/onnx_env/lib/python3.6/site-packages/onnxruntime/capi/session.py in init(self, path_or_bytes, sess_options)
27
28 if isinstance(path_or_bytes, str):
---> 29 self._sess.load_model(path_or_bytes)
30 elif isinstance(path_or_bytes, bytes):
31 self._sess.read_bytes(path_or_bytes)

RuntimeError: [ONNXRuntimeError] : 1 : GENERAL ERROR : Load model from lb.onnx failed:Node:Cast Output:variable [ShapeInferenceError] Can't merge shape info. Both source and target dimension have values but they differ. Source=6 Target=2 Dimension=0