wangxinanbook commented on issue #13300: Data type error when import onnx model
URL: 
https://github.com/apache/incubator-mxnet/issues/13300#issuecomment-439693344
 
 
   I ran the test. It came out another issue on `test_clip_default_min_cpu`,  
even I used the master code.  I think this should be fixed elsewhere.  How do 
you think ?  @vandanavk 
   ```
   Traceback (most recent call last):
     File 
"/opt/home/wangxinan/anaconda3/envs/test_mxnet/lib/python3.6/site-packages/onnx/backend/test/runner/__init__.py",
 line 243, in device_test_func
       return test_func(*args, device=device, **kwargs)
     File 
"/opt/home/wangxinan/anaconda3/envs/test_mxnet/lib/python3.6/site-packages/onnx/backend/test/runner/__init__.py",
 line 273, in run
       prepared_model = self.backend.prepare(model, device)
     File 
"/opt/home/wangxinan/workspace/incubator-mxnet/tests/python-pytest/onnx/import/mxnet_backend.py",
 line 57, in prepare
       sym, arg_params, aux_params = graph.from_onnx(model.graph)
     File 
"/opt/home/wangxinan/workspace/incubator-mxnet/python/mxnet/contrib/onnx/onnx2mx/import_onnx.py",
 line 131, in from_onnx
       raise err
     File 
"/opt/home/wangxinan/workspace/incubator-mxnet/python/mxnet/contrib/onnx/onnx2mx/import_onnx.py",
 line 128, in from_onnx
       mxnet_sym = self._convert_operator(node_name, op_name, onnx_attr, inputs)
     File 
"/opt/home/wangxinan/workspace/incubator-mxnet/python/mxnet/contrib/onnx/onnx2mx/import_onnx.py",
 line 69, in _convert_operator
       mxnet_sym = new_op(*inputs, **new_attrs)
     File "<string>", line 73, in clip
     File 
"/opt/home/wangxinan/workspace/incubator-mxnet/python/mxnet/_ctypes/symbol.py", 
line 125, in _symbol_creator
       ctypes.byref(sym_handle)))
     File "/opt/home/wangxinan/workspace/incubator-mxnet/python/mxnet/base.py", 
line 252, in check_call
       raise MXNetError(py_str(_LIB.MXGetLastError()))
   mxnet.base.MXNetError: Invalid Parameter format for a_max expect float but 
value='inf', in operator clip(name="", a_max="inf", a_min="0.0")
   ```

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
[email protected]


With regards,
Apache Git Services

Reply via email to