JFishLover commented on issue #3428: URL: https://github.com/apache/incubator-tvm/issues/3428#issuecomment-712521181
> When I run the `tutorial/frontend/from_tensorflow.py` script with my own custom model (ResNet style), I get the following error: > > ``` > Traceback (most recent call last): > File "/usr/tvm/tutorials/frontend/from_tensorflow.py", line 104, in <module> > shape=shape_dict) > File "/usr/tvm/python/tvm/relay/frontend/tensorflow.py", line 2349, in from_tensorflow > mod, params = g.from_tensorflow(graph, layout, shape, outputs) > File "/usr/tvm/python/tvm/relay/frontend/tensorflow.py", line 1994, in from_tensorflow > op = self._convert_operator(node.op, inputs, attr, graph) > File "/usr/tvm/python/tvm/relay/frontend/tensorflow.py", line 2312, in _convert_operator > sym = convert_map[op_name](inputs, attrs, self._params) > File "/usr/tvm/python/tvm/relay/frontend/tensorflow.py", line 469, in _impl > custom_check=_dimension_constraint())([inputs[0], inputs[1]], attr) > File "/usr/tvm/python/tvm/relay/frontend/tensorflow.py", line 155, in __call__ > return _get_relay_op(op_name)(*inputs, **new_attrs) > TypeError: conv2d() got an unexpected keyword argument 'explicit_paddings' > ``` > > If I delete the `explicit_padding` attribute when processing my model in `python/tvm/relay/frontend/tensorflow.py` then I don't get any error and everything works fine. your delete aperation gives me an idea, thx ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected]
