Hi, all. Hope everyone is doing well.
I’m trying to run tensorflow frontend and having issue running tutorial Compile Tensorflow Models — tvm 0.8.dev0 documentation .
My tensorflow version is 2.4.1 and this is trackback that I’m getting:
Traceback (most recent call last):
File "from_tensorflow.py", line 134, in <module>
mod, params = relay.frontend.from_tensorflow(graph_def, layout=layout, shape=shape_dict)
File "/opt/tvm/python/tvm/relay/frontend/tensorflow.py", line 3612, in from_tensorflow
mod, params = g.from_tensorflow(graph, layout, shape, outputs)
File "/opt/tvm/python/tvm/relay/frontend/tensorflow.py", line 3018, in from_tensorflow
func = self._get_relay_func(graph, layout=layout, shape=shape, outputs=outputs)
File "/opt/tvm/python/tvm/relay/frontend/tensorflow.py", line 2982, in _get_relay_func
self._backtrack_construct(node.name)
File "/opt/tvm/python/tvm/relay/frontend/tensorflow.py", line 3542, in _backtrack_construct
op = self._convert_operator(node.op, node.name, inputs, attr)
File "/opt/tvm/python/tvm/relay/frontend/tensorflow.py", line 3384, in _convert_operator
sym = convert_map[op_name](inputs, attrs, self._params, self._mod)
File "/opt/tvm/python/tvm/relay/frontend/tensorflow.py", line 284, in _impl
)(inputs, attr)
File "/opt/tvm/python/tvm/relay/frontend/common.py", line 430, in __call__
return get_relay_op(op_name)(*inputs, **new_attrs)
TypeError: max_pool2d() got an unexpected keyword argument 'explicit_paddings'
I saw there was a similar report back then, but the tensorflow version assumed in this discussion seems quite far from the current tensorflow.
Any thoughts or advice will be greatly appreciated. Thank you!