How To Update Graphsurgeon Converter

[lowspec-1997]

how do I update graphsurgeon converter I am confused to put the code that has been provided

diff --git a/node_manipulation.py b/node_manipulation.py
index d2d012a..1ef30a0 100644
--- a/node_manipulation.py
+++ b/node_manipulation.py
@@ -30,6 +30,7 @@ def create_node(name, op=None, _do_suffix=False, **kwargs):
node = NodeDef()
node.name = name
node.op = op if op else name

• node.attr["dtype"].type = 1
  for key, val in kwargs.items():
  if key == "dtype":
  node.attr["dtype"].type = val.as_datatype_enu

[ZouYunzhe]

Just add these lines directly to the create_node function.

def create_node(name, op=None, trt_plugin=False, **kwargs):
if not trt_plugin:
print("WARNING: To create TensorRT plugin nodes, please use the create_plugin_node function instead.")
node = tf.NodeDef()
node.name = name
node.op = op if op else name
node.attr["dtype"].type = 1
for key, val in kwargs.items():
if key == "dtype":
node.attr["dtype"].type = val.as_datatype_enum
return update_node(node, name, op, trt_plugin, **kwargs)

[omisha-bajoria]

Hello @ZouYunzhe

Just add these lines directly to the create_node function.

def create_node(name, op=None, trt_plugin=False, **kwargs): if not trt_plugin: print("WARNING: To create TensorRT plugin nodes, please use the create_plugin_node function instead.") node = tf.NodeDef() node.name = name node.op = op if op else name node.attr["dtype"].type = 1 for key, val in kwargs.items(): if key == "dtype": node.attr["dtype"].type = val.as_datatype_enum return update_node(node, name, op, trt_plugin, **kwargs)

When we update the node_manipulation.py file, where do we add these lines:
diff --git a/node_manipulation.py b/node_manipulation.py
index d2d012a..1ef30a0 100644
--- a/node_manipulation.py
+++ b/node_manipulation.py

We add the rest in the create_node function, however adding the above lines at the top of the document results in errors while importing graphsurgeoun to our notebook, and only adding the lines to the create_node function results in the TypeError: Cannot convert value 0 to a TensorFlow DType.

It would be a huge help if you could share what your node_manipulation.py file looked like after you're done with the changes.