You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
When I try to convert the model weights to TensorRT engines I get the following error:
File "/home/dt/miniconda3/envs/TensorRT/lib/python3.6/site-packages/tensorflow/python/framework/importer.py", line 497, in _import_graph_def_internal
graph._c_graph, serialized, options) # pylint: disable=protected-access
tensorflow.python.framework.errors_impl.InvalidArgumentError: NodeDef mentions attr 'validate_shape' not in Op<name=AssignVariableOp; signature=resource:resource, value:dtype -> ; attr=dtype:type; is_stateful=true>; NodeDef: {{node AssignNewValue}}. (Check whether your GraphDef-interpreting binary is up to date with your GraphDef-generating binary.).
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/home/dt/miniconda3/envs/TensorRT/lib/python3.6/site-packages/tensorflow/python/compiler/tensorrt/trt_convert.py", line 1085, in convert
self._input_saved_model_tags)
File "/home/dt/miniconda3/envs/TensorRT/lib/python3.6/site-packages/tensorflow/python/saved_model/load.py", line 578, in load
return load_internal(export_dir, tags)
File "/home/dt/miniconda3/envs/TensorRT/lib/python3.6/site-packages/tensorflow/python/saved_model/load.py", line 604, in load_internal
export_dir)
File "/home/dt/miniconda3/envs/TensorRT/lib/python3.6/site-packages/tensorflow/python/saved_model/load.py", line 116, in __init__
meta_graph.graph_def.library))
File "/home/dt/miniconda3/envs/TensorRT/lib/python3.6/site-packages/tensorflow/python/saved_model/function_deserialization.py", line 311, in load_function_def_library
func_graph = function_def_lib.function_def_to_graph(copy)
File "/home/dt/miniconda3/envs/TensorRT/lib/python3.6/site-packages/tensorflow/python/framework/function_def_to_graph.py", line 63, in function_def_to_graph
importer.import_graph_def_for_function(graph_def, name="")
File "/home/dt/miniconda3/envs/TensorRT/lib/python3.6/site-packages/tensorflow/python/framework/importer.py", line 412, in import_graph_def_for_function
graph_def, validate_colocation_constraints=False, name=name)
File "/home/dt/miniconda3/envs/TensorRT/lib/python3.6/site-packages/tensorflow/python/framework/importer.py", line 501, in _import_graph_def_internal
raise ValueError(str(e))
ValueError: NodeDef mentions attr 'validate_shape' not in Op<name=AssignVariableOp; signature=resource:resource, value:dtype -> ; attr=dtype:type; is_stateful=true>; NodeDef: {{node AssignNewValue}}. (Check whether your GraphDef-interpreting binary is up to date with your GraphDef-generating binary.).
What tensorflow version was used to save these weights? I am using the same requirements.txt for my environment but still running into this issue.
The text was updated successfully, but these errors were encountered:
Installed packages:
packages.txt
GTX 1070 8Gb memory, Ryzen 5, Ubuntu 20.04
When I try to convert the model weights to TensorRT engines I get the following error:
What tensorflow version was used to save these weights? I am using the same requirements.txt for my environment but still running into this issue.
The text was updated successfully, but these errors were encountered: