当我使用 open vino 使用模型优化器将 .pb 文件转换为推理格式时，我不断面临"图形包含循环错误"。 我们使用TensorFlow对象检测模型和SSD Inception V2来生成.pb文件。
[ ERROR ] -------------------------------------------------
[ ERROR ] ----------------- INTERNAL ERROR ----------------
[ ERROR ] Unexpected exception happened.
[ ERROR ] Please contact Model Optimizer developers and forward the following information:
[ ERROR ] Graph contains a cycle.
[ ERROR ] Traceback (most recent call last):
File "/opt/intel/computer_vision_sdk_2018.1.265/deployment_tools/model_optimizer/mo/main.py", line 222, in main
return driver(argv)
File "/opt/intel/computer_vision_sdk_2018.1.265/deployment_tools/model_optimizer/mo/main.py", line 190, in driver
mean_scale_values=mean_scale)
File "/opt/intel/computer_vision_sdk_2018.1.265/deployment_tools/model_optimizer/mo/pipeline/tf.py", line 141, in tf2nx
partial_infer(graph)
File "/opt/intel/computer_vision_sdk_2018.1.265/deployment_tools/model_optimizer/mo/middle/passes/infer.py", line 55, in partial_infer
nodes = nx.topological_sort(graph)
File "/opt/intel/computer_vision_sdk_2018.1.265/deployment_tools/model_optimizer/venv/lib64/python3.5/site-packages/networkx/algorithms/dag.py", line 157, in topological_sort
raise nx.NetworkXUnfeasible("Graph contains a cycle.")
networkx.exception.NetworkXUnfeasible: Graph contains a cycle.
[ ERROR ] ---------------- END OF BUG REPORT --------------
[ ERROR ] -------------------------------------------------
我不熟悉模型优化器，但是在TensorFlow图中有循环是完全正常的。如果你的模型在某处有一个tf.while_loop，它的图将有一个周期。我的猜测是model_optimizer人不处理这样的模型。
使用以下参数执行命令：
python3 mo_tf.py --input_model <MODEL_PATH> --tensorflow_use_custom_operations_config <OPENVINO_DIR>/deployment_tools/model_optimizer/extensions/front/tf/faster_rcnn_support.json
然后 OpenVINO 将成功转换您的模型。 查看此链接以获取更多信息