2020-06-08 14:08:50.087477: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1159] Device interconnect StreamExecutor with strength 1 edge matrix:
2020-06-08 14:08:50.101983: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1165]
- [ FRAMEWORK ERROR ] Cannot load input model: "The name 'RMSProp' refers to an Operation not in the graph
Can someone help me to solve this problem？
It seems like your problem is more towards Tensorflow section.
I believe you are trying to freeze/export a saved model.
You can refer here for how to freeze a model and serve it with a python api : https://blog.metaflow.fr/tensorflow-how-to-freeze-a-model-and-serve-it-with-a-python-api-d4f3596b3ad...
Ensure to use tflearn instead of loading the model using tensorflow: https://stackoverflow.com/questions/45595646/in-tensorflow-how-to-freeze-saved-model
Also, here is the Official Openvivo Tensorflow convertion documentation: https://docs.openvinotoolkit.org/latest/_docs_MO_DG_prepare_model_convert_model_Convert_Model_From_T...
Hope my answer helps!.