Hi,
While converting the tensorflow model (.pb) to snpe (.dlc) , I'm facing issue with the "NonMaxSuppressionV2" operation.
Tensorflow Model type: SSD_Mobilenet_V1
Here is the error:
2018-01-12 17:09:37,629 - 126 - ERROR - Encountered Error: No op named NonMaxSuppressionV2 in defined operations.
Traceback (most recent call last):
File "/home/sam/snpe-sdk/snpe-1.8.0/bin/x86_64-linux-clang/snpe-tensorflow-to-dlc", line 116, in main
model = loader.load(args.graph, in_nodes, in_dims, args.in_type, args.out_node, session)
File "/home/sam/snpe-sdk/snpe-1.8.0/lib/python/converters/tensorflow/loader.py", line 67, in load
graph_def = self.__import_graph(graph_pb_or_meta_path, session, out_node_names)
File "/home/sam/snpe-sdk/snpe-1.8.0/lib/python/converters/tensorflow/loader.py", line 128, in __import_graph
tf.import_graph_def(graph_def, name="")
File "/home/sam/tensorflow/local/lib/python2.7/site-packages/tensorflow/python/framework/importer.py", line 259, in import_graph_def
raise ValueError('No op named %s in defined operations.' % node.op)
ValueError: No op named NonMaxSuppressionV2 in defined operations.
I have met the same problem as you, have you solved it?
Did you get a solution for the your problem? I have similar problem. I retrained a pretrained ssd_mobilenet_v1 model on my own dataset in gpu. I exported and froze the graph. Finally after I tried to convert it to dlc, I have got similar problem as above.
Tensorflow Version for SNPE: 1.5.0
SNPE Version: snpe-1.17.0
`ValueError: No op named NonMaxSuppressionV3 in defined operations`