I executed the following code
snpe-tensorflow-to-dlc --input_network <path_to>/exported/frozen_inference_graph.pb --input_dim Preprocessor/sub 1,300,300,3 --out_node detection_classes --out_node detection_boxes --out_node detection_scores ---output_path mobilenet_ssd.dlc
and was able to generate a dlc file
On putting the file in an app on android studio i found that the only output was from the node detection_classes:0 .
Does this mean that if i have a network like ssd mobilenet where i need output from 3 nodes, i need to create 3 seperate dlc files and hence my app will have to host 3 different copies of the neural network with each copy providing output from a different node?