Showing results for 
Search instead for 
Did you mean: 
Community Manager

Is there any instruction to train my own model?



I'm a newer to use ncs. About one month ago I purchased my ncs stick but with no idea to apply my own model.




_Goal and What I did_


Goal: I'm trying to train a vgg_16 model to detect object, I'll be very happy if faster-rcnn is also available.


What I did: I have a stable version of vgg16 model trained by Faster RCNN with my own dataset. I generated a vgg16 graphDef by using, and then use but something seems wrong (because I met rhs lhs issue) and I even don't know what is the output node for vgg16. Then I thought maybe it's important to train a smaller model by using TensorFlow's Object Detection API firstly, and that is my first step.




I'd like to apply Tensorflow's Object detection API with ssd_mobilenet v1 onto ncs. By following I got a saved_model.pb file from ssd_mobile_v1.ckpt, then I ran


mvNCCompile saved_model.pb -in=input -on=MobilenetV1/Predictions/Reshape_1 -is 224 224 -o graph


Maybe there are some error arguments, I got an issue like


Traceback (most recent call last): File "/usr/local/bin/mvNCCompile", line 118, in <module> create_graph(, args.inputnode, args.outputnode, args.outfile, args.nshaves, args.inputsize, args.weights) File "/usr/local/bin/mvNCCompile", line 104, in create_graph net = parse_tensor(args, myriad_config) File "/usr/local/bin/ncsdk/Controllers/", line 210, in parse_tensor graph_def.ParseFromString( google.protobuf.message.DecodeError: Error parsing message


I got this unexpected error in my first step. Could anyone give me some direction? Thanks.

Tags (1)
0 Kudos
1 Reply
Community Manager



I'm also facing the same problem, i trained a object detection network using Google's Tensorflow Object detection API, in my case I used the "faster_rcnn_inception_resnet_v2" architecture. Once trained I froze the, ckpt.index and ckpt.meta files into a saved_model.pb


After running:


mvNCCompile saved_model.pb -s 12 -in=image_tensor -on=detection_boxes -is 1920 1080 -o out.graph


I got the exact same error as @ZxqCreations.


Any idea on how to solve it?