- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content
Link Copied
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content
I'm experiencing a similar kind of error as below :-
mvNCCompile v02.00, Copyright @ Movidius Ltd 2016
/home/chirag/.local/lib/python3.5/site-packages/tensorflow/python/util/tf_inspect.py:75: DeprecationWarning: inspect.getargspec() is deprecated, use inspect.signature() instead
return _inspect.getargspec(target)
Traceback (most recent call last):
File "/usr/local/bin/mvNCCompile", line 118, in
create_graph(args.network, 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/TensorFlowParser.py", line 290, in parse_tensor
if have_first_input(strip_tensor_id(node.outputs[0].name)):
IndexError: list index out of range
Compilation step - mvNCCompile TF_Model/tf_model.meta -in=mobilenet_1.00_128_input -on=dense_1/Sigmoid
My model comprises of MobileNet v1_00_128 and the meta file is attached along -
Tensorflow version - v1.12.0
This model is originally converted from keras to tensorflow metafile using the command (python3 keras_2_tf.py script attached )
The original Keras script is attached too.(new.py).
Could someone please look into this and help me in fixing it????
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content
Hi everyone,
I ran across a similar issue when dealing with the MTCNN Tensorflow example that was originally included as part of the version 1 SDK AppZoo.
At first I thought it was a python error, then I took apart the makefile, and saw it was coming from the compile of the model.
Does anyone have any additional insight into this issue?
I went through all the forum messages, and what I was able to deduce was that Intel made changes between SDK version 1, and SDK version 2.
Somewhere along the lines it looks like something might have broken.
My understanding is that this worked in SDKv1
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content
Hi, I'd managed to fix the index error by fixing the broken Tensorflowparser file.It is broken at 2 different lines
1.https://github.com/ardamavi/Intel-Movidius-NCS-Keras/issues/1 Getting IndexError on conversion · Issue # 1 · ardamavi/Intel-Movidius-NCS-Keras ·
2.https://github.com/ardamavi/Intel-Movidius-NCS-Keras/issues/2 InvalidArgumentError · Issue # 2 · ardamavi/Intel-Movidius-NCS-Keras · GitHub

- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page