- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hello!
I'm trying to implement the CNN multi view network in Movidius NCS (MVCNN image).
Is it possible to use an input for NCS of dimensions [Nviews, batch_size, im_l, im_w, Nchannels]?
I have tried to isolate the CNN1 network (Tensorboard graph in the image), and generate the Movidius .graph using:
mvNCCompile MVCNN.meta -s 12 -in im0 -on Reshape -o OutGraph.graph
I got the following error:
/home/cristian/tf/lib/python3.5/site-packages/tensorflow/python/framework/ops.py:858: DeprecationWarning: builtin type EagerTensor has no __module__ attribute
EagerTensor = c_api.TFE_Py_InitEagerTensor(_EagerTensorBase)
/home/cristian/tf/lib/python3.5/site-packages/tensorflow/python/util/tf_inspect.py:45: DeprecationWarning: inspect.getargspec() is deprecated, use inspect.signature() instead
if d.decorator_argspec is not None), _inspect.getargspec(target))
/home/cristian/tf/lib/python3.5/site-packages/tensorflow/python/util/tf_inspect.py:45: DeprecationWarning: inspect.getargspec() is deprecated, use inspect.signature() instead
if d.decorator_argspec is not None), _inspect.getargspec(target))
/home/cristian/tf/lib/python3.5/site-packages/tensorflow/python/framework/tensor_util.py:539: DeprecationWarning: The binary mode of fromstring is deprecated, as it behaves surprisingly on unicode inputs. Use frombuffer instead
return np.fromstring(tensor.tensor_content, dtype=dtype).reshape(shape)
Traceback (most recent call last):
File "/usr/local/bin/mvNCCompile", line 118, in <module>
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 298, in parse_tensor
item_shape = output_item.shape.as_list()
File "/home/cristian/tf/lib/python3.5/site-packages/tensorflow/python/framework/tensor_shape.py", line 809, in as_list
raise ValueError("as_list() is not defined on an unknown TensorShape.")
ValueError: as_list() is not defined on an unknown TensorShape.
The code of the original model is here:
https://github.com/WeiTang114/MVCNN-TensorFlow
My custom code is in Train.py
Thank you very much!
- Tags:
- Tensorflow
Link Copied
0 Replies

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