Community
cancel
Showing results for 
Search instead for 
Did you mean: 
idata
Community Manager
418 Views

AttributeError: NOT_ALLOCATED

Traceback (most recent call last):

 

File "run.py", line 14, in

 

import mvnc_simple_api as mvnc

 

File "../../ncapi2_shim/mvnc_simple_api.py", line 10, in

 

class mvncStatus(Enum):

 

File "../../ncapi2_shim/mvnc_simple_api.py", line 23, in mvncStatus

 

NOT_ALLOCATED = mvncapi2.Status.NOT_ALLOCATED

 

File "/usr/local/lib/python3.5/dist-packages/mvnc/mvncapi.py", line 46, in getattr

 

return getattr(self.new_target, attr)

 

File "/usr/lib/python3.5/enum.py", line 274, in getattr

 

raise AttributeError(name) from None

 

AttributeError: NOT_ALLOCATED
Tags (1)
0 Kudos
4 Replies
idata
Community Manager
74 Views

I have the same problem.

 

If you solve this problem,could you share it with me ?
idata
Community Manager
74 Views

I had the same problem usig ncsdk2 with movidus NCS 1 for the ncappzoo example code video_face_matcher.

 

The solution for me was commenting out the line the line 8

 

#import mvnc_simple_api as mvnc

 

and uncommenting the line 9

 

from mvnc import mvncapi as mvnc
arunav
Beginner
74 Views

Hi,

I am also getting the NOT_ALLOCATED problem.

Here is my experiment.

 

I created the XML and BIN files using the openvino_2019.1.144.

With the XML I created the Movidius specific graph file as below:

 

/opt/intel/openvino_2019.1.144/deployment_tools/inference_engine/lib/intel64/myriad_compile -m model/FP16/serialized.xml -o graph_file_for_tm_npu -VPU_PLATFORM VPU_2480 -VPU_NUMBER_OF_SHAVES 4 -VPU_NUMBER_OF_CMX_SLICES 4

Now for the generated graph_file_for_tm_npu file, I am trying to import the graph using the following code:

"""NCAPI v2"""   ### initialization # from mvnc import mvncapi # import mvnc.mvncapi as fx from mvnc import mvncapi as mvnc     ######################## Device Initialization ####################### device_list = mvnc.enumerate_devices() device = mvnc.Device(device_list[0]) ########################################################################   device.open()   ####################### Load Neural Network ########################   # Initialize a graph from file at some GRAPH_FILEPATH GRAPH_FILEPATH = 'model/graph/graph_file_for_tm_npu'   with open(GRAPH_FILEPATH, mode='rb') as f: graph_buffer = f.read()   graph = mvnc.Graph('model/graph/graph_file_for_tm_npu')   print("able to read the graph successfully .... !")   input_descs = graph.get_option(mvnc.GraphOption.RO_INPUT_TENSOR_DESCRIPTORS)   print(input_descs)   # CONVENIENCE FUNCTION: # Allocate the graph to the device and create input/output Fifos with default options in one call # input_fifo, output_fifo = graph.allocate_with_fifos(device, graph_buffer) ########################################################################   device.close() device.destroy()

But I am getting the following error:

 

--------------------------------------------------------------------------- Exception Traceback (most recent call last) <ipython-input-1-ac2630ebc6c8> in <module> 26 print("able to read the graph successfully .... !") 27 ---> 28 input_descs = graph.get_option(mvnc.GraphOption.RO_INPUT_TENSOR_DESCRIPTORS) 29 30 print(input_descs)   /usr/lib/python3.5/site-packages/mvnc/mvncapi.py in get_option(self, option) 688 self.handle, GraphOption.RO_INPUT_COUNT.value, byref(desc_count), byref(optsize)) 689 if status != Status.OK.value: --> 690 raise Exception(Status(status)) 691 692 # Create an appropriately sized buffer for getting the TensorDescriptor data   Exception: Status.NOT_ALLOCATED

Please let me know how to resolve this problem.

 

Thanks

Kind Regards

Arun

 

 

SDesh14
Beginner
74 Views

Hey Were you able to solve it? I'm running the hello_ncs_py code