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

Different results from Original Tensorflow model and Inference from NCS

Hello ,

 

I have been getting wrong results in comparison with the original tensorflow model. I followed the guidance to create the tensorflow model without unneccesary layers (such as dropout) and the created model works perfectly when predicted with GPU. Then once I create the freeze graph, and use it to predict my dataset, i get completely different results. The things is that mvNCCheck passes every test(see below details). But the graph created with mvNCCompile produces completely wrong results. Kindly help me on this.

 

`sangathamilan@sangathamilan:~/Project/without_concat$ mvNCCheck ./NCS1/inference.meta -s 12 -in=input -on=softmax_out -is 100 25 -cs 0,1,2 -ec

 

mvNCCheck v02.00, Copyright @ Movidius Ltd 2016

 

/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/ops.py:939: DeprecationWarning: builtin type EagerTensor has no module attribute

 

EagerTensor = c_api.TFE_Py_InitEagerTensor(_EagerTensorBase)

 

/usr/local/lib/python3.5/dist-packages/tensorflow/python/util/tf_inspect.py:55: DeprecationWarning: inspect.getargspec() is deprecated, use inspect.signature() instead

 

if d.decorator_argspec is not None), _inspect.getargspec(target))

 

/usr/local/lib/python3.5/dist-packages/tensorflow/python/util/tf_inspect.py:55: DeprecationWarning: inspect.getargspec() is deprecated, use inspect.signature() instead

 

if d.decorator_argspec is not None), _inspect.getargspec(target))

 

/usr/local/bin/ncsdk/Controllers/FileIO.py:52: UserWarning: You are using a large type. Consider reducing your data sizes for best performance

 

"Consider reducing your data sizes for best performance\033[0m")

 

USB: Transferring Data…

 

USB: Myriad Execution Finished

 

USB: Myriad Connection Closing.

 

USB: Myriad Connection Closed.

 

Result: (1, 1, 2)

 

1) 1 0.73438

 

2) 0 0.26514

 

Expected: (1, 2)

 

1) 1 0.728714

 

2) 0 0.271286

 

 

Obtained values

 

** Obtained Min Pixel Accuracy: 0.8437934331595898% (max allowed=2%), Pass

 

Obtained Average Pixel Accuracy: 0.8102884516119957% (max allowed=1%), Pass

 

Obtained Percentage of wrong values: 0.0% (max allowed=0%), Pass

 

Obtained Pixel-wise L2 error: 0.8109808796745067% (max allowed=1%), Pass

 

Obtained Global Sum Difference: 0.011809378862380981**

 

`

0 Kudos
1 Reply
idata
Community Manager
63 Views

Hi @sangathamilan

 

What application are you using? Can you provide the code you're using? I'd like to try to reproduce this issue to see what kind of results I'm getting. Bad results sometimes mean there could be an error in the pre processing.

 

Best Regards,

 

Sahira
Reply