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

Error 4: when compiling TF-model with tanh activation

I tried to compile two very basic models that I created in Keras and then saved as a TensorFlow model (I followed this guide).

 

First I had a model which used the LeakyReLU from Keras. Trying to compile this model using mvNCCompile I got the following error log:

 

mvNCCompile v02.00, Copyright @ Intel Corporation 2017 ****** Info: No Weights provided. inferred path: tf_model.data-00000-of-00001****** tf_model.meta 2019-03-18 16:44:01.272627: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA No Bias [Error 5] Toolkit Error: Stage Details Not Supported: leaky_re_lu_1/LeakyRelu/mul

 

So I did a quick search on which activations are supported by NCSDK and found _tanh_ should be supported due to these release notes.

 

I trained a new model, now using _tanh_ as activation. But this time I got the following error log:

 

mvNCCompile v02.00, Copyright @ Intel Corporation 2017 ****** Info: No Weights provided. inferred path: tf_model.data-00000-of-00001****** tf_model.meta 2019-03-27 09:19:38.161469: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA No Bias [Error 4] Toolkit Error: Stage Type Not Supported: Tanh

 

Please help me with that, as I don't know how to work around that error.

Tags (2)
0 Kudos
2 Replies
idata
Community Manager
104 Views

Hi @martin-online

 

Which version of the NCSDK are you using?

 

The top and bottom blobs have different names right? Can you attach your model here so I can take a look at it please?

 

Best Regards,

 

Sahira
idata
Community Manager
104 Views

Hi @Sahira_at_Intel ,

 

thanks for your reply!

 

I'm using the NCSDK version 2.10.01.01.

 

That's the model.summary() of the simple model with tanh activation in the "activation_1" and softmax in "activation_2".

 

 

Layer (type) Output Shape Param #

 

=================================================================

 

dense_1 (Dense) (None, 8) 328

 

 

activation_1 (Activation) (None, 8) 0

 

 

output (Dense) (None, 3) 27

 

 

activation_2 (Activation) (None, 3) 0

 

=================================================================

 

Total params: 355

 

Trainable params: 355

 

Non-trainable params: 0

 

 

Input: []

 

Output: []

 

Here's visualisation as an image: https://imgur.com/Lx7ttfU

 

Looking forward to your answer. =)

 

Best regards,

 

Martin
Reply