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

Error with deconv (conv2d_transpose) layer

Hello,

 

I am trying to run mvNCCompile on a frozen graph file, and I get the following error:

 

[Error 5] Toolkit Error: Stage Details Not Supported: FusedBatchNorm must be preceded by convolution or fully connected layer

 

The graph that we want to compile to a movidius graph is an implementation of FlowNet. The graph has been frozen and only contains the nodes needed for inference. We are using mvNCCompile v2.05. Every batch_normalization is preceded by a conv2d or conv2d_transpose layer, and we run into this error on the first conv2d_transpose layer. Will there be support in the future for a batch_normalization node preceded a conv2d_transpose node?

0 Kudos
0 Replies
Reply