frame

Howdy, Stranger!

It looks like you're new here. If you want to get involved, click one of these buttons!

Sign In

Howdy, Stranger!

It looks like you're new here. If you want to get involved, click one of these buttons!

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?

Sign In or Register to comment.