Error with deconv (conv2d_transpose) layer

Intel® Distribution of OpenVINO™ Toolkit

Community assistance about the Intel® Distribution of OpenVINO™ toolkit, OpenCV, and all aspects of computer vision-related on Intel® platforms.

Error with deconv (conv2d_transpose) layer

752 Views

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?

Link Copied

0 Replies

Community support is provided during standard business hours (Monday to Friday 7AM - 5PM PST). Other contact methods are available here.

Intel does not verify all solutions, including but not limited to any file transfers that may appear in this community. Accordingly, Intel disclaims all express and implied warranties, including without limitation, the implied warranties of merchantability, fitness for a particular purpose, and non-infringement, as well as any warranty arising from course of performance, course of dealing, or usage in trade.

For more complete information about compiler optimizations, see our Optimization Notice.