Forums - "Error while building SNPE object" when run xception model

1 post / 0 new
"Error while building SNPE object" when run xception model
haroldyang977
Join Date: 15 May 18
Posts: 4
Posted: Wed, 2019-03-13 02:02

Hi there,

I succesfully converted my xception based onnx model to dlc.

When I use snpe-net-run to test the model on my S845 phone with "gpu", it just showing the message that:

"error_message=Layer parameters combination is invalid in GPU Layer exit_flow_block2_separable_conv1_depthwise: input depth must be divisible by 4 * number of groups; error_component=GPU Runtime;"

I'm a little confused about the message's definition.

For that separable convolution layer: my input channel number is 1024, and the group num is 1024, too.

The output channel num of the depthwise convolution is 1536.

I don't quite get depth limitation described by the message.

Can someone help explaning it?

(my snpe version is 1.22.0.212)

  • Up0
  • Down0

Opinions expressed in the content posted here are the personal opinions of the original authors, and do not necessarily reflect those of Qualcomm Incorporated or its subsidiaries (“Qualcomm”). The content is provided for informational purposes only and is not meant to be an endorsement or representation by Qualcomm or any other party. This site may also provide links or references to non-Qualcomm sites and resources. Qualcomm makes no representations, warranties, or other commitments whatsoever about any non-Qualcomm sites or third-party resources that may be referenced, accessible from, or linked to this site.