Forums - Failed to convert my caffemodel to DLC

6 posts / 0 new
Last post
Failed to convert my caffemodel to DLC
yangfan34
Join Date: 6 Dec 17
Posts: 9
Posted: Thu, 2018-05-17 00:04

Hi guys,

Now I run all examples in SNPE very well. But I got failed when trying to port  my  caffemodel on PC to snapdragon device.

I successfully trained this model (https://github.com/weiliu89/caffe.git  (refs/heads/ssd)) on PC and tried to convert its deploy.prototxt and caffemodel into DLC file.

$SNPE_ROOT/bin/x86_64-linux-clang/snpe-caffe-to-dlc --caffe_txt $SNPE_ROOT/models/alexnet/ssd_data/deploy.prototxt --caffe_bin $SNPE_ROOT/models/alexnet/ssd_data/VGG_VOC0712_SSD_700x700_iter_32800.caffemodel --dlc ssd_data/vgg_ssd_alexnet.dlc
 
----error output----
/home/yangfan34/workspace/lenovo/qualcomm/snpe-1.15.0/lib/python/snpe/snpe_caffe_to_dlc.py:1567: RuntimeWarning: error_code=902; error_message=Layer parameter value is invalid in DSP. Layer conv4_3_norm: InstanceNorm (dynamic statistics calculation in BatchNorm) scale must be 1.0 on DSP runtime.; error_component=DSP Runtime; line_no=136; thread_id=139683607803712
  output_name = str(self.get_output_name(layer)))
/home/yangfan34/workspace/lenovo/qualcomm/snpe-1.15.0/lib/python/snpe/snpe_caffe_to_dlc.py:2388: RuntimeWarning: error_code=1000; error_message=Layer is not supported. Layer detection_out of type SsdDetectionOutput not supported by GPU runtime; error_component=Model Validation; line_no=257; thread_id=139683607803712
  confidence_threshold=params.confidence_threshold)
 
There is no DLC file generated in ssd_data dir. Does the error  mean these two layers (conv4_3_norm and detection_out) should be removed? Hope your feedback.
 
Cheers,
Yangfan
 
  • Up0
  • Down0
yangfan34
Join Date: 6 Dec 17
Posts: 9
Posted: Thu, 2018-05-17 00:39

Hi, 

Layer detection_out is defined by SSD itself and we can skip it.

Layer conv4_3_norm seems a standard layer in Caffe. Can I know which version is supported by SNPE 1.15.0? 

 

Cheers,

Yangfan

  • Up0
  • Down0
sgiri1
Join Date: 18 Jun 18
Posts: 2
Posted: Thu, 2018-06-21 16:08

Hi,

I had the exact same issue. Did you manage to resolve it?

  • Up0
  • Down0
sgiri1
Join Date: 18 Jun 18
Posts: 2
Posted: Thu, 2018-06-21 16:08

Hi,

I had the exact same issue. Did you manage to resolve it?

  • Up0
  • Down0
yangfan34
Join Date: 6 Dec 17
Posts: 9
Posted: Sun, 2018-06-24 19:15

Not yet.

  • Up0
  • Down0
Jacob_Ke
Join Date: 24 Aug 17
Posts: 10
Posted: Wed, 2018-07-04 00:38

Hi yangfan34,

I have the same error with layer detection_out

how do you skip it? 

Thanks

  • Up0
  • Down0
or Register

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.