Application Integration Tips

Upgrading Neural Network DLC Files

Qualcomm® Neural Processing SDK supports DLC files created from previous Qualcomm® Neural Processing SDK release (any release after 1.0). However, users experiencing issues when upgrading to a new Qualcomm® Neural Processing SDK release may want to try reconverting their model to DLC with the current release.

Upgrading To 1.16 and Later Releases From Older Versions

Qualcomm® Neural Processing SDK Release 1.16.0 introduces support for the batch dimension which requires some special attention. In older releases, if the source model contained a batch dimension, resulting in a 4D input tensor, the dimension was quietly ignored and the converted DLC would use a 3D input tensor in its place. From Release 1.16.0 onward, the batch dimension is honored and stored in the DLC.

For example, if a Tensorflow source model contains an input with dimensions {1,3,224,224}, older releases of Qualcomm® Neural Processing SDK would have converted this to an input with dimension {224,224,3}. In the newer releases, the converter creates an input with dimension {1,224,224,3}. The addition of the batch dimension will ripple all the way through to the end of the model, and the output tensor will also have a batch of 1 added to its dimensionality. This means that existing application code that assumes a 3D input tensor has to be updated to now assume a 4D tensor, when it is executed against a DLC file that was converted using the new release.

Additionally, if the source model contained the batch dimension with a non-unity extent, this extent is reflected in the DLC. For example, if our Tensorflow source model had an input with dimension {5,3,224,224}, older Qualcomm® Neural Processing SDK releases would have produced an input of {224,224,3}. But new releases create an input of dimension {5,224,224,3}. The application code using this model is now expected to give Qualcomm® Neural Processing SDK an input tensor with a size of 5x224x224x3 = 752,640 values.