search

intel / nn-hal

44 stars 51 forks source link

Remove extra Transpose layers from the generated graph #152

Open Rjasuja opened 2 years ago

Rjasuja commented 2 years ago

Tranpose layers are added to every operator's input and output if layout is NHWC Instead it should be added only at the beginning and end of the graph

Signed-off-by: Ritul Jasuja ritul.jasuja@intel.com

Nagamani71 commented 2 years ago

@Rjasuja could you please rebase the PR. It has "001-Add-Float16-support-for-Resize-Bilinear-and-Resize-N.patch" patch. Also, could you please check below mentioned VTS test cases TestGenerated/GeneratedTest#Test mobilenet_quantized, mobilenet_224_gender_basic_fixed Or verify changes with any object detection application

I think your changes will fail to reshape the tensor when model has multiple convolution nodes. (I could be wrong, i am unable to apply your patch and verify the changes)