Shunt Connection for Optimizing MobileNet-V2

Submitted: March 22, 2019 Last updated: March 22, 2019
  • File:
    student-ambassador-brijraj-singh-poster.pdf
  • Size:
    0.69 MB
Download

Detailed Description

Brijraj Singh

This work optimizes an already compressed pretrained model by using a residual connection to reduce the number of floating point operations. It locates blocks in a pretrained architecture that have a relatively lesser knowledge quotient and then bypasses those blocks through a Shunt connection. This connection combines an encoder and decoder and is relatively more optimized in terms of the number of parameters.

Product and Performance Information

1

Intel's compilers may or may not optimize to the same degree for non-Intel microprocessors for optimizations that are not unique to Intel microprocessors. These optimizations include SSE2, SSE3, and SSSE3 instruction sets and other optimizations. Intel does not guarantee the availability, functionality, or effectiveness of any optimization on microprocessors not manufactured by Intel. Microprocessor-dependent optimizations in this product are intended for use with Intel microprocessors. Certain optimizations not specific to Intel microarchitecture are reserved for Intel microprocessors. Please refer to the applicable product User and Reference Guides for more information regarding the specific instruction sets covered by this notice.

Notice revision #20110804