Qualcomm Neural Processing SDK

Registration is required to post to the Forums. If you would like to post to the forum, you need to follow our Community and Posting Guidelines.

Discuss the Qualcomm Neural Processing SDK

Topic / Topic starter

Replies

Created

Last post

Normal topic

QNN-model-lib-generator missing compiler Paths/Installations

by ahmed.bingol31 Jan 24

by ahmed.bingol3 Mar 24

Normal topic

snpe-pytorch-to-dlc does not work with error ""NotImplementedError: "

by DONGYU.GWAK24 Jan 24

by DONGYU.GWAK29 Jan 24

Normal topic

qnn-net-run Device Creation failure

by g1o2n3g423 Jan 24

by qiang.tang26 Feb 24

Normal topic

qnn-net-run fail run with htp-v73

by mikebi21 Jan 24

by haocheng1.li29 Feb 24

Normal topic

llama2

by andy.linluo19 Jan 24

Normal topic

QNN optimization level O3 delivers lower performance than O2

by zhangq12 Jan 24

Normal topic

Porting Machine Learning Model onto Snapdragon

by greatbusinessman51711 Jan 24

Normal topic

SNPE UDO issue

by zhoubobo187 Jan 24

by alexandre.kutner22 Mar 24

Normal topic

SNPE model conversion issue

by zhoubobo185 Jan 24

Normal topic

The difference between SNPE and QNN

by zhoubobo185 Jan 24

Normal topic

QRB4210

by efi.golan3 Jan 24

by sanjjey.a.sanjjey29 Jan 24

Normal topic

Regarding object detection

by blessy.thomas2 Jan 24

Normal topic

Use DLC buffer to create tensor get error

by zhangjun14128 Dec 23

Normal topic

Why the total inference time of a model with Sigmoid activation layers is more than that of a model with Relu activation layers?

by lvarikuppala20 Dec 23

by lvarikuppala8 Jan 24

Normal topic

Compiling "Qualcomm Neural Processing SDK" for SA8295P

by kumar.kandasamy19 Dec 23

Normal topic

Hexagon version

by shuyw18 Dec 23

Normal topic

cross compiler binary

by shuyw18 Dec 23

Normal topic

Performance Setting for HTP Accelerator

by max.maung14 Dec 23

Normal topic

SNPE 2.16.0 on sm8650 yolov8 failed

by lhwywh12 Dec 23

Normal topic

Query Regarding User Buffer Encodings and Performance on DSP with SM8550 in LOW_POWER_SAVER Mode

by alona.rimon12 Dec 23

Normal topic

How to cross-compile InceptionV3 model for Qualcomm SA8650P board running aarch64-linux

by varun.gupta12 Dec 23

Normal topic

Can't understand why there's a difference between reported total inference time and the sum of per-layer computational times.

by lvarikuppala8 Dec 23

Normal topic

MaxPerGPUSize for Adreno 730

by yomalub4 Dec 23

Normal topic

Can't get all output tensor name in output tensor map

by yuris4 Dec 23

by yuris13 Dec 23

Normal topic

Android 12 - no runtimes available

by daniel.schopfhauser30 Nov 23

New posts
No new posts
Answer Available
Sticky Thread
Hot new posts
Hot posts

Pages

Sort By

Filter Results