* use mean as default for benchmark metric; change result representation;
add --all for benchmarking all configs at a time

* fix comments

* add --model_exclude

* pretty print

* improve benchmark result table header: from band-xpu to xpu-band

* suppress print message

* update benchmark results on CPU-RPI

* add the new benchmark results on the new intel cpu

* fix backend and target setting in benchmark; pre-modify the names of int8 quantized models

* add results on jetson cpu

* add cuda results

* print target and backend when using --all

* add results on Khadas VIM3

* pretty print results

* true pretty print results

* update results in new format

* fix broken backend and target vars

* fix broken backend and target vars

* fix broken backend and target var

* update benchmark results on many devices

* add db results on Ascend-310

* update info on CPU-INTEL

* update usage of the new benchmark script

* update benchmark and results

* update lpd_yunet & nanodet benchmark results

* update results for PP-HumanSeg, MobileNet-V2, MP-HandPose

* add some notes

* update handpose model

* update quantize model

* fix quantize path

* update readme of quantization and benchmark result

* fix document

* update to the latest palm detection model

* quantize palm detection model

* make palm aligned to center when resize

* update benchmark for palm detection

* update benchmark data

* update readme

* update a new quantized model

* update readme

* update document and fix bugs

* re-quantized model to per_tensor mode

* update KV3-NPU benchmark result

* re-quantize some models from per_channel mode to per_tensor mode

* remove the description about per_channel

Improved help messages for demo programs (#95)
- Added Demo Documentation
- Updated help messages
- Changed exception link

* addDBfrontpage

* add English DB

* change readme

* change two readme and replace images

* add demo images

* add demo to readme

* add lpd_yunet

* add quantization and quantized model

* quantize with inc instead

* update benchmark results

* add backend TIMVX & target NPU

* update benchmarking results on Khadas VIM3 NPU

* fix wrong column header

* update readme

* re-order column KV3-NPU

* re-order KV3-NPU specs line

* add additional description regarding TIM-VX backend and NPU target for OpenCV DNN

* add (ms) to each hardware header

* add a argument for label path

* correct filenames for face detection

* add a download link for face recognition data

* fix path to face recognition data

* correct shasum for face_detection.zip

* fix filename for person_reid benchmark data package

* add benchmark results of YuNet on D1

* add a link for tutorial of benchmarking on D1-CPU

* improve description

* improve hardware namings

* remove extra parentheses

* workable wrapper and demo (demo without visualization)

* add visualization for demo

* impl benchmark for YoutuReID

* update benchmark results on x86_64, arm and cuda

* add charsets and CRNN_CN

* workable wrapper and demo for CRNN_CN

* update README with CRNN_CN; rename models with EN/CN suffix

* impl benchmarks for CRNN_EN and CRNN_CN

* update benchmark result on arm

* update benchmark results on x86_64 & cuda

Make it easier to see benchmark results

* impl wrapper & demo

* add data for object tracking benchmark

* impl benchmark for DaSiamRPN

* update benchmark results for DaSiamRPN

* add qrcode detector and parser from wechat

* add a link to download qrcode data

* add model

* add visualize

* imporve visualize in demo

* benchmark impl

* update benchmark results for wechatqrcode

* update readme

* correct upload time

* add suffix of training dataset, arch & upload time to each model

* update DB-IC15 benchmark results

* update benchmark results on Jetson Nano

* update YuNet and SFace impl with opencv-python api

* add PPHumanSeg impl and demo

* add benchmark impl and results for PPHumanSeg

* add PPResNet impl and demo

* add benchmark impl and results for PPResNet