5 Commits

Author	SHA1	Message	Date
DefTruth	77cb9db6da	[Model] Support PP-ShiTuV2 models for PaddleClas (#1900) ... * [cmake] add faiss.cmake -> pp-shituv2 * [PP-ShiTuV2] Support PP-ShituV2-Det model * [PP-ShiTuV2] Support PP-ShiTuV2-Det model * [PP-ShiTuV2] Add PPShiTuV2Recognizer c++&python support * [PP-ShiTuV2] Add PPShiTuV2Recognizer c++&python support * [Bug Fix] fix ppshitu_pybind error * [benchmark] Add ppshituv2-det c++ benchmark * [examples] Add PP-ShiTuV2 det & rec examples * [vision] Update vision classification result * [Bug Fix] fix trt shapes setting errors	2023-05-08 14:04:09 +08:00
DefTruth	430fc424ac	[benchmark] optimize benchmark bin usage (#1868) ... * [benchmark] add disable_mkldnn option for paddle infer backend to support 3D model * [benchmark] optimize benchmark bin usage * [benchmark] optimize benchmark bin usage	2023-04-25 11:43:59 +08:00
DefTruth	37794d5f45	[benchmark] add disable_mkldnn option for paddle infer backend to support 3D model benchmark (#1866) ... [benchmark] add disable_mkldnn option for paddle infer backend to support 3D model	2023-04-25 10:43:08 +08:00
DefTruth	452885b089	[benchmark] fixed runtime benchmark bin macros bug (#1748) ... * [Benchmark] Add pure runtime benchmark bin * [Benchmark] add cpu/gpu memory collect -> benchmark bin * [Backend] update trt max_batch_size policy * [backend] Update trt backend max_batch_size policy * [Benchmark] Add more model format support -> benchmark bin * [benchmark] fixed runtime benchmark bin marcos bug	2023-03-30 21:08:38 +08:00
DefTruth	7d1b706caf	[Benchmark] Add pure runtime benchmark bin (#1731) ... * [Benchmark] Add pure runtime benchmark bin * [Benchmark] add cpu/gpu memory collect -> benchmark bin * [Backend] update trt max_batch_size policy * [backend] Update trt backend max_batch_size policy * [Benchmark] Add more model format support -> benchmark bin	2023-03-30 19:03:30 +08:00