[Benchmark] Open collect_info in config (#1649)

* add GPL lisence

* add GPL-3.0 lisence

* add GPL-3.0 lisence

* add GPL-3.0 lisence

* support yolov8

* add pybind for yolov8

* add yolov8 readme

* add cpp benchmark

* add cpu and gpu mem

* public part split

* add runtime mode

* fixed bugs

* add cpu_thread_nums

* deal with comments

* deal with comments

* deal with comments

* rm useless code

* add FASTDEPLOY_DECL

* add FASTDEPLOY_DECL

* fixed for windows

* mv rss to pss

* mv rss to pss

* Update utils.cc

* use thread to collect mem

* Add ResourceUsageMonitor

* rm useless code

* fixed bug

* fixed typo

* update ResourceUsageMonitor

* fixed bug

* fixed bug

* add note for ResourceUsageMonitor

* deal with comments

* add macros

* deal with comments

* deal with comments

* deal with comments

* re-lint

* rm pmap and use mem api

* rm pmap and use mem api

* add mem api

* Add PrintBenchmarkInfo func

* Add PrintBenchmarkInfo func

* Add PrintBenchmarkInfo func

* deal with comments

* fixed enable_paddle_to_trt

* add log for paddle_trt

* support ppcls benchmark

* use new trt option api

* update benchmark info

* simplify benchmark.cc

* simplify benchmark.cc

* deal with comments

* Add ppseg && ppocr benchmark

* add OCR rec img

* add ocr benchmark

* fixed trt shape

* add trt shape

* resolve conflict

* add ENABLE_BENCHMARK define

* Add ClassifyDiff

* Add Resize for ClassifyResult

* deal with comments

* add convert info script

* resolve conflict

* Add SaveBenchmarkResult func

* fixed bug

* fixed bug

* fixed bug

* add config.txt for option

* fixed bug

* fixed bug

* fixed bug

* add benchmark.sh

* mv thread_nums from 8 to 1

* deal with comments

* deal with comments

* fixed readme

* deal with comments

* add all platform shell

* Update config.arm.txt

* Update config.gpu.txt

* Update config.x86.txt

* fixed printinfo bug

* rm proxy

* add more model support

* all backend config.txt

* deal with comments

* Add MattingDiff compare

* fixed predict bug

* adjust warmup/repeat times

* add e2e/mem configs

* fixed typo

* open collect_mem

---------

Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>

benchmark/cpp/config/config.gpu.ort.fp32.e2e.mem.txt

@@ -2,12 +2,12 @@ device: gpu
 device_id: 3
 cpu_thread_nums: 1
 warmup: 10
-repeat: 20
+repeat: 50
 backend: ort
 profile_mode: end2end
 include_h2d_d2h: false
 use_fp16: false
-collect_memory_info: false
+collect_memory_info: true
 sampling_interval: 1
 precision_compare: false
 xpu_l3_cache: 0

benchmark/cpp/config/config.gpu.paddle.fp32.e2e.mem.txt

@@ -2,12 +2,12 @@ device: gpu
 device_id: 3
 cpu_thread_nums: 1
 warmup: 10
-repeat: 20
+repeat: 50
 backend: paddle
 profile_mode: end2end
 include_h2d_d2h: false
 use_fp16: false
-collect_memory_info: false
+collect_memory_info: true
 sampling_interval: 1
 precision_compare: false
 xpu_l3_cache: 0

benchmark/cpp/config/config.gpu.paddle_trt.fp16.e2e.mem.txt

@@ -2,12 +2,12 @@ device: gpu
 device_id: 3
 cpu_thread_nums: 1
 warmup: 10
-repeat: 20
+repeat: 50
 backend: paddle_trt
 profile_mode: end2end
 include_h2d_d2h: false
 use_fp16: true
-collect_memory_info: false
+collect_memory_info: true
 sampling_interval: 1
 precision_compare: false
 xpu_l3_cache: 0

benchmark/cpp/config/config.gpu.paddle_trt.fp32.e2e.mem.txt

@@ -2,12 +2,12 @@ device: gpu
 device_id: 3
 cpu_thread_nums: 1
 warmup: 10
-repeat: 20
+repeat: 50
 backend: paddle_trt
 profile_mode: end2end
 include_h2d_d2h: false
 use_fp16: false
-collect_memory_info: false
+collect_memory_info: true
 sampling_interval: 1
 precision_compare: false
 xpu_l3_cache: 0

benchmark/cpp/config/config.gpu.trt.fp16.e2e.mem.txt

@@ -2,12 +2,12 @@ device: gpu
 device_id: 3
 cpu_thread_nums: 1
 warmup: 10
-repeat: 20
+repeat: 50
 backend: trt
 profile_mode: end2end
 include_h2d_d2h: false
 use_fp16: true
-collect_memory_info: false
+collect_memory_info: true
 sampling_interval: 1
 precision_compare: false
 xpu_l3_cache: 0

benchmark/cpp/config/config.gpu.trt.fp32.e2e.mem.txt

@@ -2,12 +2,12 @@ device: gpu
 device_id: 3
 cpu_thread_nums: 1
 warmup: 10
-repeat: 20
+repeat: 50
 backend: trt
 profile_mode: end2end
 include_h2d_d2h: false
 use_fp16: false
-collect_memory_info: false
+collect_memory_info: true
 sampling_interval: 1
 precision_compare: false
 xpu_l3_cache: 0

benchmark/cpp/config/config.x86.ort.fp32.e2e.mem.txt

@@ -2,12 +2,12 @@ device: cpu
 device_id: 0
 cpu_thread_nums: 1
 warmup: 10
-repeat: 20
+repeat: 50
 backend: ort
 profile_mode: end2end
 include_h2d_d2h: false
 use_fp16: false
-collect_memory_info: false
+collect_memory_info: true
 sampling_interval: 1
 precision_compare: false
 xpu_l3_cache: 0

benchmark/cpp/config/config.x86.ov.fp32.e2e.mem.txt

@@ -2,12 +2,12 @@ device: cpu
 device_id: 0
 cpu_thread_nums: 1
 warmup: 10
-repeat: 20
+repeat: 50
 backend: ov
 profile_mode: end2end
 include_h2d_d2h: false
 use_fp16: false
-collect_memory_info: false
+collect_memory_info: true
 sampling_interval: 1
 precision_compare: false
 xpu_l3_cache: 0

benchmark/cpp/config/config.x86.paddle.fp32.e2e.mem.txt

@@ -2,12 +2,12 @@ device: cpu
 device_id: 0
 cpu_thread_nums: 1
 warmup: 10
-repeat: 20
+repeat: 50
 backend: paddle
 profile_mode: end2end
 include_h2d_d2h: false
 use_fp16: false
-collect_memory_info: false
+collect_memory_info: true
 sampling_interval: 1
 precision_compare: false
 xpu_l3_cache: 0

benchmark/cpp/config/config.xpu.lite.fp32.e2e.mem.txt

@@ -7,7 +7,7 @@ backend: lite
 profile_mode: end2end
 include_h2d_d2h: false
 use_fp16: false
-collect_memory_info: false
+collect_memory_info: true
 sampling_interval: 1
 precision_compare: false
 xpu_l3_cache: 0