mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-10-06 00:57:33 +08:00
d522ef28b4
* 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 * fixed typo * add trt cache option * fixed bug * fixed repeat times --------- Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
26 lines
1.7 KiB
Bash
Executable File
26 lines
1.7 KiB
Bash
Executable File
# Download and decompress the ERNIE 3.0 Medium model finetuned on AFQMC
|
|
# wget https://bj.bcebos.com/fastdeploy/models/ernie-3.0/ernie-3.0-medium-zh-afqmc.tgz
|
|
# tar xvfz ernie-3.0-medium-zh-afqmc.tgz
|
|
|
|
# Download and decompress the quantization model of ERNIE 3.0 Medium model
|
|
# wget https://bj.bcebos.com/fastdeploy/models/ernie-3.0/ernie-3.0-medium-zh-afqmc-new-quant.tgz
|
|
# tar xvfz ernie-3.0-medium-zh-afqmc-new-quant.tgz
|
|
|
|
# PP-TRT
|
|
python benchmark_ernie_seq_cls.py --batch_size 40 --model_dir ernie-3.0-medium-zh-afqmc --backend pp-trt
|
|
python benchmark_ernie_seq_cls.py --batch_size 40 --model_dir ernie-3.0-medium-zh-afqmc --backend pp-trt --use_fp16 True
|
|
python benchmark_ernie_seq_cls.py --batch_size 40 --model_dir ernie-3.0-medium-zh-afqmc-new-quant --backend pp-trt
|
|
|
|
# TRT
|
|
python benchmark_ernie_seq_cls.py --batch_size 40 --model_dir ernie-3.0-medium-zh-afqmc --backend trt
|
|
python benchmark_ernie_seq_cls.py --batch_size 40 --model_dir ernie-3.0-medium-zh-afqmc --backend trt --use_fp16 True
|
|
python benchmark_ernie_seq_cls.py --batch_size 40 --model_dir ernie-3.0-medium-zh-afqmc-new-quant --backend trt --use_fp16 True
|
|
|
|
# CPU PP
|
|
python benchmark_ernie_seq_cls.py --batch_size 40 --cpu_num_threads 10 --model_dir ernie-3.0-medium-zh-afqmc --backend pp --device cpu
|
|
python benchmark_ernie_seq_cls.py --batch_size 40 --cpu_num_threads 10 --model_dir ernie-3.0-medium-zh-afqmc-new-quant --backend pp --device cpu
|
|
|
|
# CPU ORT
|
|
python benchmark_ernie_seq_cls.py --batch_size 40 --cpu_num_threads 10 --model_dir ernie-3.0-medium-zh-afqmc --backend ort --device cpu
|
|
python benchmark_ernie_seq_cls.py --batch_size 40 --cpu_num_threads 10 --model_dir ernie-3.0-medium-zh-afqmc-new-quant --backend ort --device cpu
|