Skip to content
体验新版
项目
组织
正在加载...
登录
切换导航
打开侧边栏
PaddlePaddle
PaddleClas
提交
e77ba41e
P
PaddleClas
项目概览
PaddlePaddle
/
PaddleClas
大约 1 年 前同步成功
通知
115
Star
4999
Fork
1114
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
19
列表
看板
标记
里程碑
合并请求
6
Wiki
0
Wiki
分析
仓库
DevOps
项目成员
Pages
P
PaddleClas
项目概览
项目概览
详情
发布
仓库
仓库
文件
提交
分支
标签
贡献者
分支图
比较
Issue
19
Issue
19
列表
看板
标记
里程碑
合并请求
6
合并请求
6
Pages
分析
分析
仓库分析
DevOps
Wiki
0
Wiki
成员
成员
收起侧边栏
关闭侧边栏
动态
分支图
创建新Issue
提交
Issue看板
提交
e77ba41e
编写于
6月 22, 2022
作者:
H
HydrogenSulfate
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
fix GPUID setting and LOG_PATH
上级
9f1ec3a5
变更
29
隐藏空白更改
内联
并排
Showing
29 changed file
with
318 addition
and
72 deletion
+318
-72
deploy/slim/quant_post_static.py
deploy/slim/quant_post_static.py
+2
-0
docs/images/PP-HGNet/PP-HGNet-block.png
docs/images/PP-HGNet/PP-HGNet-block.png
+0
-0
test_tipc/config/MobileNetV3/MobileNetV3_large_x1_0_KL_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
..._0_KL_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
+0
-0
test_tipc/config/MobileNetV3/MobileNetV3_large_x1_0_KL_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
..._KL_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
+0
-0
test_tipc/config/MobileNetV3/MobileNetV3_large_x1_0_KL_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
..._linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
+0
-0
test_tipc/config/PP-ShiTu/PPShiTu_general_rec_KL_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
...ec_KL_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
+18
-0
test_tipc/config/PP-ShiTu/PPShiTu_general_rec_KL_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
..._KL_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
+14
-0
test_tipc/config/PP-ShiTu/PPShiTu_general_rec_KL_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
..._linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
+14
-0
test_tipc/config/PPHGNet/PPHGNet_small_KL_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
...ll_KL_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
+18
-0
test_tipc/config/PPHGNet/PPHGNet_small_KL_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
..._KL_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
+14
-0
test_tipc/config/PPHGNet/PPHGNet_small_KL_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
..._linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
+14
-0
test_tipc/config/PPLCNet/PPLCNet_x1_0_KL_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
..._0_KL_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
+18
-0
test_tipc/config/PPLCNet/PPLCNet_x1_0_KL_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
..._KL_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
+14
-0
test_tipc/config/PPLCNet/PPLCNet_x1_0_KL_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
..._linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
+14
-0
test_tipc/config/PPLCNetV2/PPLCNetV2_base_KL_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
...se_KL_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
+18
-0
test_tipc/config/PPLCNetV2/PPLCNetV2_base_KL_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
..._KL_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
+14
-0
test_tipc/config/PPLCNetV2/PPLCNetV2_base_KL_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
..._linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
+14
-0
test_tipc/config/ResNet/ResNet50_vd_KL_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
...vd_KL_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
+0
-0
test_tipc/config/ResNet/ResNet50_vd_KL_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
..._KL_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
+0
-0
test_tipc/config/ResNet/ResNet50_vd_KL_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
..._linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
+0
-0
test_tipc/config/SwinTransformer/SwinTransformer_tiny_patch4_window7_224_KL_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
...24_KL_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
+18
-0
test_tipc/config/SwinTransformer/SwinTransformer_tiny_patch4_window7_224_KL_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
..._KL_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
+14
-0
test_tipc/config/SwinTransformer/SwinTransformer_tiny_patch4_window7_224_KL_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
..._linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
+14
-0
test_tipc/docs/test_inference_cpp.md
test_tipc/docs/test_inference_cpp.md
+30
-26
test_tipc/docs/test_serving_infer_cpp.md
test_tipc/docs/test_serving_infer_cpp.md
+25
-20
test_tipc/docs/test_serving_infer_python.md
test_tipc/docs/test_serving_infer_python.md
+25
-20
test_tipc/prepare.sh
test_tipc/prepare.sh
+1
-1
test_tipc/test_inference_cpp.sh
test_tipc/test_inference_cpp.sh
+4
-4
test_tipc/test_serving_infer_python.sh
test_tipc/test_serving_infer_python.sh
+1
-1
未找到文件。
deploy/slim/quant_post_static.py
浏览文件 @
e77ba41e
...
...
@@ -41,6 +41,8 @@ def main():
'inference.pdmodel'
))
and
os
.
path
.
exists
(
os
.
path
.
join
(
config
[
"Global"
][
"save_inference_dir"
],
'inference.pdiparams'
))
if
"Query"
in
config
[
"DataLoader"
][
"Eval"
]:
config
[
"DataLoader"
][
"Eval"
]
=
config
[
"DataLoader"
][
"Eval"
][
"Query"
]
config
[
"DataLoader"
][
"Eval"
][
"sampler"
][
"batch_size"
]
=
1
config
[
"DataLoader"
][
"Eval"
][
"loader"
][
"num_workers"
]
=
0
...
...
docs/images/PP-HGNet/PP-HGNet-block.png
查看替换文件 @
9f1ec3a5
浏览文件 @
e77ba41e
104.2 KB
|
W:
|
H:
405.7 KB
|
W:
|
H:
2-up
Swipe
Onion skin
test_tipc/config/MobileNetV3/MobileNetV3_large_x1_0
-
KL_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
→
test_tipc/config/MobileNetV3/MobileNetV3_large_x1_0
_
KL_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
浏览文件 @
e77ba41e
文件已移动
test_tipc/config/MobileNetV3/MobileNetV3_large_x1_0
-
KL_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
→
test_tipc/config/MobileNetV3/MobileNetV3_large_x1_0
_
KL_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
浏览文件 @
e77ba41e
文件已移动
test_tipc/config/MobileNetV3/MobileNetV3_large_x1_0
-
KL_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
→
test_tipc/config/MobileNetV3/MobileNetV3_large_x1_0
_
KL_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
浏览文件 @
e77ba41e
文件已移动
test_tipc/config/PP-ShiTu/PPShiTu_general_rec_KL_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
0 → 100644
浏览文件 @
e77ba41e
===========================cpp_infer_params===========================
model_name:GeneralRecognition_PPLCNet_x2_5_KL
cpp_infer_type:cls
cls_inference_model_dir:./general_PPLCNet_x2_5_lite_v1.0_kl_quant_infer/
det_inference_model_dir:
cls_inference_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/inference/slim_model/general_PPLCNet_x2_5_lite_v1.0_kl_quant_infer.tar
det_inference_url:
infer_quant:False
inference_cmd:./deploy/cpp/build/clas_system -c inference_cls.yaml
use_gpu:True|False
enable_mkldnn:False
cpu_threads:1
batch_size:1
use_tensorrt:False
precision:fp32
image_dir:./dataset/ILSVRC2012/val/ILSVRC2012_val_00000001.JPEG
benchmark:False
generate_yaml_cmd:python3.7 test_tipc/generate_cpp_yaml.py
test_tipc/config/PP-ShiTu/PPShiTu_general_rec_KL_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
0 → 100644
浏览文件 @
e77ba41e
===========================serving_params===========================
model_name:GeneralRecognition_PPLCNet_x2_5_KL
python:python3.7
inference_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/inference/slim_model/general_PPLCNet_x2_5_lite_v1.0_kl_quant_infer.tar
trans_model:-m paddle_serving_client.convert
--dirname:./deploy/paddleserving/general_PPLCNet_x2_5_lite_v1.0_kl_quant_infer/
--model_filename:inference.pdmodel
--params_filename:inference.pdiparams
--serving_server:./deploy/paddleserving/GeneralRecognition_PPLCNet_x2_5_kl_quant_serving/
--serving_client:./deploy/paddleserving/GeneralRecognition_PPLCNet_x2_5_kl_quant_client/
serving_dir:./deploy/paddleserving
web_service:null
--use_gpu:0|null
pipline:test_cpp_serving_client.py
test_tipc/config/PP-ShiTu/PPShiTu_general_rec_KL_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
0 → 100644
浏览文件 @
e77ba41e
===========================serving_params===========================
model_name:GeneralRecognition_PPLCNet_x2_5_KL
python:python3.7
inference_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/inference/slim_model/general_PPLCNet_x2_5_lite_v1.0_kl_quant_infer.tar
trans_model:-m paddle_serving_client.convert
--dirname:./deploy/paddleserving/general_PPLCNet_x2_5_lite_v1.0_kl_quant_infer/
--model_filename:inference.pdmodel
--params_filename:inference.pdiparams
--serving_server:./deploy/paddleserving/GeneralRecognition_PPLCNet_x2_5_kl_quant_serving/
--serving_client:./deploy/paddleserving/GeneralRecognition_PPLCNet_x2_5_kl_quant_client/
serving_dir:./deploy/paddleserving
web_service:classification_web_service.py
--use_gpu:0|null
pipline:pipeline_http_client.py
test_tipc/config/PPHGNet/PPHGNet_small_KL_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
0 → 100644
浏览文件 @
e77ba41e
===========================cpp_infer_params===========================
model_name:PPHGNet_small_KL
cpp_infer_type:cls
cls_inference_model_dir:./PPHGNet_small_kl_quant_infer/
det_inference_model_dir:
cls_inference_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/inference/slim_model/PPHGNet_small_kl_quant_infer.tar
det_inference_url:
infer_quant:False
inference_cmd:./deploy/cpp/build/clas_system -c inference_cls.yaml
use_gpu:True|False
enable_mkldnn:False
cpu_threads:1
batch_size:1
use_tensorrt:False
precision:fp32
image_dir:./dataset/ILSVRC2012/val/ILSVRC2012_val_00000001.JPEG
benchmark:False
generate_yaml_cmd:python3.7 test_tipc/generate_cpp_yaml.py
test_tipc/config/PPHGNet/PPHGNet_small_KL_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
0 → 100644
浏览文件 @
e77ba41e
===========================serving_params===========================
model_name:PPHGNet_small_KL
python:python3.7
inference_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/inference/slim_model/PPHGNet_small_kl_quant_infer.tar
trans_model:-m paddle_serving_client.convert
--dirname:./deploy/paddleserving/PPHGNet_small_kl_quant_infer/
--model_filename:inference.pdmodel
--params_filename:inference.pdiparams
--serving_server:./deploy/paddleserving/PPHGNet_small_kl_quant_serving/
--serving_client:./deploy/paddleserving/PPHGNet_small_kl_quant_client/
serving_dir:./deploy/paddleserving
web_service:null
--use_gpu:0|null
pipline:test_cpp_serving_client.py
test_tipc/config/PPHGNet/PPHGNet_small_KL_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
0 → 100644
浏览文件 @
e77ba41e
===========================serving_params===========================
model_name:PPHGNet_small_KL
python:python3.7
inference_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/inference/slim_model/PPHGNet_small_kl_quant_infer.tar
trans_model:-m paddle_serving_client.convert
--dirname:./deploy/paddleserving/PPHGNet_small_kl_quant_infer/
--model_filename:inference.pdmodel
--params_filename:inference.pdiparams
--serving_server:./deploy/paddleserving/PPHGNet_small_kl_quant_serving/
--serving_client:./deploy/paddleserving/PPHGNet_small_kl_quant_client/
serving_dir:./deploy/paddleserving
web_service:classification_web_service.py
--use_gpu:0|null
pipline:pipeline_http_client.py
test_tipc/config/PPLCNet/PPLCNet_x1_0_KL_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
0 → 100644
浏览文件 @
e77ba41e
===========================cpp_infer_params===========================
model_name:PPLCNet_x1_0_KL
cpp_infer_type:cls
cls_inference_model_dir:./PPLCNet_x1_0_kl_quant_infer/
det_inference_model_dir:
cls_inference_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/inference/slim_model/PPLCNet_x1_0_kl_quant_infer.tar
det_inference_url:
infer_quant:False
inference_cmd:./deploy/cpp/build/clas_system -c inference_cls.yaml
use_gpu:True|False
enable_mkldnn:False
cpu_threads:1
batch_size:1
use_tensorrt:False
precision:fp32
image_dir:./dataset/ILSVRC2012/val/ILSVRC2012_val_00000001.JPEG
benchmark:False
generate_yaml_cmd:python3.7 test_tipc/generate_cpp_yaml.py
test_tipc/config/PPLCNet/PPLCNet_x1_0_KL_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
0 → 100644
浏览文件 @
e77ba41e
===========================serving_params===========================
model_name:PPLCNet_x1_0_KL
python:python3.7
inference_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/inference/slim_model/PPLCNet_x1_0_kl_quant_infer.tar
trans_model:-m paddle_serving_client.convert
--dirname:./deploy/paddleserving/PPLCNet_x1_0_kl_quant_infer/
--model_filename:inference.pdmodel
--params_filename:inference.pdiparams
--serving_server:./deploy/paddleserving/PPLCNet_x1_0_kl_quant_serving/
--serving_client:./deploy/paddleserving/PPLCNet_x1_0_kl_quant_client/
serving_dir:./deploy/paddleserving
web_service:null
--use_gpu:0|null
pipline:test_cpp_serving_client.py
test_tipc/config/PPLCNet/PPLCNet_x1_0_KL_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
0 → 100644
浏览文件 @
e77ba41e
===========================serving_params===========================
model_name:PPLCNet_x1_0_KL
python:python3.7
inference_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/inference/slim_model/PPLCNet_x1_0_kl_quant_infer.tar
trans_model:-m paddle_serving_client.convert
--dirname:./deploy/paddleserving/PPLCNet_x1_0_kl_quant_infer/
--model_filename:inference.pdmodel
--params_filename:inference.pdiparams
--serving_server:./deploy/paddleserving/PPLCNet_x1_0_kl_quant_serving/
--serving_client:./deploy/paddleserving/PPLCNet_x1_0_kl_quant_client/
serving_dir:./deploy/paddleserving
web_service:classification_web_service.py
--use_gpu:0|null
pipline:pipeline_http_client.py
test_tipc/config/PPLCNetV2/PPLCNetV2_base_KL_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
0 → 100644
浏览文件 @
e77ba41e
===========================cpp_infer_params===========================
model_name:PPLCNetV2_base_KL
cpp_infer_type:cls
cls_inference_model_dir:./PPLCNetV2_base_kl_quant_infer/
det_inference_model_dir:
cls_inference_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/inference/slim_model/PPLCNetV2_base_kl_quant_infer.tar
det_inference_url:
infer_quant:False
inference_cmd:./deploy/cpp/build/clas_system -c inference_cls.yaml
use_gpu:True|False
enable_mkldnn:False
cpu_threads:1
batch_size:1
use_tensorrt:False
precision:fp32
image_dir:./dataset/ILSVRC2012/val/ILSVRC2012_val_00000001.JPEG
benchmark:False
generate_yaml_cmd:python3.7 test_tipc/generate_cpp_yaml.py
test_tipc/config/PPLCNetV2/PPLCNetV2_base_KL_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
0 → 100644
浏览文件 @
e77ba41e
===========================serving_params===========================
model_name:PPLCNetV2_base_KL
python:python3.7
inference_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/inference/slim_model/PPLCNetV2_base_kl_quant_infer.tar
trans_model:-m paddle_serving_client.convert
--dirname:./deploy/paddleserving/PPLCNetV2_base_kl_quant_infer/
--model_filename:inference.pdmodel
--params_filename:inference.pdiparams
--serving_server:./deploy/paddleserving/PPLCNetV2_base_kl_quant_serving/
--serving_client:./deploy/paddleserving/PPLCNetV2_base_kl_quant_client/
serving_dir:./deploy/paddleserving
web_service:null
--use_gpu:0|null
pipline:test_cpp_serving_client.py
test_tipc/config/PPLCNetV2/PPLCNetV2_base_KL_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
0 → 100644
浏览文件 @
e77ba41e
===========================serving_params===========================
model_name:PPLCNetV2_base_KL
python:python3.7
inference_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/inference/slim_model/PPLCNetV2_base_kl_quant_infer.tar
trans_model:-m paddle_serving_client.convert
--dirname:./deploy/paddleserving/PPLCNetV2_base_kl_quant_infer/
--model_filename:inference.pdmodel
--params_filename:inference.pdiparams
--serving_server:./deploy/paddleserving/PPLCNetV2_base_kl_quant_serving/
--serving_client:./deploy/paddleserving/PPLCNetV2_base_kl_quant_client/
serving_dir:./deploy/paddleserving
web_service:classification_web_service.py
--use_gpu:0|null
pipline:pipeline_http_client.py
test_tipc/config/ResNet/ResNet50_vd
-
KL_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
→
test_tipc/config/ResNet/ResNet50_vd
_
KL_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
浏览文件 @
e77ba41e
文件已移动
test_tipc/config/ResNet/ResNet50_vd
-
KL_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
→
test_tipc/config/ResNet/ResNet50_vd
_
KL_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
浏览文件 @
e77ba41e
文件已移动
test_tipc/config/ResNet/ResNet50_vd
-
KL_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
→
test_tipc/config/ResNet/ResNet50_vd
_
KL_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
浏览文件 @
e77ba41e
文件已移动
test_tipc/config/SwinTransformer/SwinTransformer_tiny_patch4_window7_224_KL_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
0 → 100644
浏览文件 @
e77ba41e
===========================cpp_infer_params===========================
model_name:SwinTransformer_tiny_patch4_window7_224_KL
cpp_infer_type:cls
cls_inference_model_dir:./SwinTransformer_tiny_patch4_window7_224_kl_quant_infer/
det_inference_model_dir:
cls_inference_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/inference/slim_model/SwinTransformer_tiny_patch4_window7_224_kl_quant_infer.tar
det_inference_url:
infer_quant:False
inference_cmd:./deploy/cpp/build/clas_system -c inference_cls.yaml
use_gpu:True|False
enable_mkldnn:False
cpu_threads:1
batch_size:1
use_tensorrt:False
precision:fp32
image_dir:./dataset/ILSVRC2012/val/ILSVRC2012_val_00000001.JPEG
benchmark:False
generate_yaml_cmd:python3.7 test_tipc/generate_cpp_yaml.py
test_tipc/config/SwinTransformer/SwinTransformer_tiny_patch4_window7_224_KL_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
0 → 100644
浏览文件 @
e77ba41e
===========================serving_params===========================
model_name:SwinTransformer_tiny_patch4_window7_224_KL
python:python3.7
inference_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/inference/slim_model/SwinTransformer_tiny_patch4_window7_224_kl_quant_infer.tar
trans_model:-m paddle_serving_client.convert
--dirname:./deploy/paddleserving/SwinTransformer_tiny_patch4_window7_224_kl_quant_infer/
--model_filename:inference.pdmodel
--params_filename:inference.pdiparams
--serving_server:./deploy/paddleserving/SwinTransformer_tiny_patch4_window7_224_kl_quant_serving/
--serving_client:./deploy/paddleserving/SwinTransformer_tiny_patch4_window7_224_kl_quant_client/
serving_dir:./deploy/paddleserving
web_service:null
--use_gpu:0|null
pipline:test_cpp_serving_client.py
test_tipc/config/SwinTransformer/SwinTransformer_tiny_patch4_window7_224_KL_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
0 → 100644
浏览文件 @
e77ba41e
===========================serving_params===========================
model_name:SwinTransformer_tiny_patch4_window7_224_KL
python:python3.7
inference_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/inference/slim_model/SwinTransformer_tiny_patch4_window7_224_kl_quant_infer.tar
trans_model:-m paddle_serving_client.convert
--dirname:./deploy/paddleserving/SwinTransformer_tiny_patch4_window7_224_kl_quant_infer/
--model_filename:inference.pdmodel
--params_filename:inference.pdiparams
--serving_server:./deploy/paddleserving/SwinTransformer_tiny_patch4_window7_224_kl_quant_serving/
--serving_client:./deploy/paddleserving/SwinTransformer_tiny_patch4_window7_224_kl_quant_client/
serving_dir:./deploy/paddleserving
web_service:classification_web_service.py
--use_gpu:0|null
pipline:pipeline_http_client.py
test_tipc/docs/test_inference_cpp.md
浏览文件 @
e77ba41e
...
...
@@ -6,27 +6,31 @@ Linux GPU/CPU C++ 推理功能测试的主程序为`test_inference_cpp.sh`,可
-
推理相关:
| 算法名称 | 模型名称 | device_CPU | device_GPU |
| :-------------: | :---------------------------------------: | :--------: | :--------: |
| MobileNetV3 | MobileNetV3_large_x1_0 | 支持 | 支持 |
| MobileNetV3 | MobileNetV3_large_x1_0_KL | 支持 | 支持 |
| PP-ShiTu | PPShiTu_general_rec、PPShiTu_mainbody_det | 支持 | 支持 |
| PP-ShiTu | PPShiTu_mainbody_det | 支持 | 支持 |
| PPHGNet | PPHGNet_small | 支持 | 支持 |
| PPHGNet | PPHGNet_tiny | 支持 | 支持 |
| PPLCNet | PPLCNet_x0_25 | 支持 | 支持 |
| PPLCNet | PPLCNet_x0_35 | 支持 | 支持 |
| PPLCNet | PPLCNet_x0_5 | 支持 | 支持 |
| PPLCNet | PPLCNet_x0_75 | 支持 | 支持 |
| PPLCNet | PPLCNet_x1_0 | 支持 | 支持 |
| PPLCNet | PPLCNet_x1_5 | 支持 | 支持 |
| PPLCNet | PPLCNet_x2_0 | 支持 | 支持 |
| PPLCNet | PPLCNet_x2_5 | 支持 | 支持 |
| PPLCNetV2 | PPLCNetV2_base | 支持 | 支持 |
| ResNet | ResNet50 | 支持 | 支持 |
| ResNet | ResNet50_vd | 支持 | 支持 |
| ResNet | ResNet50_vd_KL | 支持 | 支持 |
| SwinTransformer | SwinTransformer_tiny_patch4_window7_224 | 支持 | 支持 |
| 算法名称 | 模型名称 | device_CPU | device_GPU |
| :-------------: | :----------------------------------------: | :--------: | :--------: |
| MobileNetV3 | MobileNetV3_large_x1_0 | 支持 | 支持 |
| MobileNetV3 | MobileNetV3_large_x1_0_KL | 支持 | 支持 |
| PP-ShiTu | PPShiTu_general_rec、PPShiTu_mainbody_det | 支持 | 支持 |
| PP-ShiTu | GeneralRecognition_PPLCNet_x2_5_KL | 支持 | 支持 |
| PPHGNet | PPHGNet_small | 支持 | 支持 |
| PPHGNet | PPHGNet_small_KL | 支持 | 支持 |
| PPHGNet | PPHGNet_tiny | 支持 | 支持 |
| PPLCNet | PPLCNet_x0_25 | 支持 | 支持 |
| PPLCNet | PPLCNet_x0_35 | 支持 | 支持 |
| PPLCNet | PPLCNet_x0_5 | 支持 | 支持 |
| PPLCNet | PPLCNet_x0_75 | 支持 | 支持 |
| PPLCNet | PPLCNet_x1_0 | 支持 | 支持 |
| PPLCNet | PPLCNet_x1_0_KL | 支持 | 支持 |
| PPLCNet | PPLCNet_x1_5 | 支持 | 支持 |
| PPLCNet | PPLCNet_x2_0 | 支持 | 支持 |
| PPLCNet | PPLCNet_x2_5 | 支持 | 支持 |
| PPLCNetV2 | PPLCNetV2_base | 支持 | 支持 |
| PPLCNetV2 | PPLCNetV2_base_KL | 支持 | 支持 |
| ResNet | ResNet50 | 支持 | 支持 |
| ResNet | ResNet50_vd | 支持 | 支持 |
| ResNet | ResNet50_vd_KL | 支持 | 支持 |
| SwinTransformer | SwinTransformer_tiny_patch4_window7_224 | 支持 | 支持 |
| SwinTransformer | SwinTransformer_tiny_patch4_window7_224_KL | 支持 | 支持 |
## 2. 测试流程(以**ResNet50**为例)
...
...
@@ -244,20 +248,20 @@ bash test_tipc/prepare.sh test_tipc/config/ResNet/ResNet50_linux_gpu_normal_norm
测试方法如下所示,希望测试不同的模型文件,只需更换为自己的参数配置文件,即可完成对应模型的测试。
```
shell
bash test_tipc/test_inference_cpp.sh
${
your_params_file
}
bash test_tipc/test_inference_cpp.sh
${
your_params_file
}
cpp_infer
```
以
`ResNet50`
的
`Linux GPU/CPU C++推理测试`
为例,命令如下所示。
```
shell
bash test_tipc/test_inference_cpp.sh test_tipc/config/ResNet/ResNet50_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
bash test_tipc/test_inference_cpp.sh test_tipc/config/ResNet/ResNet50_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
cpp_infer
```
输出结果如下,表示命令运行成功。
```
shell
Run successfully with
command
-
./deploy/cpp/build/clas_system
-c
inference_cls.yaml
>
./test_tipc/output/ResNet50/cls_
cpp_infer_gpu_usetrt_False_precision_fp32_batchsize_1.log 2>&1!
Run successfully with
command
-
./deploy/cpp/build/clas_system
-c
inference_cls.yaml
>
./test_tipc/output/ResNet50/cls_
cpp_infer_cpu_usemkldnn_False_threads_1_precision_fp32_batchsize_1.log 2>&1!
Run successfully with
command
-
ResNet50 - ./deploy/cpp/build/clas_system
-c
inference_cls.yaml
>
./test_tipc/output/ResNet50/cpp_infer/
cpp_infer_gpu_usetrt_False_precision_fp32_batchsize_1.log 2>&1!
Run successfully with
command
-
ResNet50 - ./deploy/cpp/build/clas_system
-c
inference_cls.yaml
>
./test_tipc/output/ResNet50/cpp_infer/
cpp_infer_cpu_usemkldnn_False_threads_1_precision_fp32_batchsize_1.log 2>&1!
```
最终log中会打印出结果,如下所示
...
...
@@ -308,6 +312,6 @@ Current total inferen time cost: 5449.39 ms.
Top5: class_id: 265, score: 0.0420, label: toy poodle
```
详细log位于
`./test_tipc/output/ResNet50/c
ls_cpp_infer_gpu_usetrt_False_precision_fp32_batchsize_1.log`
和
`./test_tipc/output/ResNet50/cls_
cpp_infer_cpu_usemkldnn_False_threads_1_precision_fp32_batchsize_1.log`
中。
详细log位于
`./test_tipc/output/ResNet50/c
pp_infer/cpp_infer_gpu_usetrt_False_precision_fp32_batchsize_1.log`
和
`./test_tipc/output/ResNet50/
cpp_infer_cpu_usemkldnn_False_threads_1_precision_fp32_batchsize_1.log`
中。
如果运行失败,也会在终端中输出运行失败的日志信息以及对应的运行命令。可以基于该命令,分析运行失败的原因。
test_tipc/docs/test_serving_infer_cpp.md
浏览文件 @
e77ba41e
...
...
@@ -7,26 +7,31 @@ Linux GPU/CPU C++ 服务化部署测试的主程序为`test_serving_infer_cpp.sh
-
推理相关:
| 算法名称 | 模型名称 | device_CPU | device_GPU |
| :-------------: | :---------------------------------------: | :--------: | :--------: |
| MobileNetV3 | MobileNetV3_large_x1_0 | 支持 | 支持 |
| MobileNetV3 | MobileNetV3_large_x1_0_KL | 支持 | 支持 |
| PP-ShiTu | PPShiTu_general_rec、PPShiTu_mainbody_det | 支持 | 支持 |
| PPHGNet | PPHGNet_small | 支持 | 支持 |
| PPHGNet | PPHGNet_tiny | 支持 | 支持 |
| PPLCNet | PPLCNet_x0_25 | 支持 | 支持 |
| PPLCNet | PPLCNet_x0_35 | 支持 | 支持 |
| PPLCNet | PPLCNet_x0_5 | 支持 | 支持 |
| PPLCNet | PPLCNet_x0_75 | 支持 | 支持 |
| PPLCNet | PPLCNet_x1_0 | 支持 | 支持 |
| PPLCNet | PPLCNet_x1_5 | 支持 | 支持 |
| PPLCNet | PPLCNet_x2_0 | 支持 | 支持 |
| PPLCNet | PPLCNet_x2_5 | 支持 | 支持 |
| PPLCNetV2 | PPLCNetV2_base | 支持 | 支持 |
| ResNet | ResNet50 | 支持 | 支持 |
| ResNet | ResNet50_vd | 支持 | 支持 |
| ResNet | ResNet50_vd_KL | 支持 | 支持 |
| SwinTransformer | SwinTransformer_tiny_patch4_window7_224 | 支持 | 支持 |
| 算法名称 | 模型名称 | device_CPU | device_GPU |
| :-------------: | :----------------------------------------: | :--------: | :--------: |
| MobileNetV3 | MobileNetV3_large_x1_0 | 支持 | 支持 |
| MobileNetV3 | MobileNetV3_large_x1_0_KL | 支持 | 支持 |
| PP-ShiTu | PPShiTu_general_rec、PPShiTu_mainbody_det | 支持 | 支持 |
| PP-ShiTu | GeneralRecognition_PPLCNet_x2_5_KL | 支持 | 支持 |
| PPHGNet | PPHGNet_small | 支持 | 支持 |
| PPHGNet | PPHGNet_small_KL | 支持 | 支持 |
| PPHGNet | PPHGNet_tiny | 支持 | 支持 |
| PPLCNet | PPLCNet_x0_25 | 支持 | 支持 |
| PPLCNet | PPLCNet_x0_35 | 支持 | 支持 |
| PPLCNet | PPLCNet_x0_5 | 支持 | 支持 |
| PPLCNet | PPLCNet_x0_75 | 支持 | 支持 |
| PPLCNet | PPLCNet_x1_0 | 支持 | 支持 |
| PPLCNet | PPLCNet_x1_0_KL | 支持 | 支持 |
| PPLCNet | PPLCNet_x1_5 | 支持 | 支持 |
| PPLCNet | PPLCNet_x2_0 | 支持 | 支持 |
| PPLCNet | PPLCNet_x2_5 | 支持 | 支持 |
| PPLCNetV2 | PPLCNetV2_base | 支持 | 支持 |
| PPLCNetV2 | PPLCNetV2_base_KL | 支持 | 支持 |
| ResNet | ResNet50 | 支持 | 支持 |
| ResNet | ResNet50_vd | 支持 | 支持 |
| ResNet | ResNet50_vd_KL | 支持 | 支持 |
| SwinTransformer | SwinTransformer_tiny_patch4_window7_224 | 支持 | 支持 |
| SwinTransformer | SwinTransformer_tiny_patch4_window7_224_KL | 支持 | 支持 |
## 2. 测试流程
...
...
test_tipc/docs/test_serving_infer_python.md
浏览文件 @
e77ba41e
...
...
@@ -7,26 +7,31 @@ Linux GPU/CPU PYTHON 服务化部署测试的主程序为`test_serving_infer_pyt
-
推理相关:
| 算法名称 | 模型名称 | device_CPU | device_GPU |
| :-------------: | :---------------------------------------: | :--------: | :--------: |
| MobileNetV3 | MobileNetV3_large_x1_0 | 支持 | 支持 |
| MobileNetV3 | MobileNetV3_large_x1_0_KL | 支持 | 支持 |
| PP-ShiTu | PPShiTu_general_rec、PPShiTu_mainbody_det | 支持 | 支持 |
| PPHGNet | PPHGNet_small | 支持 | 支持 |
| PPHGNet | PPHGNet_tiny | 支持 | 支持 |
| PPLCNet | PPLCNet_x0_25 | 支持 | 支持 |
| PPLCNet | PPLCNet_x0_35 | 支持 | 支持 |
| PPLCNet | PPLCNet_x0_5 | 支持 | 支持 |
| PPLCNet | PPLCNet_x0_75 | 支持 | 支持 |
| PPLCNet | PPLCNet_x1_0 | 支持 | 支持 |
| PPLCNet | PPLCNet_x1_5 | 支持 | 支持 |
| PPLCNet | PPLCNet_x2_0 | 支持 | 支持 |
| PPLCNet | PPLCNet_x2_5 | 支持 | 支持 |
| PPLCNetV2 | PPLCNetV2_base | 支持 | 支持 |
| ResNet | ResNet50 | 支持 | 支持 |
| ResNet | ResNet50_vd | 支持 | 支持 |
| ResNet | ResNet50_vd_KL | 支持 | 支持 |
| SwinTransformer | SwinTransformer_tiny_patch4_window7_224 | 支持 | 支持 |
| 算法名称 | 模型名称 | device_CPU | device_GPU |
| :-------------: | :----------------------------------------: | :--------: | :--------: |
| MobileNetV3 | MobileNetV3_large_x1_0 | 支持 | 支持 |
| MobileNetV3 | MobileNetV3_large_x1_0_KL | 支持 | 支持 |
| PP-ShiTu | PPShiTu_general_rec、PPShiTu_mainbody_det | 支持 | 支持 |
| PP-ShiTu | GeneralRecognition_PPLCNet_x2_5_KL | 支持 | 支持 |
| PPHGNet | PPHGNet_small | 支持 | 支持 |
| PPHGNet | PPHGNet_small_KL | 支持 | 支持 |
| PPHGNet | PPHGNet_tiny | 支持 | 支持 |
| PPLCNet | PPLCNet_x0_25 | 支持 | 支持 |
| PPLCNet | PPLCNet_x0_35 | 支持 | 支持 |
| PPLCNet | PPLCNet_x0_5 | 支持 | 支持 |
| PPLCNet | PPLCNet_x0_75 | 支持 | 支持 |
| PPLCNet | PPLCNet_x1_0 | 支持 | 支持 |
| PPLCNet | PPLCNet_x1_0_KL | 支持 | 支持 |
| PPLCNet | PPLCNet_x1_5 | 支持 | 支持 |
| PPLCNet | PPLCNet_x2_0 | 支持 | 支持 |
| PPLCNet | PPLCNet_x2_5 | 支持 | 支持 |
| PPLCNetV2 | PPLCNetV2_base | 支持 | 支持 |
| PPLCNetV2 | PPLCNetV2_base_KL | 支持 | 支持 |
| ResNet | ResNet50 | 支持 | 支持 |
| ResNet | ResNet50_vd | 支持 | 支持 |
| ResNet | ResNet50_vd_KL | 支持 | 支持 |
| SwinTransformer | SwinTransformer_tiny_patch4_window7_224 | 支持 | 支持 |
| SwinTransformer | SwinTransformer_tiny_patch4_window7_224_KL | 支持 | 支持 |
## 2. 测试流程
...
...
test_tipc/prepare.sh
浏览文件 @
e77ba41e
...
...
@@ -208,7 +208,7 @@ fi
if
[[
${
MODE
}
=
"serving_infer"
]]
;
then
# prepare serving env
python_name
=
$(
func_parser_value
"
${
lines
[2]
}
"
)
if
[[
${
model_name
}
=
~
"
ShiTu"
]]
;
then
if
[[
${
model_name
}
=
"PP
ShiTu"
]]
;
then
cls_inference_model_url
=
$(
func_parser_value
"
${
lines
[3]
}
"
)
cls_tar_name
=
$(
func_get_url_file_name
"
${
cls_inference_model_url
}
"
)
det_inference_model_url
=
$(
func_parser_value
"
${
lines
[4]
}
"
)
...
...
test_tipc/test_inference_cpp.sh
浏览文件 @
e77ba41e
...
...
@@ -63,7 +63,7 @@ function func_shitu_cpp_inference(){
if
[
${
use_mkldnn
}
=
"False"
]
&&
[
${
_flag_quant
}
=
"True"
]
;
then
precison
=
"int8"
fi
_save_log_path
=
"
${
_log_path
}
/
shitu_
cpp_infer_cpu_usemkldnn_
${
use_mkldnn
}
_threads_
${
threads
}
_precision_
${
precision
}
_batchsize_
${
batch_size
}
.log"
_save_log_path
=
"
${
_log_path
}
/cpp_infer_cpu_usemkldnn_
${
use_mkldnn
}
_threads_
${
threads
}
_precision_
${
precision
}
_batchsize_
${
batch_size
}
.log"
eval
$transform_index_cmd
command
=
"
${
generate_yaml_cmd
}
--type shitu --batch_size
${
batch_size
}
--mkldnn
${
use_mkldnn
}
--gpu
${
use_gpu
}
--cpu_thread
${
threads
}
--tensorrt False --precision
${
precision
}
--data_dir
${
_img_dir
}
--benchmark True --cls_model_dir
${
cpp_infer_model_dir
}
--det_model_dir
${
cpp_det_infer_model_dir
}
--gpu_id
${
GPUID
}
"
eval
$command
...
...
@@ -87,7 +87,7 @@ function func_shitu_cpp_inference(){
continue
fi
for
batch_size
in
${
cpp_batch_size_list
[*]
}
;
do
_save_log_path
=
"
${
_log_path
}
/
shitu_
cpp_infer_gpu_usetrt_
${
use_trt
}
_precision_
${
precision
}
_batchsize_
${
batch_size
}
.log"
_save_log_path
=
"
${
_log_path
}
/cpp_infer_gpu_usetrt_
${
use_trt
}
_precision_
${
precision
}
_batchsize_
${
batch_size
}
.log"
eval
$transform_index_cmd
command
=
"
${
generate_yaml_cmd
}
--type shitu --batch_size
${
batch_size
}
--mkldnn False --gpu
${
use_gpu
}
--cpu_thread 1 --tensorrt
${
use_trt
}
--precision
${
precision
}
--data_dir
${
_img_dir
}
--benchmark True --cls_model_dir
${
cpp_infer_model_dir
}
--det_model_dir
${
cpp_det_infer_model_dir
}
--gpu_id
${
GPUID
}
"
eval
$command
...
...
@@ -125,7 +125,7 @@ function func_cls_cpp_inference(){
if
[
${
use_mkldnn
}
=
"False"
]
&&
[
${
_flag_quant
}
=
"True"
]
;
then
precison
=
"int8"
fi
_save_log_path
=
"
${
_log_path
}
/c
ls_c
pp_infer_cpu_usemkldnn_
${
use_mkldnn
}
_threads_
${
threads
}
_precision_
${
precision
}
_batchsize_
${
batch_size
}
.log"
_save_log_path
=
"
${
_log_path
}
/cpp_infer_cpu_usemkldnn_
${
use_mkldnn
}
_threads_
${
threads
}
_precision_
${
precision
}
_batchsize_
${
batch_size
}
.log"
command
=
"
${
generate_yaml_cmd
}
--type cls --batch_size
${
batch_size
}
--mkldnn
${
use_mkldnn
}
--gpu
${
use_gpu
}
--cpu_thread
${
threads
}
--tensorrt False --precision
${
precision
}
--data_dir
${
_img_dir
}
--benchmark True --cls_model_dir
${
cpp_infer_model_dir
}
--gpu_id
${
GPUID
}
"
eval
$command
...
...
@@ -149,7 +149,7 @@ function func_cls_cpp_inference(){
continue
fi
for
batch_size
in
${
cpp_batch_size_list
[*]
}
;
do
_save_log_path
=
"
${
_log_path
}
/c
ls_c
pp_infer_gpu_usetrt_
${
use_trt
}
_precision_
${
precision
}
_batchsize_
${
batch_size
}
.log"
_save_log_path
=
"
${
_log_path
}
/cpp_infer_gpu_usetrt_
${
use_trt
}
_precision_
${
precision
}
_batchsize_
${
batch_size
}
.log"
command
=
"
${
generate_yaml_cmd
}
--type cls --batch_size
${
batch_size
}
--mkldnn False --gpu
${
use_gpu
}
--cpu_thread 1 --tensorrt
${
use_trt
}
--precision
${
precision
}
--data_dir
${
_img_dir
}
--benchmark True --cls_model_dir
${
cpp_infer_model_dir
}
--gpu_id
${
GPUID
}
"
eval
$command
command
=
"
${
_script
}
>
${
_save_log_path
}
2>&1"
...
...
test_tipc/test_serving_infer_python.sh
浏览文件 @
e77ba41e
...
...
@@ -310,7 +310,7 @@ echo "################### run test ###################"
export
Count
=
0
IFS
=
"|"
if
[[
${
model_name
}
=
~
"
ShiTu"
]]
;
then
if
[[
${
model_name
}
=
"PP
ShiTu"
]]
;
then
func_serving_rec
else
func_serving_cls
...
...
编辑
预览
Markdown
is supported
0%
请重试
或
添加新附件
.
添加附件
取消
You are about to add
0
people
to the discussion. Proceed with caution.
先完成此消息的编辑!
取消
想要评论请
注册
或
登录