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
456891c3
P
PaddleClas
项目概览
PaddlePaddle
/
PaddleClas
接近 2 年 前同步成功
通知
116
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
未验证
提交
456891c3
编写于
9月 05, 2022
作者:
W
Walter
提交者:
GitHub
9月 05, 2022
浏览文件
操作
浏览文件
下载
差异文件
Merge pull request #2244 from HydrogenSulfate/add_ShiTuV2_tipc
【WIP】Add PP-ShiTuV2 TIPC
上级
f52f7b95
4ee9dd49
变更
31
显示空白变更内容
内联
并排
Showing
31 changed file
with
421 addition
and
37 deletion
+421
-37
deploy/configs/inference_rec.yaml
deploy/configs/inference_rec.yaml
+6
-5
deploy/paddleserving/recognition/test_cpp_serving_client.py
deploy/paddleserving/recognition/test_cpp_serving_client.py
+0
-1
docs/zh_CN/image_recognition_pipeline/feature_extraction.md
docs/zh_CN/image_recognition_pipeline/feature_extraction.md
+5
-5
test_tipc/README.md
test_tipc/README.md
+0
-1
test_tipc/configs/GeneralRecognition/GeneralRecognition_PPLCNet_x2_5_train_custom_sampler.txt
.../GeneralRecognition_PPLCNet_x2_5_train_custom_sampler.txt
+2
-2
test_tipc/configs/GeneralRecognition/GeneralRecognition_PPLCNet_x2_5_train_infer_python.txt
...on/GeneralRecognition_PPLCNet_x2_5_train_infer_python.txt
+2
-2
test_tipc/configs/GeneralRecognition/GeneralRecognition_PPLCNet_x2_5_train_linux_gpu_fleet_normal_infer_python_linux_gpu_cpu.txt
...ain_linux_gpu_fleet_normal_infer_python_linux_gpu_cpu.txt
+1
-1
test_tipc/configs/GeneralRecognition/GeneralRecognition_PPLCNet_x2_5_train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
...train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
+1
-1
test_tipc/configs/GeneralRecognition/GeneralRecognition_PPLCNet_x2_5_train_multicard_eval.txt
.../GeneralRecognition_PPLCNet_x2_5_train_multicard_eval.txt
+1
-1
test_tipc/configs/GeneralRecognition/GeneralRecognition_PPLCNet_x2_5_train_no_eval.txt
...gnition/GeneralRecognition_PPLCNet_x2_5_train_no_eval.txt
+1
-1
test_tipc/configs/GeneralRecognition/GeneralRecognition_PPLCNet_x2_5_train_pact_infer_python.txt
...neralRecognition_PPLCNet_x2_5_train_pact_infer_python.txt
+1
-1
test_tipc/configs/GeneralRecognition/GeneralRecognition_PPLCNet_x2_5_train_ptq_infer_python.txt
...eneralRecognition_PPLCNet_x2_5_train_ptq_infer_python.txt
+2
-2
test_tipc/configs/GeneralRecognitionV2/GeneralRecognitionV2_PPLCNetV2_base_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt
..._linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt
+16
-0
test_tipc/configs/GeneralRecognitionV2/GeneralRecognitionV2_PPLCNetV2_base_train_infer_python.txt
...eneralRecognitionV2_PPLCNetV2_base_train_infer_python.txt
+60
-0
test_tipc/configs/GeneralRecognitionV2/GeneralRecognitionV2_PPLCNetV2_base_train_linux_gpu_fleet_normal_infer_python_linux_gpu_cpu.txt
...ain_linux_gpu_fleet_normal_infer_python_linux_gpu_cpu.txt
+54
-0
test_tipc/configs/GeneralRecognitionV2/GeneralRecognitionV2_PPLCNetV2_base_train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
...train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
+52
-0
test_tipc/configs/GeneralRecognitionV2/GeneralRecognitionV2_PPLCNetV2_base_train_pact_infer_python.txt
...lRecognitionV2_PPLCNetV2_base_train_pact_infer_python.txt
+54
-0
test_tipc/configs/GeneralRecognitionV2/GeneralRecognitionV2_PPLCNetV2_base_train_ptq_infer_python.txt
...alRecognitionV2_PPLCNetV2_base_train_ptq_infer_python.txt
+54
-0
test_tipc/configs/PP-ShiTuV2/PPShiTuV2_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
...iTuV2_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
+19
-0
test_tipc/configs/PP-ShiTuV2/PPShiTuV2_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
...uV2_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
+18
-0
test_tipc/configs/PP-ShiTuV2/PPShiTuV2_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
..._linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
+18
-0
test_tipc/configs/PP-ShiTuV2/PPShiTuV2_mainbody_det_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt
..._linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt
+16
-0
test_tipc/docs/test_inference_cpp.md
test_tipc/docs/test_inference_cpp.md
+1
-0
test_tipc/docs/test_serving_infer_cpp.md
test_tipc/docs/test_serving_infer_cpp.md
+1
-0
test_tipc/docs/test_serving_infer_python.md
test_tipc/docs/test_serving_infer_python.md
+1
-0
test_tipc/docs/test_train_amp_inference_python.md
test_tipc/docs/test_train_amp_inference_python.md
+2
-0
test_tipc/docs/test_train_pact_inference_python.md
test_tipc/docs/test_train_pact_inference_python.md
+2
-0
test_tipc/docs/test_train_ptq_inference_python.md
test_tipc/docs/test_train_ptq_inference_python.md
+2
-0
test_tipc/prepare.sh
test_tipc/prepare.sh
+16
-11
test_tipc/test_serving_infer_cpp.sh
test_tipc/test_serving_infer_cpp.sh
+12
-2
test_tipc/test_serving_infer_python.sh
test_tipc/test_serving_infer_python.sh
+1
-1
未找到文件。
deploy/configs/inference_rec.yaml
浏览文件 @
456891c3
...
@@ -15,14 +15,15 @@ Global:
...
@@ -15,14 +15,15 @@ Global:
RecPreProcess
:
RecPreProcess
:
transform_ops
:
transform_ops
:
-
ResizeImage
:
-
ResizeImage
:
resize_short
:
256
size
:
[
224
,
224
]
-
CropImage
:
return_numpy
:
False
size
:
224
interpolation
:
bilinear
backend
:
cv2
-
NormalizeImage
:
-
NormalizeImage
:
scale
:
0.00392157
scale
:
1.0/255.0
mean
:
[
0.485
,
0.456
,
0.406
]
mean
:
[
0.485
,
0.456
,
0.406
]
std
:
[
0.229
,
0.224
,
0.225
]
std
:
[
0.229
,
0.224
,
0.225
]
order
:
"
"
order
:
hwc
-
ToCHWImage
:
-
ToCHWImage
:
RecPostProcess
:
null
RecPostProcess
:
null
deploy/paddleserving/recognition/test_cpp_serving_client.py
浏览文件 @
456891c3
...
@@ -113,7 +113,6 @@ if __name__ == "__main__":
...
@@ -113,7 +113,6 @@ if __name__ == "__main__":
batch
=
False
)
batch
=
False
)
# add retrieval procedure
# add retrieval procedure
print
(
fetch_map
.
keys
())
det_boxes
=
fetch_map
[
"boxes"
]
det_boxes
=
fetch_map
[
"boxes"
]
searcher
,
id_map
=
init_index
(
index_dir
)
searcher
,
id_map
=
init_index
(
index_dir
)
results
=
postprocess
(
fetch_map
,
feature_normalize
,
det_boxes
,
searcher
,
results
=
postprocess
(
fetch_map
,
feature_normalize
,
det_boxes
,
searcher
,
...
...
docs/zh_CN/image_recognition_pipeline/feature_extraction.md
浏览文件 @
456891c3
...
@@ -252,12 +252,12 @@ python3.7 python/predict_rec.py \
...
@@ -252,12 +252,12 @@ python3.7 python/predict_rec.py \
得到的特征输出格式如下所示:
得到的特征输出格式如下所示:
```
log
```
log
wangzai.jpg: [-
4.72979844e-02 3.40038240e-02 -4.06982675e-02 2.46225717e-03
wangzai.jpg: [-
7.82453567e-02 2.55877394e-02 -3.66694555e-02 1.34572461e-02
9.67078656e-03 2.70162839e-02 -8.85589980e-03 -4.7198325
4e-02
4.39076796e-02 -2.34078392e-02 -9.49947070e-03 1.2822121
4e-02
6.18615076e-02 1.38509814e-02 -1.11342799e-02 6.73768669
e-02
5.53947650e-02 1.01355985e-02 -1.06436480e-02 4.97181974
e-02
-
1.03065455e-02 -4.88462113e-02 8.46387446e-03 1.57074817e-02
-
2.21862812e-02 -1.75557341e-02 1.55848479e-02 -3.33278324e-03
...
...
-3.
14170569e-02 7.35917836e-02 -3.09373233e-02 -2.31755469
e-02]
-3.
40284109e-02 8.35561901e-02 2.10910216e-02 -3.27066667
e-02]
```
```
在实际使用过程中,仅仅得到特征可能并不能满足业务需求。如果想进一步通过特征检索来进行图像识别,可以参照文档
[
向量检索
](
./vector_search.md
)
。
在实际使用过程中,仅仅得到特征可能并不能满足业务需求。如果想进一步通过特征检索来进行图像识别,可以参照文档
[
向量检索
](
./vector_search.md
)
。
...
...
test_tipc/README.md
浏览文件 @
456891c3
...
@@ -110,7 +110,6 @@ bash test_tipc/test_train_inference_python.sh ./test_tipc/configs/MobileNetV3/Mo
...
@@ -110,7 +110,6 @@ bash test_tipc/test_train_inference_python.sh ./test_tipc/configs/MobileNetV3/Mo
-
[
test_train_pact_inference_python 使用
](
docs/test_train_pact_inference_python.md
)
:测试基于Python的模型PACT在线量化等基本功能。
-
[
test_train_pact_inference_python 使用
](
docs/test_train_pact_inference_python.md
)
:测试基于Python的模型PACT在线量化等基本功能。
-
[
test_train_ptq_inference_python 使用
](
docs/test_train_ptq_inference_python.md
)
:测试基于Python的模型KL离线量化等基本功能。
-
[
test_train_ptq_inference_python 使用
](
docs/test_train_ptq_inference_python.md
)
:测试基于Python的模型KL离线量化等基本功能。
-
[
test_inference_cpp 使用
](
docs/test_inference_cpp.md
)
:测试基于C++的模型推理。
-
[
test_inference_cpp 使用
](
docs/test_inference_cpp.md
)
:测试基于C++的模型推理。
-
[
test_serving 使用
](
docs/test_serving.md
)
:测试基于Paddle Serving的服务化部署功能。
-
[
test_lite_arm_cpu_cpp 使用
](
docs/test_lite_arm_cpu_cpp.md
)
: 测试基于Paddle-Lite的ARM CPU端c++预测部署功能.
-
[
test_lite_arm_cpu_cpp 使用
](
docs/test_lite_arm_cpu_cpp.md
)
: 测试基于Paddle-Lite的ARM CPU端c++预测部署功能.
-
[
test_paddle2onnx 使用
](
docs/test_paddle2onnx.md
)
:测试Paddle2ONNX的模型转化功能,并验证正确性。
-
[
test_paddle2onnx 使用
](
docs/test_paddle2onnx.md
)
:测试Paddle2ONNX的模型转化功能,并验证正确性。
-
[
test_serving_infer_python 使用
](
docs/test_serving_infer_python.md
)
:测试python serving功能。
-
[
test_serving_infer_python 使用
](
docs/test_serving_infer_python.md
)
:测试python serving功能。
...
...
test_tipc/configs/GeneralRecognition/GeneralRecognition_PPLCNet_x2_5_train_custom_sampler.txt
浏览文件 @
456891c3
test_tipc/configs/GeneralRecognition/GeneralRecognition_PPLCNet_x2_5_train_infer_python.txt
浏览文件 @
456891c3
...
@@ -37,7 +37,7 @@ pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/r
...
@@ -37,7 +37,7 @@ pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/r
infer_model:../inference/
infer_model:../inference/
infer_export:True
infer_export:True
infer_quant:Fasle
infer_quant:Fasle
inference:python/predict_rec.py -c configs/inference_rec.yaml
inference:python/predict_rec.py -c configs/inference_rec.yaml
-o Global.rec_inference_model_dir="./models/general_PPLCNet_x2_5_lite_v1.0_infer"
-o Global.use_gpu:True|False
-o Global.use_gpu:True|False
-o Global.enable_mkldnn:False
-o Global.enable_mkldnn:False
-o Global.cpu_num_threads:1
-o Global.cpu_num_threads:1
...
...
test_tipc/configs/GeneralRecognition/GeneralRecognition_PPLCNet_x2_5_train_linux_gpu_fleet_normal_infer_python_linux_gpu_cpu.txt
浏览文件 @
456891c3
...
@@ -37,7 +37,7 @@ pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/r
...
@@ -37,7 +37,7 @@ pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/r
infer_model:../inference/
infer_model:../inference/
infer_export:True
infer_export:True
infer_quant:Fasle
infer_quant:Fasle
inference:python/predict_rec.py -c configs/inference_rec.yaml
inference:python/predict_rec.py -c configs/inference_rec.yaml
-o Global.rec_inference_model_dir="./models/general_PPLCNet_x2_5_lite_v1.0_infer"
-o Global.use_gpu:True|False
-o Global.use_gpu:True|False
-o Global.enable_mkldnn:False
-o Global.enable_mkldnn:False
-o Global.cpu_num_threads:1
-o Global.cpu_num_threads:1
...
...
test_tipc/configs/GeneralRecognition/GeneralRecognition_PPLCNet_x2_5_train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
浏览文件 @
456891c3
...
@@ -37,7 +37,7 @@ pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/r
...
@@ -37,7 +37,7 @@ pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/r
infer_model:../inference/
infer_model:../inference/
infer_export:True
infer_export:True
infer_quant:Fasle
infer_quant:Fasle
inference:python/predict_rec.py -c configs/inference_rec.yaml
inference:python/predict_rec.py -c configs/inference_rec.yaml
-o Global.rec_inference_model_dir="./models/general_PPLCNet_x2_5_lite_v1.0_infer"
-o Global.use_gpu:True|False
-o Global.use_gpu:True|False
-o Global.enable_mkldnn:False
-o Global.enable_mkldnn:False
-o Global.cpu_num_threads:6
-o Global.cpu_num_threads:6
...
...
test_tipc/configs/GeneralRecognition/GeneralRecognition_PPLCNet_x2_5_train_multicard_eval.txt
浏览文件 @
456891c3
test_tipc/configs/GeneralRecognition/GeneralRecognition_PPLCNet_x2_5_train_no_eval.txt
浏览文件 @
456891c3
test_tipc/configs/GeneralRecognition/GeneralRecognition_PPLCNet_x2_5_train_pact_infer_python.txt
浏览文件 @
456891c3
...
@@ -37,7 +37,7 @@ pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/r
...
@@ -37,7 +37,7 @@ pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/r
infer_model:../inference/
infer_model:../inference/
infer_export:True
infer_export:True
infer_quant:Fasle
infer_quant:Fasle
inference:python/predict_rec.py -c configs/inference_rec.yaml
inference:python/predict_rec.py -c configs/inference_rec.yaml
-o Global.rec_inference_model_dir="./models/general_PPLCNet_x2_5_lite_v1.0_infer"
-o Global.use_gpu:True|False
-o Global.use_gpu:True|False
-o Global.enable_mkldnn:False
-o Global.enable_mkldnn:False
-o Global.cpu_num_threads:1
-o Global.cpu_num_threads:1
...
...
test_tipc/configs/GeneralRecognition/GeneralRecognition_PPLCNet_x2_5_train_ptq_infer_python.txt
浏览文件 @
456891c3
...
@@ -37,7 +37,7 @@ pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/r
...
@@ -37,7 +37,7 @@ pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/r
infer_model:./general_PPLCNet_x2_5_lite_v1.0_infer/
infer_model:./general_PPLCNet_x2_5_lite_v1.0_infer/
infer_export:True
infer_export:True
infer_quant:Fasle
infer_quant:Fasle
inference:python/predict_rec.py -c configs/inference_rec.yaml
inference:python/predict_rec.py -c configs/inference_rec.yaml
-o Global.rec_inference_model_dir="./models/general_PPLCNet_x2_5_lite_v1.0_infer"
-o Global.use_gpu:True|False
-o Global.use_gpu:True|False
-o Global.enable_mkldnn:False
-o Global.enable_mkldnn:False
-o Global.cpu_num_threads:1
-o Global.cpu_num_threads:1
...
...
test_tipc/configs/GeneralRecognitionV2/GeneralRecognitionV2_PPLCNetV2_base_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt
0 → 100644
浏览文件 @
456891c3
===========================paddle2onnx_params===========================
model_name:GeneralRecognitionV2_PPLCNetV2_base
python:python3.7
2onnx: paddle2onnx
--model_dir:./deploy/models/general_PPLCNetV2_base_pretrained_v1.0_infer/
--model_filename:inference.pdmodel
--params_filename:inference.pdiparams
--save_file:./deploy/models/general_PPLCNetV2_base_pretrained_v1.0_infer/inference.onnx
--opset_version:10
--enable_onnx_checker:True
inference_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/models/inference/PP-ShiTuV2/general_PPLCNetV2_base_pretrained_v1.0_infer.tar
inference:./python/predict_rec.py
Global.use_onnx:True
Global.rec_inference_model_dir:./models/general_PPLCNetV2_base_pretrained_v1.0_infer
Global.use_gpu:False
-c:configs/inference_rec.yaml
\ No newline at end of file
test_tipc/configs/GeneralRecognitionV2/GeneralRecognitionV2_PPLCNetV2_base_train_infer_python.txt
0 → 100644
浏览文件 @
456891c3
===========================train_params===========================
model_name:GeneralRecognitionV2_PPLCNetV2_base
python:python3.7
gpu_list:0|0,1
-o Global.device:gpu
-o Global.auto_cast:null
-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120
-o Global.output_dir:./output/
-o DataLoader.Train.sampler.batch_size:8
-o Global.pretrained_model:null
train_model_name:latest
train_infer_img_dir:./dataset/ILSVRC2012/val
null:null
##
trainer:norm_train
norm_train:tools/train.py -c ppcls/configs/GeneralRecognitionV2/GeneralRecognitionV2_PPLCNetV2_base.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False -o Global.eval_during_train=False -o Global.save_interval=2 -o DataLoader.Train.dataset.cls_label_path=./dataset/train_reg_all_data.txt -o DataLoader.Train.loader.sampler.batch_size=8
pact_train:null
fpgm_train:null
distill_train:null
null:null
null:null
##
===========================eval_params===========================
eval:tools/eval.py -c ppcls/configs/GeneralRecognitionV2/GeneralRecognitionV2_PPLCNetV2_base.yaml
null:null
##
===========================infer_params==========================
-o Global.save_inference_dir:./inference
-o Global.pretrained_model:
norm_export:tools/export_model.py -c ppcls/configs/GeneralRecognitionV2/GeneralRecognitionV2_PPLCNetV2_base.yaml
quant_export:null
fpgm_export:null
distill_export:null
kl_quant:null
export2:null
pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/models/pretrain/PPShiTuV2/general_PPLCNetV2_base_pretrained_v1.0.pdparams
infer_model:../inference/
infer_export:True
infer_quant:Fasle
inference:python/predict_rec.py -c configs/inference_rec.yaml
-o Global.use_gpu:True|False
-o Global.enable_mkldnn:False
-o Global.cpu_num_threads:1
-o Global.batch_size:1
-o Global.use_tensorrt:False
-o Global.use_fp16:False
-o Global.rec_inference_model_dir:../inference
-o Global.infer_imgs:../dataset/Aliproduct/demo_test/
-o Global.save_log_path:null
-o Global.benchmark:False
null:null
null:null
===========================train_benchmark_params==========================
batch_size:256
fp_items:fp32|fp16
epoch:1
--profiler_options:batch_range=[10,20];state=GPU;tracer_option=Default;profile_path=model.profile
flags:FLAGS_eager_delete_tensor_gb=0.0;FLAGS_fraction_of_gpu_memory_to_use=0.98;FLAGS_conv_workspace_size_limit=4096
===========================infer_benchmark_params==========================
random_infer_input:[{float32,[3,224,224]}]
\ No newline at end of file
test_tipc/configs/GeneralRecognitionV2/GeneralRecognitionV2_PPLCNetV2_base_train_linux_gpu_fleet_normal_infer_python_linux_gpu_cpu.txt
0 → 100644
浏览文件 @
456891c3
===========================train_params===========================
model_name:GeneralRecognition_PPLCNet_x2_5
python:python3.7
gpu_list:192.168.0.1,192.168.0.2;0,1
-o Global.device:gpu
-o Global.auto_cast:null
-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120
-o Global.output_dir:./output/
-o DataLoader.Train.sampler.batch_size:8
-o Global.pretrained_model:null
train_model_name:latest
train_infer_img_dir:./dataset/ILSVRC2012/val
null:null
##
trainer:norm_train
norm_train:tools/train.py -c ppcls/configs/GeneralRecognitionV2/GeneralRecognitionV2_PPLCNetV2_base.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False -o Global.eval_during_train=False -o Global.save_interval=2 -o DataLoader.Train.dataset.cls_label_path=./dataset/train_reg_all_data.txt -o DataLoader.Train.loader.sampler.batch_size=8
pact_train:null
fpgm_train:null
distill_train:null
null:null
null:null
##
===========================eval_params===========================
eval:tools/eval.py -c ppcls/configs/GeneralRecognitionV2/GeneralRecognitionV2_PPLCNetV2_base.yaml
null:null
##
===========================infer_params==========================
-o Global.save_inference_dir:./inference
-o Global.pretrained_model:
norm_export:tools/export_model.py -c ppcls/configs/GeneralRecognitionV2/GeneralRecognitionV2_PPLCNetV2_base.yaml
quant_export:null
fpgm_export:null
distill_export:null
kl_quant:null
export2:null
pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/models/pretrain/PPShiTuV2/general_PPLCNetV2_base_pretrained_v1.0.pdparams
infer_model:../inference/
infer_export:True
infer_quant:Fasle
inference:python/predict_rec.py -c configs/inference_rec.yaml
-o Global.use_gpu:True|False
-o Global.enable_mkldnn:False
-o Global.cpu_num_threads:1
-o Global.batch_size:1
-o Global.use_tensorrt:False
-o Global.use_fp16:False
-o Global.rec_inference_model_dir:../inference
-o Global.infer_imgs:../dataset/Aliproduct/demo_test/
-o Global.save_log_path:null
-o Global.benchmark:False
null:null
null:null
===========================infer_benchmark_params==========================
random_infer_input:[{float32,[3,224,224]}]
\ No newline at end of file
test_tipc/configs/GeneralRecognitionV2/GeneralRecognitionV2_PPLCNetV2_base_train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
0 → 100644
浏览文件 @
456891c3
===========================train_params===========================
model_name:GeneralRecognitionV2_PPLCNetV2_base
python:python3.7
gpu_list:0|0,1
-o Global.device:gpu
-o Global.auto_cast:null
-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=100
-o Global.output_dir:./output/
-o DataLoader.Train.sampler.batch_size:8
-o Global.pretrained_model:null
train_model_name:latest
train_infer_img_dir:./dataset/ILSVRC2012/val
null:null
##
trainer:amp_train
amp_train:tools/train.py -c ppcls/configs/GeneralRecognitionV2/GeneralRecognitionV2_PPLCNetV2_base.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False -o AMP.scale_loss=65536 -o AMP.use_dynamic_loss_scaling=True -o AMP.level=O2 -o Optimizer.multi_precision=True -o Global.eval_during_train=False -o DataLoader.Train.dataset.cls_label_path=./dataset/train_reg_all_data.txt -o DataLoader.Train.loader.sampler.batch_size=8
pact_train:null
fpgm_train:null
distill_train:null
null:null
null:null
##
===========================eval_params===========================
eval:tools/eval.py -c ppcls/configs/GeneralRecognitionV2/GeneralRecognitionV2_PPLCNetV2_base.yaml
null:null
##
===========================infer_params==========================
-o Global.save_inference_dir:./inference
-o Global.pretrained_model:
norm_export:tools/export_model.py -c ppcls/configs/GeneralRecognitionV2/GeneralRecognitionV2_PPLCNetV2_base.yaml
quant_export:null
fpgm_export:null
distill_export:null
kl_quant:null
export2:null
pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/models/pretrain/PPShiTuV2/general_PPLCNetV2_base_pretrained_v1.0.pdparams
infer_model:../inference/
infer_export:True
infer_quant:Fasle
inference:python/predict_rec.py -c configs/inference_rec.yaml
-o Global.use_gpu:True|False
-o Global.enable_mkldnn:False
-o Global.cpu_num_threads:6
-o Global.batch_size:1
-o Global.use_tensorrt:False
-o Global.use_fp16:False
-o Global.rec_inference_model_dir:../inference
-o Global.infer_imgs:../dataset/Aliproduct/demo_test/
-o Global.save_log_path:null
-o Global.benchmark:False
null:null
null:null
test_tipc/configs/GeneralRecognitionV2/GeneralRecognitionV2_PPLCNetV2_base_train_pact_infer_python.txt
0 → 100644
浏览文件 @
456891c3
===========================train_params===========================
model_name:GeneralRecognitionV2_PPLCNetV2_base
python:python3.7
gpu_list:0
-o Global.device:gpu
-o Global.auto_cast:null
-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=100
-o Global.output_dir:./output/
-o DataLoader.Train.sampler.batch_size:8
-o Global.pretrained_model:null
train_model_name:latest
train_infer_img_dir:./dataset/ILSVRC2012/val
null:null
##
trainer:pact_train
norm_train:null
pact_train:tools/train.py -c ppcls/configs/GeneralRecognitionV2/GeneralRecognitionV2_PPLCNetV2_base.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False -o Slim.quant.name=pact -o Optimizer.lr.learning_rate=0.006 -o Global.pretrained_model="pretrained_model/general_PPLCNetV2_base_pretrained_v1.0" -o DataLoader.Train.dataset.cls_label_path=./dataset/train_reg_all_data.txt -o AMP=None -o DataLoader.Train.sampler.batch_size=8
fpgm_train:null
distill_train:null
null:null
null:null
##
===========================eval_params===========================
eval:tools/eval.py -c ppcls/configs/GeneralRecognitionV2/GeneralRecognitionV2_PPLCNetV2_base.yaml -o Slim.quant.name=pact
null:null
##
===========================infer_params==========================
-o Global.save_inference_dir:./inference
-o Global.pretrained_model:
norm_export:null
quant_export:tools/export_model.py -c ppcls/configs/GeneralRecognitionV2/GeneralRecognitionV2_PPLCNetV2_base.yaml -o Slim.quant.name=pact
fpgm_export:null
distill_export:null
kl_quant:null
export2:null
pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/models/pretrain/PPShiTuV2/general_PPLCNetV2_base_pretrained_v1.0.pdparams
infer_model:../inference/
infer_export:True
infer_quant:Fasle
inference:python/predict_rec.py -c configs/inference_rec.yaml
-o Global.use_gpu:True|False
-o Global.enable_mkldnn:False
-o Global.cpu_num_threads:1
-o Global.batch_size:1
-o Global.use_tensorrt:False
-o Global.use_fp16:False
-o Global.rec_inference_model_dir:../inference
-o Global.infer_imgs:../dataset/Aliproduct/demo_test/
-o Global.save_log_path:null
-o Global.benchmark:True
null:null
null:null
===========================infer_benchmark_params==========================
random_infer_input:[{float32,[3,224,224]}]
\ No newline at end of file
test_tipc/configs/GeneralRecognitionV2/GeneralRecognitionV2_PPLCNetV2_base_train_ptq_infer_python.txt
0 → 100644
浏览文件 @
456891c3
===========================train_params===========================
model_name:GeneralRecognitionV2_PPLCNetV2_base
python:python3.7
gpu_list:0
-o Global.device:gpu
-o Global.auto_cast:null
-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=100
-o Global.output_dir:./output/
-o DataLoader.Train.sampler.batch_size:8
-o Global.pretrained_model:null
train_model_name:latest
train_infer_img_dir:./dataset/ILSVRC2012/val
null:null
##
trainer:pact_train
norm_train:null
pact_train:tools/train.py -c ppcls/configs/GeneralRecognitionV2/GeneralRecognitionV2_PPLCNetV2_base.yaml -o Global.seed=1234 -o DataLoader.Train.sampler.shuffle=False -o DataLoader.Train.loader.num_workers=0 -o DataLoader.Train.loader.use_shared_memory=False
fpgm_train:null
distill_train:null
null:null
null:null
##
===========================eval_params===========================
eval:tools/eval.py -c ppcls/configs/GeneralRecognitionV2/GeneralRecognitionV2_PPLCNetV2_base.yaml
null:null
##
===========================infer_params==========================
-o Global.save_inference_dir:./inference
-o Global.pretrained_model:
norm_export:null
quant_export:tools/export_model.py -c ppcls/configs/GeneralRecognitionV2/GeneralRecognitionV2_PPLCNetV2_base.yaml
fpgm_export:null
distill_export:null
kl_quant:deploy/slim/quant_post_static.py -c ppcls/configs/GeneralRecognitionV2/GeneralRecognitionV2_PPLCNetV2_base.yaml -o Global.save_inference_dir=./general_PPLCNetV2_base_pretrained_v1.0_infer
export2:null
pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/models/inference/PP-ShiTuV2/general_PPLCNetV2_base_pretrained_v1.0_infer.tar
infer_model:./general_PPLCNetV2_base_pretrained_v1.0_infer
infer_export:True
infer_quant:Fasle
inference:python/predict_rec.py -c configs/inference_rec.yaml
-o Global.use_gpu:True|False
-o Global.enable_mkldnn:False
-o Global.cpu_num_threads:1
-o Global.batch_size:1
-o Global.use_tensorrt:False
-o Global.use_fp16:False
-o Global.rec_inference_model_dir:../inference
-o Global.infer_imgs:../dataset/Aliproduct/demo_test/
-o Global.save_log_path:null
-o Global.benchmark:False
null:null
null:null
===========================infer_benchmark_params==========================
random_infer_input:[{float32,[3,224,224]}]
\ No newline at end of file
test_tipc/configs/PP-ShiTuV2/PPShiTuV2_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
0 → 100644
浏览文件 @
456891c3
===========================cpp_infer_params===========================
model_name:PPShiTuV2
cpp_infer_type:shitu
feature_inference_model_dir:./general_PPLCNetV2_base_pretrained_v1.0_infer/
det_inference_model_dir:./picodet_PPLCNet_x2_5_mainbody_lite_v1.0_infer/
cls_inference_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/models/inference/PP-ShiTuV2/general_PPLCNetV2_base_pretrained_v1.0_infer.tar
det_inference_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/models/inference/picodet_PPLCNet_x2_5_mainbody_lite_v1.0_infer.tar
infer_quant:False
inference_cmd:./deploy/cpp_shitu/build/pp_shitu -c inference_drink.yaml
use_gpu:True|False
enable_mkldnn:False
cpu_threads:1
batch_size:1
use_tensorrt:False
precision:fp32
data_dir:./dataset/drink_dataset_v2.0
benchmark:True
generate_yaml_cmd:python3.7 test_tipc/generate_cpp_yaml.py
transform_index_cmd:python3.7 deploy/cpp_shitu/tools/transform_id_map.py -c inference_drink.yaml
test_tipc/configs/PP-ShiTuV2/PPShiTuV2_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
0 → 100644
浏览文件 @
456891c3
===========================serving_params===========================
model_name:PPShiTuV2
python:python3.7
cls_inference_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/models/inference/PP-ShiTuV2/general_PPLCNetV2_base_pretrained_v1.0_infer.tar
det_inference_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/models/inference/picodet_PPLCNet_x2_5_mainbody_lite_v1.0_infer.tar
trans_model:-m paddle_serving_client.convert
--dirname:./models/general_PPLCNetV2_base_pretrained_v1.0_infer/
--dirname:./models/picodet_PPLCNet_x2_5_mainbody_lite_v1.0_infer/
--model_filename:inference.pdmodel
--params_filename:inference.pdiparams
--serving_server:./models/general_PPLCNetV2_base_pretrained_v1.0_serving/
--serving_client:./models/general_PPLCNetV2_base_pretrained_v1.0_client/
--serving_server:./models/picodet_PPLCNet_x2_5_mainbody_lite_v1.0_serving/
--serving_client:./models/picodet_PPLCNet_x2_5_mainbody_lite_v1.0_client/
serving_dir:./paddleserving/recognition
web_service:null
--use_gpu:0|null
pipline:test_cpp_serving_client.py
test_tipc/configs/PP-ShiTuV2/PPShiTuV2_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
0 → 100644
浏览文件 @
456891c3
===========================serving_params===========================
model_name:PPShiTuV2
python:python3.7
cls_inference_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/models/inference/PP-ShiTuV2/general_PPLCNetV2_base_pretrained_v1.0_infer.tar
det_inference_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/models/inference/picodet_PPLCNet_x2_5_mainbody_lite_v1.0_infer.tar
trans_model:-m paddle_serving_client.convert
--dirname:./models/general_PPLCNetV2_base_pretrained_v1.0_infer/
--dirname:./models/picodet_PPLCNet_x2_5_mainbody_lite_v1.0_infer/
--model_filename:inference.pdmodel
--params_filename:inference.pdiparams
--serving_server:./models/general_PPLCNetV2_base_pretrained_v1.0_serving/
--serving_client:./models/general_PPLCNetV2_base_pretrained_v1.0_client/
--serving_server:./models/picodet_PPLCNet_x2_5_mainbody_lite_v1.0_serving/
--serving_client:./models/picodet_PPLCNet_x2_5_mainbody_lite_v1.0_client/
serving_dir:./paddleserving/recognition
web_service:recognition_web_service.py
--use_gpu:0|null
pipline:pipeline_http_client.py
test_tipc/configs/PP-ShiTuV2/PPShiTuV2_mainbody_det_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt
0 → 100644
浏览文件 @
456891c3
===========================paddle2onnx_params===========================
model_name:PP-ShiTu_mainbody_det
python:python3.7
2onnx: paddle2onnx
--model_dir:./deploy/models/picodet_lcnet_x2_5_640_mainbody_infer/
--model_filename:inference.pdmodel
--params_filename:inference.pdiparams
--save_file:./deploy/models/picodet_lcnet_x2_5_640_mainbody_infer/inference.onnx
--opset_version:11
--enable_onnx_checker:True
inference_model_url:https://paddledet.bj.bcebos.com/models/picodet_lcnet_x2_5_640_mainbody_infer.tar
inference:null
Global.use_onnx:null
Global.inference_model_dir:null
Global.use_gpu:null
-c:null
\ No newline at end of file
test_tipc/docs/test_inference_cpp.md
浏览文件 @
456891c3
...
@@ -12,6 +12,7 @@ Linux GPU/CPU C++ 推理功能测试的主程序为`test_inference_cpp.sh`,可
...
@@ -12,6 +12,7 @@ Linux GPU/CPU C++ 推理功能测试的主程序为`test_inference_cpp.sh`,可
| MobileNetV3 | MobileNetV3_large_x1_0_KL | 支持 | 支持 |
| MobileNetV3 | MobileNetV3_large_x1_0_KL | 支持 | 支持 |
| MobileNetV3 | MobileNetV3_large_x1_0_PACT | 支持 | 支持 |
| MobileNetV3 | MobileNetV3_large_x1_0_PACT | 支持 | 支持 |
| PP-ShiTu | PPShiTu_general_rec、PPShiTu_mainbody_det | 支持 | 支持 |
| PP-ShiTu | PPShiTu_general_rec、PPShiTu_mainbody_det | 支持 | 支持 |
| PP-ShiTuV2 | PPShiTuV2_general_rec、PPShiTu_mainbody_det | 支持 | 支持 |
| PP-ShiTu | GeneralRecognition_PPLCNet_x2_5_KL | 支持 | 支持 |
| PP-ShiTu | GeneralRecognition_PPLCNet_x2_5_KL | 支持 | 支持 |
| PP-ShiTu | GeneralRecognition_PPLCNet_x2_5_PACT | 支持 | 支持 |
| PP-ShiTu | GeneralRecognition_PPLCNet_x2_5_PACT | 支持 | 支持 |
| PPHGNet | PPHGNet_small | 支持 | 支持 |
| PPHGNet | PPHGNet_small | 支持 | 支持 |
...
...
test_tipc/docs/test_serving_infer_cpp.md
浏览文件 @
456891c3
...
@@ -15,6 +15,7 @@ Linux GPU/CPU C++ 服务化部署测试的主程序为`test_serving_infer_cpp.sh
...
@@ -15,6 +15,7 @@ Linux GPU/CPU C++ 服务化部署测试的主程序为`test_serving_infer_cpp.sh
| PP-ShiTu | PPShiTu_general_rec、PPShiTu_mainbody_det | 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 |
| PP-ShiTu | GeneralRecognition_PPLCNet_x2_5_KL | 支持 | 支持 |
| PP-ShiTu | GeneralRecognition_PPLCNet_x2_5_PACT | 支持 | 支持 |
| PP-ShiTu | GeneralRecognition_PPLCNet_x2_5_PACT | 支持 | 支持 |
| PP-ShiTuV2 | PPShiTuV2_general_rec、PPShiTu_mainbody_det | 支持 | 支持 |
| PPHGNet | PPHGNet_small | 支持 | 支持 |
| PPHGNet | PPHGNet_small | 支持 | 支持 |
| PPHGNet | PPHGNet_small_KL | 支持 | 支持 |
| PPHGNet | PPHGNet_small_KL | 支持 | 支持 |
| PPHGNet | PPHGNet_small_PACT | 支持 | 支持 |
| PPHGNet | PPHGNet_small_PACT | 支持 | 支持 |
...
...
test_tipc/docs/test_serving_infer_python.md
浏览文件 @
456891c3
...
@@ -15,6 +15,7 @@ Linux GPU/CPU PYTHON 服务化部署测试的主程序为`test_serving_infer_pyt
...
@@ -15,6 +15,7 @@ Linux GPU/CPU PYTHON 服务化部署测试的主程序为`test_serving_infer_pyt
| PP-ShiTu | PPShiTu_general_rec、PPShiTu_mainbody_det | 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 |
| PP-ShiTu | GeneralRecognition_PPLCNet_x2_5_KL | 支持 | 支持 |
| PP-ShiTu | GeneralRecognition_PPLCNet_x2_5_PACT | 支持 | 支持 |
| PP-ShiTu | GeneralRecognition_PPLCNet_x2_5_PACT | 支持 | 支持 |
| PP-ShiTuV2 | PPShiTuV2_general_rec、PPShiTu_mainbody_det | 支持 | 支持 |
| PPHGNet | PPHGNet_small | 支持 | 支持 |
| PPHGNet | PPHGNet_small | 支持 | 支持 |
| PPHGNet | PPHGNet_small_KL | 支持 | 支持 |
| PPHGNet | PPHGNet_small_KL | 支持 | 支持 |
| PPHGNet | PPHGNet_small_PACT | 支持 | 支持 |
| PPHGNet | PPHGNet_small_PACT | 支持 | 支持 |
...
...
test_tipc/docs/test_train_amp_inference_python.md
浏览文件 @
456891c3
...
@@ -10,6 +10,7 @@ Linux GPU/CPU 混合精度训练推理测试的主程序为`test_train_inference
...
@@ -10,6 +10,7 @@ Linux GPU/CPU 混合精度训练推理测试的主程序为`test_train_inference
| :-------------: | :-------------------------------------: | :----------: | :----------: |
| :-------------: | :-------------------------------------: | :----------: | :----------: |
| MobileNetV3 | MobileNetV3_large_x1_0 | 混合精度训练 | 混合精度训练 |
| MobileNetV3 | MobileNetV3_large_x1_0 | 混合精度训练 | 混合精度训练 |
| PP-ShiTu | GeneralRecognition_PPLCNet_x2_5 | 混合精度训练 | 混合精度训练 |
| PP-ShiTu | GeneralRecognition_PPLCNet_x2_5 | 混合精度训练 | 混合精度训练 |
| PP-ShiTuV2 | GeneralRecognitionV2_PPLCNetV2_base | 混合精度训练 | 混合精度训练 |
| PPHGNet | PPHGNet_small | 混合精度训练 | 混合精度训练 |
| PPHGNet | PPHGNet_small | 混合精度训练 | 混合精度训练 |
| PPHGNet | PPHGNet_tiny | 混合精度训练 | 混合精度训练 |
| PPHGNet | PPHGNet_tiny | 混合精度训练 | 混合精度训练 |
| PPLCNet | PPLCNet_x0_25 | 混合精度训练 | 混合精度训练 |
| PPLCNet | PPLCNet_x0_25 | 混合精度训练 | 混合精度训练 |
...
@@ -31,6 +32,7 @@ Linux GPU/CPU 混合精度训练推理测试的主程序为`test_train_inference
...
@@ -31,6 +32,7 @@ Linux GPU/CPU 混合精度训练推理测试的主程序为`test_train_inference
| :-------------: | :-------------------------------------: | :--------: | :--------: | :-------: |
| :-------------: | :-------------------------------------: | :--------: | :--------: | :-------: |
| MobileNetV3 | MobileNetV3_large_x1_0 | 支持 | 支持 | 1 |
| MobileNetV3 | MobileNetV3_large_x1_0 | 支持 | 支持 | 1 |
| PP-ShiTu | GeneralRecognition_PPLCNet_x2_5 | 支持 | 支持 | 1 |
| PP-ShiTu | GeneralRecognition_PPLCNet_x2_5 | 支持 | 支持 | 1 |
| PP-ShiTuV2 | GeneralRecognitionV2_PPLCNetV2_base | 支持 | 支持 | 1 |
| PPHGNet | PPHGNet_small | 支持 | 支持 | 1 |
| PPHGNet | PPHGNet_small | 支持 | 支持 | 1 |
| PPHGNet | PPHGNet_tiny | 支持 | 支持 | 1 |
| PPHGNet | PPHGNet_tiny | 支持 | 支持 | 1 |
| PPLCNet | PPLCNet_x0_25 | 支持 | 支持 | 1 |
| PPLCNet | PPLCNet_x0_25 | 支持 | 支持 | 1 |
...
...
test_tipc/docs/test_train_pact_inference_python.md
浏览文件 @
456891c3
...
@@ -10,6 +10,7 @@ Linux GPU/CPU PACT量化训练推理测试的主程序为`test_train_inference_p
...
@@ -10,6 +10,7 @@ Linux GPU/CPU PACT量化训练推理测试的主程序为`test_train_inference_p
| :-------------: | :-------------------------------------: | :----------: |
| :-------------: | :-------------------------------------: | :----------: |
| MobileNetV3 | MobileNetV3_large_x1_0 | PACT量化训练 |
| MobileNetV3 | MobileNetV3_large_x1_0 | PACT量化训练 |
| PP-ShiTu | GeneralRecognition_PPLCNet_x2_5 | PACT量化训练 |
| PP-ShiTu | GeneralRecognition_PPLCNet_x2_5 | PACT量化训练 |
| PP-ShiTuV2 | GeneralRecognitionV2_PPLCNetV2_base | PACT量化训练 |
| PPHGNet | PPHGNet_small | PACT量化训练 |
| PPHGNet | PPHGNet_small | PACT量化训练 |
| PPHGNet | PPHGNet_tiny | PACT量化训练 |
| PPHGNet | PPHGNet_tiny | PACT量化训练 |
| PPLCNet | PPLCNet_x0_25 | PACT量化训练 |
| PPLCNet | PPLCNet_x0_25 | PACT量化训练 |
...
@@ -31,6 +32,7 @@ Linux GPU/CPU PACT量化训练推理测试的主程序为`test_train_inference_p
...
@@ -31,6 +32,7 @@ Linux GPU/CPU PACT量化训练推理测试的主程序为`test_train_inference_p
| :-------------: | :-------------------------------------: | :--------: | :--------: | :-------: |
| :-------------: | :-------------------------------------: | :--------: | :--------: | :-------: |
| MobileNetV3 | MobileNetV3_large_x1_0 | 支持 | 支持 | 1 |
| MobileNetV3 | MobileNetV3_large_x1_0 | 支持 | 支持 | 1 |
| PP-ShiTu | GeneralRecognition_PPLCNet_x2_5 | 支持 | 支持 | 1 |
| PP-ShiTu | GeneralRecognition_PPLCNet_x2_5 | 支持 | 支持 | 1 |
| PP-ShiTuV2 | GeneralRecognitionV2_PPLCNetV2_base | 支持 | 支持 | 1 |
| PPHGNet | PPHGNet_small | 支持 | 支持 | 1 |
| PPHGNet | PPHGNet_small | 支持 | 支持 | 1 |
| PPHGNet | PPHGNet_tiny | 支持 | 支持 | 1 |
| PPHGNet | PPHGNet_tiny | 支持 | 支持 | 1 |
| PPLCNet | PPLCNet_x0_25 | 支持 | 支持 | 1 |
| PPLCNet | PPLCNet_x0_25 | 支持 | 支持 | 1 |
...
...
test_tipc/docs/test_train_ptq_inference_python.md
浏览文件 @
456891c3
...
@@ -10,6 +10,7 @@ Linux GPU/CPU KL离线量化推理测试的主程序为`test_ptq_inference_pytho
...
@@ -10,6 +10,7 @@ Linux GPU/CPU KL离线量化推理测试的主程序为`test_ptq_inference_pytho
| :-------------: | :-------------------------------------: | :----------: |
| :-------------: | :-------------------------------------: | :----------: |
| MobileNetV3 | MobileNetV3_large_x1_0 | KL离线量化 |
| MobileNetV3 | MobileNetV3_large_x1_0 | KL离线量化 |
| PP-ShiTu | GeneralRecognition_PPLCNet_x2_5 | KL离线量化 |
| PP-ShiTu | GeneralRecognition_PPLCNet_x2_5 | KL离线量化 |
| PP-ShiTuV2 | GeneralRecognitionV2_PPLCNetV2_base | KL离线量化 |
| PPHGNet | PPHGNet_small | KL离线量化 |
| PPHGNet | PPHGNet_small | KL离线量化 |
| PPHGNet | PPHGNet_tiny | KL离线量化 |
| PPHGNet | PPHGNet_tiny | KL离线量化 |
| PPLCNet | PPLCNet_x0_25 | KL离线量化 |
| PPLCNet | PPLCNet_x0_25 | KL离线量化 |
...
@@ -31,6 +32,7 @@ Linux GPU/CPU KL离线量化推理测试的主程序为`test_ptq_inference_pytho
...
@@ -31,6 +32,7 @@ Linux GPU/CPU KL离线量化推理测试的主程序为`test_ptq_inference_pytho
| :-------------: | :-------------------------------------: | :----------: |
| :-------------: | :-------------------------------------: | :----------: |
| MobileNetV3 | MobileNetV3_large_x1_0 | KL离线量化 |
| MobileNetV3 | MobileNetV3_large_x1_0 | KL离线量化 |
| PP-ShiTu | GeneralRecognition_PPLCNet_x2_5 | KL离线量化 |
| PP-ShiTu | GeneralRecognition_PPLCNet_x2_5 | KL离线量化 |
| PP-ShiTuV2 | GeneralRecognitionV2_PPLCNetV2_base | KL离线量化 |
| PPHGNet | PPHGNet_small | KL离线量化 |
| PPHGNet | PPHGNet_small | KL离线量化 |
| PPHGNet | PPHGNet_tiny | KL离线量化 |
| PPHGNet | PPHGNet_tiny | KL离线量化 |
| PPLCNet | PPLCNet_x0_25 | KL离线量化 |
| PPLCNet | PPLCNet_x0_25 | KL离线量化 |
...
...
test_tipc/prepare.sh
浏览文件 @
456891c3
...
@@ -43,7 +43,8 @@ function func_get_url_file_name() {
...
@@ -43,7 +43,8 @@ function func_get_url_file_name() {
model_name
=
$(
func_parser_value
"
${
lines
[1]
}
"
)
model_name
=
$(
func_parser_value
"
${
lines
[1]
}
"
)
# install paddleclas whl
# install paddleclas whl
python setup.py
install
python_name
=
$(
func_parser_value
"
${
lines
[2]
}
"
)
${
python_name
}
setup.py
install
if
[[
${
MODE
}
=
"cpp_infer"
]]
;
then
if
[[
${
MODE
}
=
"cpp_infer"
]]
;
then
if
[
-d
"./deploy/cpp/opencv-3.4.7/opencv3/"
]
&&
[
$(
md5sum
./deploy/cpp/opencv-3.4.7.tar.gz |
awk
-F
' '
'{print $1}'
)
=
"faa2b5950f8bee3f03118e600c74746a"
]
;
then
if
[
-d
"./deploy/cpp/opencv-3.4.7/opencv3/"
]
&&
[
$(
md5sum
./deploy/cpp/opencv-3.4.7.tar.gz |
awk
-F
' '
'{print $1}'
)
=
"faa2b5950f8bee3f03118e600c74746a"
]
;
then
...
@@ -142,6 +143,8 @@ if [[ ${MODE} = "cpp_infer" ]]; then
...
@@ -142,6 +143,8 @@ if [[ ${MODE} = "cpp_infer" ]]; then
cd
dataset
cd
dataset
wget
-nc
https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/data/drink_dataset_v1.0.tar
wget
-nc
https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/data/drink_dataset_v1.0.tar
tar
-xf
drink_dataset_v1.0.tar
tar
-xf
drink_dataset_v1.0.tar
wget
-nc
https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/data/drink_dataset_v2.0.tar
tar
-xf
drink_dataset_v2.0.tar
else
else
echo
"Wrong cpp type in config file in line 3. only support cls, shitu"
echo
"Wrong cpp type in config file in line 3. only support cls, shitu"
fi
fi
...
@@ -170,8 +173,9 @@ if [[ $model_name == *ShiTu* ]]; then
...
@@ -170,8 +173,9 @@ if [[ $model_name == *ShiTu* ]]; then
ln
-s
demo_test.txt val_list.txt
ln
-s
demo_test.txt val_list.txt
cd
../../
cd
../../
eval
"wget -nc
$model_url_value
--no-check-certificate"
eval
"wget -nc
$model_url_value
--no-check-certificate"
if
[[
-d
"./general_PPLCNet_x2_5_pretrained_v1.0.pdparams"
]]
;
then
mv
general_PPLCNet_x2_5_pretrained_v1.0.pdparams GeneralRecognition_PPLCNet_x2_5_pretrained.pdparams
mv
general_PPLCNet_x2_5_pretrained_v1.0.pdparams GeneralRecognition_PPLCNet_x2_5_pretrained.pdparams
exit
0
fi
fi
fi
if
[[
$FILENAME
==
*
use_dali
*
]]
;
then
if
[[
$FILENAME
==
*
use_dali
*
]]
;
then
...
@@ -243,12 +247,12 @@ elif [[ ${MODE} = "whole_infer" ]]; then
...
@@ -243,12 +247,12 @@ elif [[ ${MODE} = "whole_infer" ]]; then
cd
../../
cd
../../
fi
fi
# download inference or pretrained model
# download inference or pretrained model
eval
"wget -nc
$
model_url_value
"
eval
"wget -nc
$
{
model_url_value
}
"
if
[[
${
model_url_value
}
=
~
".tar"
]]
;
then
if
[[
${
model_url_value
}
=
~
".tar"
]]
;
then
tar_name
=
$(
func_get_url_file_name
"
${
model_url_value
}
"
)
tar_name
=
$(
func_get_url_file_name
"
${
model_url_value
}
"
)
echo
$
tar_name
echo
$
{
tar_name
}
rm
-rf
{
tar_name
}
eval
"tar -xf
${
tar_name
}
"
tar
x
f
${
tar_name
}
rm
-
f
${
tar_name
}
fi
fi
if
[[
$model_name
==
"SwinTransformer_large_patch4_window7_224"
||
$model_name
==
"SwinTransformer_large_patch4_window12_384"
]]
;
then
if
[[
$model_name
==
"SwinTransformer_large_patch4_window7_224"
||
$model_name
==
"SwinTransformer_large_patch4_window12_384"
]]
;
then
cmd
=
"mv
${
model_name
}
_22kto1k_pretrained.pdparams
${
model_name
}
_pretrained.pdparams"
cmd
=
"mv
${
model_name
}
_22kto1k_pretrained.pdparams
${
model_name
}
_pretrained.pdparams"
...
@@ -278,7 +282,7 @@ fi
...
@@ -278,7 +282,7 @@ fi
if
[[
${
MODE
}
=
"serving_infer"
]]
;
then
if
[[
${
MODE
}
=
"serving_infer"
]]
;
then
# prepare serving env
# prepare serving env
python_name
=
$(
func_parser_value
"
${
lines
[2]
}
"
)
python_name
=
$(
func_parser_value
"
${
lines
[2]
}
"
)
if
[[
${
model_name
}
=
"PPShiTu"
]]
;
then
if
[[
${
model_name
}
=
~
"PPShiTu"
]]
;
then
cls_inference_model_url
=
$(
func_parser_value
"
${
lines
[3]
}
"
)
cls_inference_model_url
=
$(
func_parser_value
"
${
lines
[3]
}
"
)
cls_tar_name
=
$(
func_get_url_file_name
"
${
cls_inference_model_url
}
"
)
cls_tar_name
=
$(
func_get_url_file_name
"
${
cls_inference_model_url
}
"
)
det_inference_model_url
=
$(
func_parser_value
"
${
lines
[4]
}
"
)
det_inference_model_url
=
$(
func_parser_value
"
${
lines
[4]
}
"
)
...
@@ -286,6 +290,8 @@ if [[ ${MODE} = "serving_infer" ]]; then
...
@@ -286,6 +290,8 @@ if [[ ${MODE} = "serving_infer" ]]; then
cd
./deploy
cd
./deploy
wget
-nc
https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/data/drink_dataset_v1.0.tar
--no-check-certificate
wget
-nc
https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/data/drink_dataset_v1.0.tar
--no-check-certificate
tar
-xf
drink_dataset_v1.0.tar
tar
-xf
drink_dataset_v1.0.tar
wget
-nc
https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/data/drink_dataset_v2.0.tar
--no-check-certificate
tar
-xf
drink_dataset_v2.0.tar
mkdir
models
mkdir
models
cd
models
cd
models
wget
-nc
${
cls_inference_model_url
}
&&
tar
xf
${
cls_tar_name
}
wget
-nc
${
cls_inference_model_url
}
&&
tar
xf
${
cls_tar_name
}
...
@@ -319,6 +325,7 @@ if [[ ${MODE} = "paddle2onnx_infer" ]]; then
...
@@ -319,6 +325,7 @@ if [[ ${MODE} = "paddle2onnx_infer" ]]; then
inference_model_url
=
$(
func_parser_value
"
${
lines
[10]
}
"
)
inference_model_url
=
$(
func_parser_value
"
${
lines
[10]
}
"
)
tar_name
=
${
inference_model_url
##*/
}
tar_name
=
${
inference_model_url
##*/
}
${
python_name
}
-m
pip
install
onnx
${
python_name
}
-m
pip
install
paddle2onnx
${
python_name
}
-m
pip
install
paddle2onnx
${
python_name
}
-m
pip
install
onnxruntime
${
python_name
}
-m
pip
install
onnxruntime
if
[[
${
model_name
}
=
~
"GeneralRecognition"
]]
;
then
if
[[
${
model_name
}
=
~
"GeneralRecognition"
]]
;
then
...
@@ -335,14 +342,12 @@ if [[ ${MODE} = "paddle2onnx_infer" ]]; then
...
@@ -335,14 +342,12 @@ if [[ ${MODE} = "paddle2onnx_infer" ]]; then
rm
-rf
val_list.txt
rm
-rf
val_list.txt
ln
-s
demo_test.txt val_list.txt
ln
-s
demo_test.txt val_list.txt
cd
../../
cd
../../
eval
"wget -nc
$model_url_value
--no-check-certificate"
mv
general_PPLCNet_x2_5_pretrained_v1.0.pdparams GeneralRecognition_PPLCNet_x2_5_pretrained.pdparams
fi
fi
cd
deploy
cd
deploy
mkdir
models
mkdir
models
cd
models
cd
models
wget
-nc
${
inference_model_url
}
wget
-nc
${
inference_model_url
}
tar
xf
${
tar_name
}
eval
"tar -xf
${
tar_name
}
"
cd
../../
cd
../../
fi
fi
...
...
test_tipc/test_serving_infer_cpp.sh
浏览文件 @
456891c3
...
@@ -192,9 +192,19 @@ function func_serving_rec(){
...
@@ -192,9 +192,19 @@ function func_serving_rec(){
det_trans_model_cmd
=
"
${
python_interp
}
${
trans_model_py
}
${
set_dirname
}
${
set_model_filename
}
${
set_params_filename
}
${
set_serving_server
}
${
set_serving_client
}
"
det_trans_model_cmd
=
"
${
python_interp
}
${
trans_model_py
}
${
set_dirname
}
${
set_model_filename
}
${
set_params_filename
}
${
set_serving_server
}
${
set_serving_client
}
"
eval
${
det_trans_model_cmd
}
eval
${
det_trans_model_cmd
}
cp_prototxt_cmd
=
"cp ./paddleserving/recognition/preprocess/general_PPLCNet_x2_5_lite_v1.0_serving/*.prototxt
${
cls_serving_server_value
}
"
OLD_IFS
=
"
${
IFS
}
"
IFS
=
'/'
tmp_arr
=(
$cls_serving_server_value
)
lastIndex
=
$((${#
tmp_arr
[@]
}
-
1
))
cls_serving_server_dirname
=
"
${
tmp_arr
[lastIndex]
}
"
tmp_arr
=(
$cls_serving_client_value
)
lastIndex
=
$((${#
tmp_arr
[@]
}
-
1
))
cls_serving_client_dirname
=
"
${
tmp_arr
[lastIndex]
}
"
IFS
=
"
${
OLD_IFS
}
"
cp_prototxt_cmd
=
"cp ./paddleserving/recognition/preprocess/
${
cls_serving_server_dirname
}
/*.prototxt
${
cls_serving_server_value
}
"
eval
${
cp_prototxt_cmd
}
eval
${
cp_prototxt_cmd
}
cp_prototxt_cmd
=
"cp ./paddleserving/recognition/preprocess/
general_PPLCNet_x2_5_lite_v1.0_client
/*.prototxt
${
cls_serving_client_value
}
"
cp_prototxt_cmd
=
"cp ./paddleserving/recognition/preprocess/
${
cls_serving_client_dirname
}
/*.prototxt
${
cls_serving_client_value
}
"
eval
${
cp_prototxt_cmd
}
eval
${
cp_prototxt_cmd
}
cp_prototxt_cmd
=
"cp ./paddleserving/recognition/preprocess/picodet_PPLCNet_x2_5_mainbody_lite_v1.0_client/*.prototxt
${
det_serving_client_value
}
"
cp_prototxt_cmd
=
"cp ./paddleserving/recognition/preprocess/picodet_PPLCNet_x2_5_mainbody_lite_v1.0_client/*.prototxt
${
det_serving_client_value
}
"
eval
${
cp_prototxt_cmd
}
eval
${
cp_prototxt_cmd
}
...
...
test_tipc/test_serving_infer_python.sh
浏览文件 @
456891c3
...
@@ -311,7 +311,7 @@ echo "################### run test ###################"
...
@@ -311,7 +311,7 @@ echo "################### run test ###################"
export
Count
=
0
export
Count
=
0
IFS
=
"|"
IFS
=
"|"
if
[[
${
model_name
}
=
"PPShiTu"
]]
;
then
if
[[
${
model_name
}
=
~
"PPShiTu"
]]
;
then
func_serving_rec
func_serving_rec
else
else
func_serving_cls
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