Skip to content

Commit 456891c

Browse files
RainFrost1RainFrost1
authored
Merge pull request #2244 from HydrogenSulfate/add_ShiTuV2_tipc
【WIP】Add PP-ShiTuV2 TIPC
2 parents f52f7b9 + 4ee9dd4 commit 456891c

File tree

31 files changed

+421
-37
lines changed

31 files changed

+421
-37
lines changed

‎deploy/configs/inference_rec.yaml

Lines changed: 6 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -15,14 +15,15 @@ Global:
1515
RecPreProcess:
1616
transform_ops:
1717
- ResizeImage:
18-
resize_short: 256
19-
- CropImage:
20-
size: 224
18+
size: [224, 224]
19+
return_numpy: False
20+
interpolation: bilinear
21+
backend: cv2
2122
- NormalizeImage:
22-
scale: 0.00392157
23+
scale: 1.0/255.0
2324
mean: [0.485, 0.456, 0.406]
2425
std: [0.229, 0.224, 0.225]
25-
order: ""
26+
order: hwc
2627
- ToCHWImage:
2728

2829
RecPostProcess: null

‎deploy/paddleserving/recognition/test_cpp_serving_client.py

Lines changed: 0 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -113,7 +113,6 @@ def postprocess(fetch_dict, feature_normalize, det_boxes, searcher, id_map,
113113
batch=False)
114114

115115
# add retrieval procedure
116-
print(fetch_map.keys())
117116
det_boxes = fetch_map["boxes"]
118117
searcher, id_map = init_index(index_dir)
119118
results = postprocess(fetch_map, feature_normalize, det_boxes, searcher,

‎docs/zh_CN/image_recognition_pipeline/feature_extraction.md

Lines changed: 5 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -252,12 +252,12 @@ python3.7 python/predict_rec.py \
252252
得到的特征输出格式如下所示：
253253

254254
```log
255-
wangzai.jpg: [-4.72979844e-02 3.40038240e-02 -4.06982675e-02 2.46225717e-03
256-
9.67078656e-03 2.70162839e-02 -8.85589980e-03 -4.71983254e-02
257-
6.18615076e-02 1.38509814e-02 -1.11342799e-02 6.73768669e-02
258-
-1.03065455e-02 -4.88462113e-02 8.46387446e-03 1.57074817e-02
255+
wangzai.jpg: [-7.82453567e-02 2.55877394e-02 -3.66694555e-02 1.34572461e-02
256+
4.39076796e-02 -2.34078392e-02 -9.49947070e-03 1.28221214e-02
257+
5.53947650e-02 1.01355985e-02 -1.06436480e-02 4.97181974e-02
258+
-2.21862812e-02 -1.75557341e-02 1.55848479e-02 -3.33278324e-03
259259
...
260-
-3.14170569e-02 7.35917836e-02 -3.09373233e-02 -2.31755469e-02]
260+
-3.40284109e-02 8.35561901e-02 2.10910216e-02 -3.27066667e-02]
261261
```
262262

263263
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

Lines changed: 0 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -110,7 +110,6 @@ bash test_tipc/test_train_inference_python.sh ./test_tipc/configs/MobileNetV3/Mo
110110
- [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。
111111
- [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。
112112
- [test_inference_cpp 使用](docs/test_inference_cpp.md) ：测试基于C++的模型推理。
113-
- [test_serving 使用](docs/test_serving.md) ：测试基于Paddle Serving的服务化部署功能。
114113
- [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.
115114
- [test_paddle2onnx 使用](docs/test_paddle2onnx.md)：测试Paddle2ONNX的模型转化功能，并验证正确性。
116115
- [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

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -13,14 +13,14 @@ train_infer_img_dir:./dataset/ILSVRC2012/val
1313
null:null
1414
##
1515
trainer:norm_train
16-
norm_train:tools/train.py -c ppcls/configs/GeneralRecognition/GeneralRecognition_PPLCNet_x2_5.yaml -o DataLoader.Train.sampler.name="PKSampler" -o DataLoader.Train.sampler.sample_per_id=2
16+
norm_train:tools/train.py -c ppcls/configs/GeneralRecognition/GeneralRecognition_PPLCNet_x2_5.yaml -o DataLoader.Train.sampler.name="PKSampler" -o DataLoader.Train.sampler.sample_per_id=2
1717
pact_train:null
1818
fpgm_train:null
1919
distill_train:null
2020
null:null
2121
null:null
2222
##
23-
===========================eval_params===========================
23+
===========================eval_params===========================
2424
eval:null
2525
null:null
2626
##

‎test_tipc/configs/GeneralRecognition/GeneralRecognition_PPLCNet_x2_5_train_infer_python.txt

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -20,7 +20,7 @@ distill_train:null
2020
null:null
2121
null:null
2222
##
23-
===========================eval_params===========================
23+
===========================eval_params===========================
2424
eval:tools/eval.py -c ppcls/configs/GeneralRecognition/GeneralRecognition_PPLCNet_x2_5.yaml
2525
null:null
2626
##
@@ -37,7 +37,7 @@ pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/r
3737
infer_model:../inference/
3838
infer_export:True
3939
infer_quant:Fasle
40-
inference:python/predict_rec.py -c configs/inference_rec.yaml
40+
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"
4141
-o Global.use_gpu:True|False
4242
-o Global.enable_mkldnn:False
4343
-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

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -37,7 +37,7 @@ pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/r
3737
infer_model:../inference/
3838
infer_export:True
3939
infer_quant:Fasle
40-
inference:python/predict_rec.py -c configs/inference_rec.yaml
40+
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"
4141
-o Global.use_gpu:True|False
4242
-o Global.enable_mkldnn:False
4343
-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

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -37,7 +37,7 @@ pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/r
3737
infer_model:../inference/
3838
infer_export:True
3939
infer_quant:Fasle
40-
inference:python/predict_rec.py -c configs/inference_rec.yaml
40+
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"
4141
-o Global.use_gpu:True|False
4242
-o Global.enable_mkldnn:False
4343
-o Global.cpu_num_threads:6

‎test_tipc/configs/GeneralRecognition/GeneralRecognition_PPLCNet_x2_5_train_multicard_eval.txt

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -20,7 +20,7 @@ distill_train:null
2020
null:null
2121
null:null
2222
##
23-
===========================eval_params===========================
23+
===========================eval_params===========================
2424
eval:null
2525
null:null
2626
##

‎test_tipc/configs/GeneralRecognition/GeneralRecognition_PPLCNet_x2_5_train_no_eval.txt

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -20,7 +20,7 @@ distill_train:null
2020
null:null
2121
null:null
2222
##
23-
===========================eval_params===========================
23+
===========================eval_params===========================
2424
eval:null
2525
null:null
2626
##

‎test_tipc/configs/GeneralRecognition/GeneralRecognition_PPLCNet_x2_5_train_pact_infer_python.txt

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -37,7 +37,7 @@ pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/r
3737
infer_model:../inference/
3838
infer_export:True
3939
infer_quant:Fasle
40-
inference:python/predict_rec.py -c configs/inference_rec.yaml
40+
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"
4141
-o Global.use_gpu:True|False
4242
-o Global.enable_mkldnn:False
4343
-o Global.cpu_num_threads:1

‎test_tipc/configs/GeneralRecognition/GeneralRecognition_PPLCNet_x2_5_train_ptq_infer_python.txt

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -20,7 +20,7 @@ distill_train:null
2020
null:null
2121
null:null
2222
##
23-
===========================eval_params===========================
23+
===========================eval_params===========================
2424
eval:tools/eval.py -c ppcls/configs/GeneralRecognition/GeneralRecognition_PPLCNet_x2_5.yaml
2525
null:null
2626
##
@@ -37,7 +37,7 @@ pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/r
3737
infer_model:./general_PPLCNet_x2_5_lite_v1.0_infer/
3838
infer_export:True
3939
infer_quant:Fasle
40-
inference:python/predict_rec.py -c configs/inference_rec.yaml
40+
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"
4141
-o Global.use_gpu:True|False
4242
-o Global.enable_mkldnn:False
4343
-o Global.cpu_num_threads:1

‎test_tipc/configs/GeneralRecognitionV2/GeneralRecognitionV2_PPLCNetV2_base_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt

Lines changed: 16 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,16 @@
1+
===========================paddle2onnx_params===========================
2+
model_name:GeneralRecognitionV2_PPLCNetV2_base
3+
python:python3.7
4+
2onnx: paddle2onnx
5+
--model_dir:./deploy/models/general_PPLCNetV2_base_pretrained_v1.0_infer/
6+
--model_filename:inference.pdmodel
7+
--params_filename:inference.pdiparams
8+
--save_file:./deploy/models/general_PPLCNetV2_base_pretrained_v1.0_infer/inference.onnx
9+
--opset_version:10
10+
--enable_onnx_checker:True
11+
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
12+
inference:./python/predict_rec.py
13+
Global.use_onnx:True
14+
Global.rec_inference_model_dir:./models/general_PPLCNetV2_base_pretrained_v1.0_infer
15+
Global.use_gpu:False
16+
-c:configs/inference_rec.yaml

‎test_tipc/configs/GeneralRecognitionV2/GeneralRecognitionV2_PPLCNetV2_base_train_infer_python.txt

Lines changed: 60 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,60 @@
1+
===========================train_params===========================
2+
model_name:GeneralRecognitionV2_PPLCNetV2_base
3+
python:python3.7
4+
gpu_list:0|0,1
5+
-o Global.device:gpu
6+
-o Global.auto_cast:null
7+
-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120
8+
-o Global.output_dir:./output/
9+
-o DataLoader.Train.sampler.batch_size:8
10+
-o Global.pretrained_model:null
11+
train_model_name:latest
12+
train_infer_img_dir:./dataset/ILSVRC2012/val
13+
null:null
14+
##
15+
trainer:norm_train
16+
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
17+
pact_train:null
18+
fpgm_train:null
19+
distill_train:null
20+
null:null
21+
null:null
22+
##
23+
===========================eval_params===========================
24+
eval:tools/eval.py -c ppcls/configs/GeneralRecognitionV2/GeneralRecognitionV2_PPLCNetV2_base.yaml
25+
null:null
26+
##
27+
===========================infer_params==========================
28+
-o Global.save_inference_dir:./inference
29+
-o Global.pretrained_model:
30+
norm_export:tools/export_model.py -c ppcls/configs/GeneralRecognitionV2/GeneralRecognitionV2_PPLCNetV2_base.yaml
31+
quant_export:null
32+
fpgm_export:null
33+
distill_export:null
34+
kl_quant:null
35+
export2:null
36+
pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/models/pretrain/PPShiTuV2/general_PPLCNetV2_base_pretrained_v1.0.pdparams
37+
infer_model:../inference/
38+
infer_export:True
39+
infer_quant:Fasle
40+
inference:python/predict_rec.py -c configs/inference_rec.yaml
41+
-o Global.use_gpu:True|False
42+
-o Global.enable_mkldnn:False
43+
-o Global.cpu_num_threads:1
44+
-o Global.batch_size:1
45+
-o Global.use_tensorrt:False
46+
-o Global.use_fp16:False
47+
-o Global.rec_inference_model_dir:../inference
48+
-o Global.infer_imgs:../dataset/Aliproduct/demo_test/
49+
-o Global.save_log_path:null
50+
-o Global.benchmark:False
51+
null:null
52+
null:null
53+
===========================train_benchmark_params==========================
54+
batch_size:256
55+
fp_items:fp32|fp16
56+
epoch:1
57+
--profiler_options:batch_range=[10,20];state=GPU;tracer_option=Default;profile_path=model.profile
58+
flags:FLAGS_eager_delete_tensor_gb=0.0;FLAGS_fraction_of_gpu_memory_to_use=0.98;FLAGS_conv_workspace_size_limit=4096
59+
===========================infer_benchmark_params==========================
60+
random_infer_input:[{float32,[3,224,224]}]

‎test_tipc/configs/GeneralRecognitionV2/GeneralRecognitionV2_PPLCNetV2_base_train_linux_gpu_fleet_normal_infer_python_linux_gpu_cpu.txt

Lines changed: 54 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,54 @@
1+
===========================train_params===========================
2+
model_name:GeneralRecognition_PPLCNet_x2_5
3+
python:python3.7
4+
gpu_list:192.168.0.1,192.168.0.2;0,1
5+
-o Global.device:gpu
6+
-o Global.auto_cast:null
7+
-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=120
8+
-o Global.output_dir:./output/
9+
-o DataLoader.Train.sampler.batch_size:8
10+
-o Global.pretrained_model:null
11+
train_model_name:latest
12+
train_infer_img_dir:./dataset/ILSVRC2012/val
13+
null:null
14+
##
15+
trainer:norm_train
16+
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
17+
pact_train:null
18+
fpgm_train:null
19+
distill_train:null
20+
null:null
21+
null:null
22+
##
23+
===========================eval_params===========================
24+
eval:tools/eval.py -c ppcls/configs/GeneralRecognitionV2/GeneralRecognitionV2_PPLCNetV2_base.yaml
25+
null:null
26+
##
27+
===========================infer_params==========================
28+
-o Global.save_inference_dir:./inference
29+
-o Global.pretrained_model:
30+
norm_export:tools/export_model.py -c ppcls/configs/GeneralRecognitionV2/GeneralRecognitionV2_PPLCNetV2_base.yaml
31+
quant_export:null
32+
fpgm_export:null
33+
distill_export:null
34+
kl_quant:null
35+
export2:null
36+
pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/models/pretrain/PPShiTuV2/general_PPLCNetV2_base_pretrained_v1.0.pdparams
37+
infer_model:../inference/
38+
infer_export:True
39+
infer_quant:Fasle
40+
inference:python/predict_rec.py -c configs/inference_rec.yaml
41+
-o Global.use_gpu:True|False
42+
-o Global.enable_mkldnn:False
43+
-o Global.cpu_num_threads:1
44+
-o Global.batch_size:1
45+
-o Global.use_tensorrt:False
46+
-o Global.use_fp16:False
47+
-o Global.rec_inference_model_dir:../inference
48+
-o Global.infer_imgs:../dataset/Aliproduct/demo_test/
49+
-o Global.save_log_path:null
50+
-o Global.benchmark:False
51+
null:null
52+
null:null
53+
===========================infer_benchmark_params==========================
54+
random_infer_input:[{float32,[3,224,224]}]

‎test_tipc/configs/GeneralRecognitionV2/GeneralRecognitionV2_PPLCNetV2_base_train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt

Lines changed: 52 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,52 @@
1+
===========================train_params===========================
2+
model_name:GeneralRecognitionV2_PPLCNetV2_base
3+
python:python3.7
4+
gpu_list:0|0,1
5+
-o Global.device:gpu
6+
-o Global.auto_cast:null
7+
-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=100
8+
-o Global.output_dir:./output/
9+
-o DataLoader.Train.sampler.batch_size:8
10+
-o Global.pretrained_model:null
11+
train_model_name:latest
12+
train_infer_img_dir:./dataset/ILSVRC2012/val
13+
null:null
14+
##
15+
trainer:amp_train
16+
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
17+
pact_train:null
18+
fpgm_train:null
19+
distill_train:null
20+
null:null
21+
null:null
22+
##
23+
===========================eval_params===========================
24+
eval:tools/eval.py -c ppcls/configs/GeneralRecognitionV2/GeneralRecognitionV2_PPLCNetV2_base.yaml
25+
null:null
26+
##
27+
===========================infer_params==========================
28+
-o Global.save_inference_dir:./inference
29+
-o Global.pretrained_model:
30+
norm_export:tools/export_model.py -c ppcls/configs/GeneralRecognitionV2/GeneralRecognitionV2_PPLCNetV2_base.yaml
31+
quant_export:null
32+
fpgm_export:null
33+
distill_export:null
34+
kl_quant:null
35+
export2:null
36+
pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/models/pretrain/PPShiTuV2/general_PPLCNetV2_base_pretrained_v1.0.pdparams
37+
infer_model:../inference/
38+
infer_export:True
39+
infer_quant:Fasle
40+
inference:python/predict_rec.py -c configs/inference_rec.yaml
41+
-o Global.use_gpu:True|False
42+
-o Global.enable_mkldnn:False
43+
-o Global.cpu_num_threads:6
44+
-o Global.batch_size:1
45+
-o Global.use_tensorrt:False
46+
-o Global.use_fp16:False
47+
-o Global.rec_inference_model_dir:../inference
48+
-o Global.infer_imgs:../dataset/Aliproduct/demo_test/
49+
-o Global.save_log_path:null
50+
-o Global.benchmark:False
51+
null:null
52+
null:null

‎test_tipc/configs/GeneralRecognitionV2/GeneralRecognitionV2_PPLCNetV2_base_train_pact_infer_python.txt

Lines changed: 54 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,54 @@
1+
===========================train_params===========================
2+
model_name:GeneralRecognitionV2_PPLCNetV2_base
3+
python:python3.7
4+
gpu_list:0
5+
-o Global.device:gpu
6+
-o Global.auto_cast:null
7+
-o Global.epochs:lite_train_lite_infer=2|whole_train_whole_infer=100
8+
-o Global.output_dir:./output/
9+
-o DataLoader.Train.sampler.batch_size:8
10+
-o Global.pretrained_model:null
11+
train_model_name:latest
12+
train_infer_img_dir:./dataset/ILSVRC2012/val
13+
null:null
14+
##
15+
trainer:pact_train
16+
norm_train:null
17+
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
18+
fpgm_train:null
19+
distill_train:null
20+
null:null
21+
null:null
22+
##
23+
===========================eval_params===========================
24+
eval:tools/eval.py -c ppcls/configs/GeneralRecognitionV2/GeneralRecognitionV2_PPLCNetV2_base.yaml -o Slim.quant.name=pact
25+
null:null
26+
##
27+
===========================infer_params==========================
28+
-o Global.save_inference_dir:./inference
29+
-o Global.pretrained_model:
30+
norm_export:null
31+
quant_export:tools/export_model.py -c ppcls/configs/GeneralRecognitionV2/GeneralRecognitionV2_PPLCNetV2_base.yaml -o Slim.quant.name=pact
32+
fpgm_export:null
33+
distill_export:null
34+
kl_quant:null
35+
export2:null
36+
pretrained_model_url:https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/models/pretrain/PPShiTuV2/general_PPLCNetV2_base_pretrained_v1.0.pdparams
37+
infer_model:../inference/
38+
infer_export:True
39+
infer_quant:Fasle
40+
inference:python/predict_rec.py -c configs/inference_rec.yaml
41+
-o Global.use_gpu:True|False
42+
-o Global.enable_mkldnn:False
43+
-o Global.cpu_num_threads:1
44+
-o Global.batch_size:1
45+
-o Global.use_tensorrt:False
46+
-o Global.use_fp16:False
47+
-o Global.rec_inference_model_dir:../inference
48+
-o Global.infer_imgs:../dataset/Aliproduct/demo_test/
49+
-o Global.save_log_path:null
50+
-o Global.benchmark:True
51+
null:null
52+
null:null
53+
===========================infer_benchmark_params==========================
54+
random_infer_input:[{float32,[3,224,224]}]

0 commit comments

Comments
 (0)