Merge pull request #1987 from TingquanGao/dev/pulc_whl_deploy

[WIP] feat: support PULC to deploy with whl

MANIFEST.in

 include LICENSE.txt
 include README.md
 include docs/en/whl_en.md
-recursive-include deploy/python predict_cls.py preprocess.py postprocess.py det_preprocess.py
+recursive-include deploy/python *.py
+recursive-include deploy/configs *.yaml
 recursive-include deploy/utils get_image_list.py config.py logger.py predictor.py
 
 recursive-include ppcls/ *.py *.txt
\ No newline at end of file

deploy/configs/PULC/traffic_sign/inference_traffic_sign.yaml

@@ -30,6 +30,6 @@ PostProcess:
   main_indicator: Topk
   Topk:
     topk: 5
-    class_id_map_file: "../dataset/traffic_sign/label_name_id.txt"
+    class_id_map_file: "../ppcls/utils/PULC_label_list/traffic_sign_label_list.txt"
   SavePreLabel:
     save_dir: ./pre_label/

docs/en/inference_deployment/whl_deploy_en.md

@@ -212,14 +212,14 @@ You can save the prediction result(s) as pre-label, only need to use `pre_label_
 ```python
 from paddleclas import PaddleClas
 clas = PaddleClas(model_name='ResNet50', save_dir='./output_pre_label/')
-infer_imgs = 'docs/images/inference_deployment/whl_' # it can be infer_imgs folder path which contains all of images you want to predict.
+infer_imgs = 'docs/images/' # it can be infer_imgs folder path which contains all of images you want to predict.
 result=clas.predict(infer_imgs)
 print(next(result))
 ```
 
 * CLI
 ```bash
-paddleclas --model_name='ResNet50' --infer_imgs='docs/images/inference_deployment/whl_' --save_dir='./output_pre_label/'
+paddleclas --model_name='ResNet50' --infer_imgs='docs/images/' --save_dir='./output_pre_label/'
 ```
 
 <a name="4.8"></a>

docs/zh_CN/inference_deployment/whl_deploy.md

@@ -18,7 +18,7 @@ PaddleClas 支持 Python Whl 包方式进行预测，目前 Whl 包方式仅支
    - [4.6 对 `NumPy.ndarray` 格式数据进行预测](#4.6)
    - [4.7 保存预测结果](#4.7)
    - [4.8 指定 label name](#4.8)
-   
+
 
 <a name="1"></a>
 ## 1. 安装 paddleclas
@@ -212,14 +212,14 @@ print(next(result))
 ```python
 from paddleclas import PaddleClas
 clas = PaddleClas(model_name='ResNet50', save_dir='./output_pre_label/')
-infer_imgs = 'docs/images/whl/' # it can be infer_imgs folder path which contains all of images you want to predict.
+infer_imgs = 'docs/images/' # it can be infer_imgs folder path which contains all of images you want to predict.
 result=clas.predict(infer_imgs)
 print(next(result))
 ```
 
 * CLI
 ```bash
-paddleclas --model_name='ResNet50' --infer_imgs='docs/images/whl/' --save_dir='./output_pre_label/'
+paddleclas --model_name='ResNet50' --infer_imgs='docs/images/' --save_dir='./output_pre_label/'
 ```
 
 <a name="4.8"></a>

ppcls/utils/PULC_label_list/text_image_orientation_label_list.txt

+0 0
+1 90
+2 180
+3 270

ppcls/utils/PULC_label_list/traffic_sign_label_list.txt

+0 pl80
+1 w9
+2 p6
+3 ph4.2
+4 i8
+5 w14
+6 w33
+7 pa13
+8 im
+9 w58
+10 pl90
+11 il70
+12 p5
+13 pm55
+14 pl60
+15 ip
+16 p11
+17 pdd
+18 wc
+19 i2r
+20 w30
+21 pmr
+22 p23
+23 pl15
+24 pm10
+25 pss
+26 w1
+27 p4
+28 w38
+29 w50
+30 w34
+31 pw3.5
+32 iz
+33 w39
+34 w11
+35 p1n
+36 pr70
+37 pd
+38 pnl
+39 pg
+40 ph5.3
+41 w66
+42 il80
+43 pb
+44 pbm
+45 pm5
+46 w24
+47 w67
+48 w49
+49 pm40
+50 ph4
+51 w45
+52 i4
+53 w37
+54 ph2.6
+55 pl70
+56 ph5.5
+57 i14
+58 i11
+59 p7
+60 p29
+61 pne
+62 pr60
+63 pm13
+64 ph4.5
+65 p12
+66 p3
+67 w40
+68 pl5
+69 w13
+70 pr10
+71 p14
+72 i4l
+73 pr30
+74 pw4.2
+75 w16
+76 p17
+77 ph3
+78 i9
+79 w15
+80 w35
+81 pa8
+82 pt
+83 pr45
+84 w17
+85 pl30
+86 pcs
+87 pctl
+88 pr50
+89 ph4.4
+90 pm46
+91 pm35
+92 i15
+93 pa12
+94 pclr
+95 i1
+96 pcd
+97 pbp
+98 pcr
+99 w28
+100 ps
+101 pm8
+102 w18
+103 w2
+104 w52
+105 ph2.9
+106 ph1.8
+107 pe
+108 p20
+109 w36
+110 p10
+111 pn
+112 pa14
+113 w54
+114 ph3.2
+115 p2
+116 ph2.5
+117 w62
+118 w55
+119 pw3
+120 pw4.5
+121 i12
+122 ph4.3
+123 phclr
+124 i10
+125 pr5
+126 i13
+127 w10
+128 p26
+129 w26
+130 p8
+131 w5
+132 w42
+133 il50
+134 p13
+135 pr40
+136 p25
+137 w41
+138 pl20
+139 ph4.8
+140 pnlc
+141 ph3.3
+142 w29
+143 ph2.1
+144 w53
+145 pm30
+146 p24
+147 p21
+148 pl40
+149 w27
+150 pmb
+151 pc
+152 i6
+153 pr20
+154 p18
+155 ph3.8
+156 pm50
+157 pm25
+158 i2
+159 w22
+160 w47
+161 w56
+162 pl120
+163 ph2.8
+164 i7
+165 w12
+166 pm1.5
+167 pm2.5
+168 w32
+169 pm15
+170 ph5
+171 w19
+172 pw3.2
+173 pw2.5
+174 pl10
+175 il60
+176 w57
+177 w48
+178 w60
+179 pl100
+180 pr80
+181 p16
+182 pl110
+183 w59
+184 w64
+185 w20
+186 ph2
+187 p9
+188 il100
+189 w31
+190 w65
+191 ph2.4
+192 pr100
+193 p19
+194 ph3.5
+195 pa10
+196 pcl
+197 pl35
+198 p15
+199 w7
+200 pa6
+201 phcs
+202 w43
+203 p28
+204 w6
+205 w3
+206 w25
+207 pl25
+208 il110
+209 p1
+210 w46
+211 pn-2
+212 w51
+213 w44
+214 w63
+215 w23
+216 pm20
+217 w8
+218 pmblr
+219 w4
+220 i5
+221 il90
+222 w21
+223 p27
+224 pl50
+225 pl65
+226 w61
+227 ph2.2
+228 pm2
+229 i3
+230 pa18
+231 pw4

ppcls/utils/cls_demo/person_label_list.txt

-0 nobody
-1 someone