[Cherry-pick] Some fixes in HubServing and whl. (#1056)

* Fix params format

* Add preprocess in HubServing

* Fix printing prediction

* Supplement some fixes

deploy/hubserving/clas/params.py

@@ -33,8 +33,10 @@ def get_default_confg():
             "enable_benchmark": False
         },
         'PostProcess': {
-            'name': 'Topk',
-            'topk': 5,
-            'class_id_map_file': './utils/imagenet1k_label_list.txt'
+            'main_indicator': 'Topk',
+            'Topk': {
+                'topk': 5,
+                'class_id_map_file': './utils/imagenet1k_label_list.txt'
+            }
         }
-    }
\ No newline at end of file
+    }

deploy/hubserving/readme.md

@@ -15,7 +15,7 @@ hubserving/clas/
 ### 1. 准备环境
 ```shell
 # 安装paddlehub,请安装2.0版本
-pip3 install paddlehub==2.0.0b1 --upgrade -i https://pypi.tuna.tsinghua.edu.cn/simple
+pip3 install paddlehub==2.1.0 --upgrade -i https://pypi.tuna.tsinghua.edu.cn/simple
 ```
 
 ### 2. 下载推理模型
@@ -128,8 +128,12 @@ python hubserving/test_hubserving.py server_url image_path
 `http://[ip_address]:[port]/predict/[module_name]`  
 - **image_path**：测试图像路径，可以是单张图片路径，也可以是图像集合目录路径。
 - **batch_size**：[**可选**] 以`batch_size`大小为单位进行预测，默认为`1`。
+- **resize_short**：[**可选**] 预处理时，按短边调整大小，默认为`256`。
+- **crop_size**：[**可选**] 预处理时，居中裁剪的大小，默认为`224`。
+- **normalize**：[**可选**] 预处理时，是否进行`normalize`，默认为`True`。
+- **to_chw**：[**可选**] 预处理时，是否调整为`CHW`顺序，默认为`True`。
 
-**注意**：如果使用`Transformer`系列模型，如`DeiT_***_384`, `ViT_***_384`等，请注意模型的输入数据尺寸。需要指定`--resize_short=384 --resize=384`。
+**注意**：如果使用`Transformer`系列模型，如`DeiT_***_384`, `ViT_***_384`等，请注意模型的输入数据尺寸，需要指定`--resize_short=384 --crop_size=384`。
 
 
 访问示例：  

deploy/hubserving/readme_en.md

@@ -15,7 +15,7 @@ hubserving/clas/
 ### 1. Prepare the environment
 ```shell
 # Install version 2.0 of PaddleHub  
-pip3 install paddlehub==2.0.0b1 --upgrade -i https://pypi.tuna.tsinghua.edu.cn/simple
+pip3 install paddlehub==2.1.0 --upgrade -i https://pypi.tuna.tsinghua.edu.cn/simple
 ```
 
 ### 2. Download inference model
@@ -126,9 +126,13 @@ Two required parameters need to be passed to the script:
 `http://[ip_address]:[port]/predict/[module_name]`  
 - **image_path**: Test image path, can be a single image path or an image directory path
 - **batch_size**: [**Optional**] batch_size. Default by `1`.
+- **resize_short**: [**Optional**] In preprocessing, resize according to short size. Default by `256`。
+- **crop_size**: [**Optional**] In preprocessing, centor crop size. Default by `224`。
+- **normalize**: [**Optional**] In preprocessing, whether to do `normalize`. Default by `True`。
+- **to_chw**: [**Optional**] In preprocessing, whether to transpose to `CHW`. Default by `True`。
 
 **Notice**:
-If you want to use `Transformer series models`, such as `DeiT_***_384`, `ViT_***_384`, etc., please pay attention to the input size of model, and need to set `--resize_short=384`, `--resize=384`.
+If you want to use `Transformer series models`, such as `DeiT_***_384`, `ViT_***_384`, etc., please pay attention to the input size of model, and need to set `--resize_short=384`, `--crop_size=384`.
 
 **Eg.**
 ```shell

deploy/hubserving/test_hubserving.py

@@ -32,30 +32,59 @@ from utils import config
 from utils.encode_decode import np_to_b64
 from python.preprocess import create_operators
 
-preprocess_config = [{
-    'ResizeImage': {
-        'resize_short': 256
-    }
-}, {
-    'CropImage': {
-        'size': 224
-    }
-}, {
-    'NormalizeImage': {
-        'scale': 0.00392157,
-        'mean': [0.485, 0.456, 0.406],
-        'std': [0.229, 0.224, 0.225],
-        'order': ''
-    }
-}, {
-    'ToCHWImage': None
-}]
+
+def get_args():
+    def str2bool(v):
+        return v.lower() in ("true", "t", "1")
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--server_url", type=str)
+    parser.add_argument("--image_file", type=str)
+    parser.add_argument("--batch_size", type=int, default=1)
+    parser.add_argument("--resize_short", type=int, default=256)
+    parser.add_argument("--crop_size", type=int, default=224)
+    parser.add_argument("--normalize", type=str2bool, default=True)
+    parser.add_argument("--to_chw", type=str2bool, default=True)
+    return parser.parse_args()
+
+
+class PreprocessConfig(object):
+    def __init__(self,
+                 resize_short=256,
+                 crop_size=224,
+                 normalize=True,
+                 to_chw=True):
+        self.config = [{
+            'ResizeImage': {
+                'resize_short': resize_short
+            }
+        }, {
+            'CropImage': {
+                'size': crop_size
+            }
+        }]
+        if normalize:
+            self.config.append({
+                'NormalizeImage': {
+                    'scale': 0.00392157,
+                    'mean': [0.485, 0.456, 0.406],
+                    'std': [0.229, 0.224, 0.225],
+                    'order': ''
+                }
+            })
+        if to_chw:
+            self.config.append({'ToCHWImage': None})
+
+    def __call__(self):
+        return self.config
 
 
 def main(args):
     image_path_list = get_image_list(args.image_file)
     headers = {"Content-type": "application/json"}
-    preprocess_ops = create_operators(preprocess_config)
+    preprocess_ops = create_operators(
+        PreprocessConfig(args.resize_short, args.crop_size, args.normalize,
+                         args.to_chw)())
 
     cnt = 0
     predict_time = 0
@@ -113,14 +142,10 @@ def main(args):
 
                 for number, result_list in enumerate(preds):
                     all_score += result_list["scores"][0]
-                    result_str = ""
-                    for i in range(len(result_list["class_ids"])):
-                        result_str += "{}: {:.2f}\t".format(
-                            result_list["class_ids"][i],
-                            result_list["scores"][i])
-
+                    pred_str = ", ".join(
+                        [f"{k}: {result_list[k]}" for k in result_list])
                     logger.info(
-                        f"File:{img_name_list[number]}, The result(s): {result_str}"
+                        f"File:{img_name_list[number]}, The result(s): {pred_str}"
                     )
 
             finally:
@@ -136,10 +161,5 @@ def main(args):
 
 
 if __name__ == '__main__':
-    parser = argparse.ArgumentParser()
-    parser.add_argument("--server_url", type=str)
-    parser.add_argument("--image_file", type=str)
-    parser.add_argument("--batch_size", type=int, default=1)
-    args = parser.parse_args()
-
+    args = get_args()
     main(args)

paddleclas.py

@@ -279,8 +279,13 @@ def args_cfg():
         "--save_dir",
         type=str,
         help="The directory to save prediction results as pre-label.")
-    parser.add_argument("--resize_short", type=int, default=256, help="")
-    parser.add_argument("--crop_size", type=int, default=224, help="")
+    parser.add_argument(
+        "--resize_short",
+        type=int,
+        default=256,
+        help="Resize according to short size.")
+    parser.add_argument(
+        "--crop_size", type=int, default=224, help="Centor crop size.")
 
     args = parser.parse_args()
     return vars(args)
@@ -407,7 +412,7 @@ class PaddleClas(object):
         Args:
             model_name: The model name supported by PaddleClas, default by None. If specified, override config.
             inference_model_dir: The directory that contained model file and params file to be used, default by None. If specified, override config.
-            use_gpu: Wheather use GPU, default by None. If specified, override config.
+            use_gpu: Whether use GPU, default by None. If specified, override config.
             batch_size: The batch size to pridict, default by None. If specified, override config.
             topk: Return the top k prediction results with the highest score.
         """
@@ -459,7 +464,7 @@ class PaddleClas(object):
 
         Args:
             input_data (str | NumPy.array): The path of image, or the directory containing images, or the URL of image from Internet.
-            print_pred (bool, optional): Wheather print the prediction result. Defaults to False.
+            print_pred (bool, optional): Whether print the prediction result. Defaults to False.
 
         Raises:
             ImageTypeError: Illegal input_data.
@@ -506,12 +511,12 @@ class PaddleClas(object):
                     preds = self.cls_predictor.postprocess(outputs,
                                                            img_path_list)
                     if print_pred and preds:
-                        for nu, pred in enumerate(preds):
+                        for pred in preds:
+                            filename = pred.pop("file_name")
                             pred_str = ", ".join(
                                 [f"{k}: {pred[k]}" for k in pred])
                             print(
-                                f"filename: {img_path_list[nu]}, top-{topk}, {pred_str}"
-                            )
+                                f"filename: {filename}, top-{topk}, {pred_str}")
 
                     img_list = []
                     img_path_list = []