Update

Signed-off-by: shiyu22 <shiyu.chen@zilliz.com>

README.md

@@ -8,7 +8,7 @@ Authors:
 
 This pipeline **cannot be run**, which is the **template for the image embedding pipeline class** and defines YAML template file for embedding images, as well as the standard inputs and outputs. You can complete the pipeline by filling in the parameters(`init_args`) of the Operator section in [image_embedding_pipeline_template.yaml](./image_embedding_pipeline_template.yaml) and update this README file. FYI, [image-embedding-resnet50](https://hub.towhee.io/towhee/image-embedding-resnet50) is based on this template.
 
-This pipeline is used to **extract the feature vector of the image**. It first normalizes the image and then uses a model to generate the vector.
+This pipeline is used to **extract the feature vector of the image**. It uses XX model to generate the vector.
 
 ## Interface
 
@@ -20,7 +20,7 @@ This pipeline is used to **extract the feature vector of the image**. It first n
 
 **Pipeline Output:**
 
-The pipeline returns a tuple `Tuple[('cnn', numpy.ndarray)]` containing following fields:
+The pipeline returns a tuple `Tuple[('feature_vector', numpy.ndarray)]` containing following fields:
 
 - feature_vector:
   - the embedding of input image
@@ -42,12 +42,12 @@ $ pip3 install towhee
 >>> from towhee import pipeline
 
 >>> embedding_pipeline = pipeline('user/repo_name')  #the pipeline repo, such as 'towhee/image-embedding-resnet50'
->>> embedding = embedding_pipeline('path/to/your/image')
+>>> embedding = embedding_pipeline('path/to/your/image') #such as './readme_res/pipeline.png'
 ```
 
 ## **How it works**
 
-This pipeline includes two main operators: [transform image](https://hub.towhee.io/towhee/transform-image-operator-template)  and [image embedding](https://hub.towhee.io/towhee/image-embedding-operator-template). The transform image operator will first convert the original image into a normalized format, such as with 512x512 resolutions. Then, the normalized image will be encoded via image embedding operator, and finally we get a feature vector of the given image.
+This pipeline includes one operator: [image embedding](https://hub.towhee.io/towhee/image-embedding-operator-template). The image will be encoded via image embedding operator, then we can get a feature vector of the given image.
 
 > Refer [Towhee architecture](https://github.com/towhee-io/towhee#towhee-architecture) for basic concepts in Towhee: pipeline, operator, dataframe.
 

image_embedding_pipeline_template.yaml

@@ -14,22 +14,6 @@ operators:
                 df: 'image'
         iter_info:
             type: map
-    -
-        name: 'preprocessing'
-        function: 'towhee/image-transform-template' #your transform-image repo name
-        tag: 'main' #tag to the repo, default is 'main'
-        init_args:
-            size:      #size of image, such as 256
-        inputs:
-            -
-                df: 'image'
-                name: 'img_path'
-                col: 0
-        outputs:
-            -
-                df: 'image_preproc'
-        iter_info:
-            type: map
     -
         name: embedding_model
         function: 'towhee/image-embedding-operator-template' #your image-embedding repo name
@@ -38,8 +22,8 @@ operators:
             model_name:  #model_name for image-embedding operator, such as 'resnet50'
         inputs:
             -
-                df: 'image_preproc'
-                name: 'img_tensor'
+                df: 'image'
+                name: 'img_path'
                 col: 0
         outputs:
             -
@@ -73,12 +57,6 @@ dataframes:
             -
                 name: 'img_path'
                 vtype: 'str'
-    -
-        name: 'image_preproc'
-        columns:
-            -
-                name: 'img_transformed'
-                vtype: 'torch.Tensor'
     -
         name: 'embedding'
         columns: