logo
Browse Source

Update README

Signed-off-by: shiyu22 <shiyu.chen@zilliz.com>
main
shiyu22 2 years ago
parent
commit
0ed4f9e04f
  1. 30
      README.md

30
README.md

@ -4,34 +4,34 @@ Authors: Kyle, shiyu22
## Overview
This pipeline is used to **extract the feature vector of the image**, first to normalize the image, and then to use the resnet50 model to generate the vector.
This pipeline is used to **extract the feature vector of the image**. First step is to normalize the image, and then use resnet50 model to generate the vector.
In fact, the pipeline runs by parsing [the yaml file](./image_embedding_resnet50.yaml), which declares some functions we call **Operator**, and the **DataFrame** required by each Operator. Next will introduce the interface, how to use it and how it works, have fun with it!
The pipeline parses [the yaml file](./image_embedding_resnet50.yaml), which declares some components we call **Operator** and **DataFrame**. Next, we will introduce the interface, show how to use it and how it works, have fun with it!
## Interface
`towhee.pipeline(task: str, fmc: FileManagerConfig = FileManagerConfig(), branch: str = 'main', force_download: bool = False)` [source](https://github.com/towhee-io/towhee/blob/main/towhee/__init__.py)
`towhee.pipeline(task: str, fmc: FileManagerConfig = FileManagerConfig(), branch: str = 'main', force_download: bool = False)` [\[source\]](https://github.com/towhee-io/towhee/blob/main/towhee/__init__.py)
**param:**
**params:**
- **task**(str), task name or pipeline repo name.
- **fmc**(FileManagerConfig), optional file manager config for the local instance, default is FileManagerConfig().
- **branch**(str), which branch to use for operators/pipelines on hub, defaults to 'main'.
- **force_download**(bool), whether to redownload pipeline and operators, default is False.
- **task**(str): task name or pipeline repo name.
- **fmc**(FileManagerConfig): optional, file manager config for the local instance, default is a default FileManagerConfig obejct.
- **branch**(str): optional, which branch to use for operators/pipelines on hub, defaults to 'main'.
- **force_download**(bool): optional, whether to redownload pipeline and operators, default is False.
**return:**
- **_PipelineWrapper**, which is a wrapper class around `Pipeline`.
- **_PipelineWrapper**, an instance of the wrapper class around `Pipeline`.
When we declare a pipeline object with a specific task, such as `towhee/image-embedding-resnet50` in this repo, it will run according to the Yaml file, and the input and output are as follows:
When we declare a pipeline object with a specific task, such as `towhee/image-embedding-resnet50` in this repo, it will run according to the Yaml file, and the input and output are:
**inputs:**
- **img_tensor**(PIL.Image), image to be embedded.
- **img_tensor**(PIL.Image), the image to be encoded.
**outputs:**
- **cnn**(numpy.ndarray), the embedding of image.
- **cnn**(numpy.ndarray), the embedding of the image.
## How to use
@ -41,7 +41,7 @@ When we declare a pipeline object with a specific task, such as `towhee/image-em
$ pip3 install towhee
```
> You can refer to [Getting Started with Towhee](towhee.io) for more details. If you have questions, you can [submit an issue to the towhee repository](https://github.com/towhee-io/towhee/issues).
> You can refer to [Getting Started with Towhee](towhee.io) for more details. If you have any questions, you can [submit an issue to the towhee repository](https://github.com/towhee-io/towhee/issues).
2. Run it with Towhee
@ -49,7 +49,7 @@ $ pip3 install towhee
>>> from towhee import pipeline
>>> from PIL import Image
>>> img = Image.open('./test_data/test.jpg')
>>> img = Image.open('path/to/your/image')
>>> embedding_pipeline = pipeline('towhee/image-embedding-resnet50')
>>> embedding = embedding_pipeline(img)
```
@ -62,7 +62,7 @@ First of all, you need to learn the pipeline and operator in Towhee architecture
- **Operator**: An `Operator` is a single node within a pipeline. It contains files (e.g. code, configs, models, etc...) and works for reusable operations (e.g., preprocessing an image, inference with a pretrained model).
This pipeline includes four functions: `_start_op`, `towhee/transform-image`, `towhee/resnet50-image-embedding` and` _end_op`. It is necessary to ensure that the input and output of the four Operators correspond to each other, and the input and output data types can be defined by DataFrame.
This pipeline includes four functions: `_start_op`, `towhee/transform-image`, `towhee/resnet50-image-embedding` and ` _end_op`. It is necessary to ensure that the input and output of the four Operators correspond to each other, and the input and output data types can be defined by DataFrame.
![img](./pic/pipeline.png)

Loading…
Cancel
Save