logo
Browse Source

Update README

Signed-off-by: shiyu22 <shiyu.chen@zilliz.com>
main
shiyu22 3 years ago
parent
commit
e57956b94c
  1. 8
      README.md

8
README.md

@ -1,6 +1,6 @@
# Pipeline: Image Embedding using Resnet50
Authors: derekdqc, shiyu22
Authors: derekdqc
## Overview
@ -38,16 +38,14 @@ $ pip3 install towhee
>>> from towhee import pipeline
>>> from PIL import Image
>>> img = Image.open('path/to/your/image') # for example, './test.jpg'
>>> img = Image.open('path/to/your/image')
>>> embedding_pipeline = pipeline('towhee/image-embedding-resnet50')
>>> embedding = embedding_pipeline(img)
```
> This pipeline uses the resnet50 model, you can also change the parameters `resnet50` in the local file **~/.towhee/image_embedding_resnet50&towhee$main/image_embedding_resnet.yaml** to the `resnet101` model.
## How it works
This pipeline includes two main operators: [transform image](https://hub.towhee.io/towhee/transform-image-operator-class) (implemented as [towhee/transform-image](https://hub.towhee.io/towhee/transform-image)) and [image embedding](https://hub.towhee.io/towhee/image-embedding-operator-class) (implemented as [towhee/resnet-image-embedding](https://hub.towhee.io/towhee/resnet-image-embedding)). 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 two main operators: [transform image](https://hub.towhee.io/towhee/transform-image-operator-template) (implemented as [towhee/transform-image](https://hub.towhee.io/towhee/transform-image)) and [image embedding](https://hub.towhee.io/towhee/image-embedding-operator-template) (implemented as [towhee/resnet-image-embedding](https://hub.towhee.io/towhee/resnet-image-embedding)). 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.
> Refer [Towhee architecture](https://github.com/towhee-io/towhee#towhee-architecture) for basic concepts in Towhee: pipeline, operator, dataframe.

Loading…
Cancel
Save