logo

towhee
/
image-embedding-resnet50
repo-copy-icon

copied

Browse Source

Update README 

Signed-off-by: shiyu22 <shiyu.chen@zilliz.com>
main
shiyu22 3 years ago
parent
8abea24e69
commit
e57956b94c
1 changed files with 3 additions and 5 deletions
Whitespace
Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL
Unified View
Diff Options
Show Stats Download Patch File Download Diff File
  1. 8
      README.md

8
README.md
View File

@ -1,6 +1,6 @@
# Pipeline: Image Embedding using Resnet50 # Pipeline: Image Embedding using Resnet50
Authors: derekdqc, shiyu22
Authors: derekdqc
## Overview ## Overview
@ -38,16 +38,14 @@ $ pip3 install towhee
>>> from towhee import pipeline >>> from towhee import pipeline
>>> from PIL import Image >>> 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_pipeline = pipeline('towhee/image-embedding-resnet50')
>>> embedding = embedding_pipeline(img) >>> 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 ## 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. > Refer [Towhee architecture](https://github.com/towhee-io/towhee#towhee-architecture) for basic concepts in Towhee: pipeline, operator, dataframe.

Write Preview
Loading…
Cancel
Save