logo

image-embedding
/
timm
repo-copy-icon

copied

Browse Source

Modify README

main
GuoRentong 3 years ago
parent
75f7215bdf
commit
7f98eca94f
1 changed files with 9 additions and 13 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. 22
      README.md

22
README.md
View File

@ -18,13 +18,13 @@ which maintains SOTA deep-learning models and tools in computer vision.
Load an image from path './towhee.jpg' Load an image from path './towhee.jpg'
and use the pretrained ResNet50 model ('resnet50') to generate an image embedding. and use the pretrained ResNet50 model ('resnet50') to generate an image embedding.
*Write the pipeline in simplified style*:
*Write the pipeline in simplified style:*
```python ```python
import towhee import towhee
towhee.glob('./towhee.jpg') \ towhee.glob('./towhee.jpg') \
.image_decode.cv2() \
.image_decode() \
.image_embedding.timm(model_name='resnet50') \ .image_embedding.timm(model_name='resnet50') \
.show() .show()
``` ```
@ -36,9 +36,9 @@ towhee.glob('./towhee.jpg') \
import towhee import towhee
towhee.glob['path']('./towhee.jpg') \ towhee.glob['path']('./towhee.jpg') \
.image_decode.cv2['path', 'img']() \
.image_decode['path', 'img']() \
.image_embedding.timm['img', 'vec'](model_name='resnet50') \ .image_embedding.timm['img', 'vec'](model_name='resnet50') \
.select('img', 'vec') \
.select['img', 'vec']() \
.show() .show()
``` ```
<img src="./result2.png" height="150px"/> <img src="./result2.png" height="150px"/>
@ -53,18 +53,17 @@ Create the operator via the following factory method
**Parameters:** **Parameters:**
***model_name***: *str*
***model_name:*** *str*
The model name in string. The default value is "resnet34". The model name in string. The default value is "resnet34".
Refer [Timm Docs](https://fastai.github.io/timmdocs/#List-Models-with-Pretrained-Weights) to get a full list of supported models. Refer [Timm Docs](https://fastai.github.io/timmdocs/#List-Models-with-Pretrained-Weights) to get a full list of supported models.
***num_classes***: *int*
***num_classes:*** *int*
The number of classes. The default value is 1000. The number of classes. The default value is 1000.
It is related to model and dataset. It is related to model and dataset.
***skip_preprocess***: *bool*
***skip_preprocess:*** *bool*
The flag to control whether to skip image preprocess. The flag to control whether to skip image preprocess.
The default value is False. The default value is False.
@ -78,18 +77,15 @@ In this case, input image data must be prepared in advance in order to properly
An image embedding operator takes a towhee image as input. An image embedding operator takes a towhee image as input.
It uses the pre-trained model specified by model name to generate an image embedding in ndarray. It uses the pre-trained model specified by model name to generate an image embedding in ndarray.
**Parameters:** **Parameters:**
***img***: *towhee.types.Image (a sub-class of numpy.ndarray)*
***img:*** *towhee.types.Image (a sub-class of numpy.ndarray)*
The decoded image data in numpy.ndarray. The decoded image data in numpy.ndarray.
**Returns**:
*numpy.ndarray*
**Returns:** *numpy.ndarray*
The image embedding extracted by model. The image embedding extracted by model.

Write Preview
Loading…
Cancel
Save