logo
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
Readme
Files and versions

Updated 3 years ago

image-embedding

Image Embedding with Timm

author: Jael Gu, Filip


Description

An image embedding operator generates a vector given an image. This operator extracts features for image with pre-trained models provided by Timm. Timm is a deep-learning library developed by Ross Wightman, who maintains SOTA deep-learning models and tools in computer vision.


Code Example

Load an image from path './towhee.jpeg' and use the pre-trained ResNet50 model ('resnet50') to generate an image embedding.

Write the pipeline in simplified style:

import towhee

towhee.glob('./towhee.jpeg') \
      .image_decode() \
      .image_embedding.timm(model_name='resnet50') \
      .show()

Write a same pipeline with explicit inputs/outputs name specifications:

import towhee

towhee.glob['path']('./towhee.jpeg') \
      .image_decode['path', 'img']() \
      .image_embedding.timm['img', 'vec'](model_name='resnet50') \
      .select['img', 'vec']() \
      .show()


Factory Constructor

Create the operator via the following factory method:

image_embedding.timm(model_name='resnet34', num_classes=1000, skip_preprocess=False)

Parameters:

model_name: str

The model name in string. The default value is "resnet34". Refer to Timm Docs to get a full list of supported models.

num_classes: int

The number of classes. The default value is 1000. It is related to model and dataset.

skip_preprocess: bool

The flag to control whether to skip image pre-process. The default value is False. If set to True, it will skip image preprocessing steps (transforms). In this case, input image data must be prepared in advance in order to properly fit the model.


Interface

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.

Parameters:

data: Union[List[towhee._types.Image], towhee._types.Image]

The decoded image data in numpy.ndarray. It allows both single input and a list for batch input.

Returns: Union[List[numpy.ndarray], numpy.ndarray]

If only 1 image input, then output is an image embedding in shape of (feature_dim,). If a list of images as input, then output is a same-length list of numpy.ndarray, each of which represents an image embedding in shape of (feature_dim,).

Jael Gu 254ea6162e Update 50 Commits
file-icon .gitattributes
1.1 KiB
download-icon
Initial commit 3 years ago
file-icon README.md
2.6 KiB
download-icon
Update 3 years ago
file-icon __init__.py
680 B
download-icon
Update 3 years ago
file-icon requirements.txt
31 B
download-icon
add requirement 3 years ago
file-icon result1.png
4.0 KiB
download-icon
Update README 3 years ago
file-icon result2.png
80 KiB
download-icon
Update README 3 years ago
file-icon test_onnx.py
2.5 KiB
download-icon
update 3 years ago
file-icon test_torchscript.py
2.5 KiB
download-icon
update 3 years ago
file-icon timm_image.py
5.3 KiB
download-icon
Update 3 years ago
file-icon towhee.jpeg
49 KiB
download-icon
Add save_model & suppported_model_names 3 years ago