timm/README.md

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: 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 numpy.ndarray in shape of (batch_num, feature_dim).