copied
Readme
Files and versions
Updated 3 years ago
face-landmark-detection
MobileFaceNet Face Landmark Detector
author: David Wang
Description
MobileFaceNets is a class of extremely efficient CNN models to extract 68 landmarks from a facial image. It use less than 1 million parameters and is specifically tailored for high-accuracy real-time face verification on mobile and embedded devices. This repository is an adaptation from cuijian/pytorch_face_landmark.
Code Example
Extract facial landmarks from './img1.jpg'.
Write the pipeline in simplified style:
import towhee
towhee.glob('./img1.jpg') \
.image_decode.cv2() \
.face_landmark_detection.mobilefacenet() \
.select('img','landmark') \
.to_list()
Write a same pipeline with explicit inputs/outputs name specifications:
import towhee
towhee.glob['path']('./img1.jpg') \
.image_decode.cv2['path', 'img']() \
.face_landmark_detection.mobilefacenet['img', 'landmark']() \
.select['img','landmark']() \
.show()

Factory Constructor
Create the operator via the following factory method:
face_landmark_detection.mobilefacenet(pretrained = True)
Parameters:
pretrained
whether load the pre-trained weights.
supported types: bool
, default is True, using pre-trained weights.
Interface
An image embedding operator takes an image as input. it extracts the embedding as ndarray.
Parameters:
img: towhee.types.Image (a sub-class of numpy.ndarray)
The input image.
Returns: numpy.ndarray
The extracted facial landmarks.
| 8 Commits | ||
---|---|---|---|
|
1.1 KiB
|
3 years ago | |
|
1.8 KiB
|
3 years ago | |
|
711 B
|
3 years ago | |
|
2.5 KiB
|
3 years ago | |
|
5.9 KiB
|
3 years ago | |
|
12 MiB
|
3 years ago | |
|
47 B
|
3 years ago | |
|
137 KiB
|
3 years ago |