Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/Fei-Wang/insightface
implementation of insightface by using Tensorflow
https://github.com/Fei-Wang/insightface
arcface insightface retinaface tensorflow
Last synced: 3 months ago
JSON representation
implementation of insightface by using Tensorflow
- Host: GitHub
- URL: https://github.com/Fei-Wang/insightface
- Owner: Fei-Wang
- License: mit
- Archived: true
- Created: 2019-07-11T13:31:50.000Z (over 5 years ago)
- Default Branch: master
- Last Pushed: 2019-08-08T06:49:01.000Z (over 5 years ago)
- Last Synced: 2024-08-02T19:01:55.630Z (6 months ago)
- Topics: arcface, insightface, retinaface, tensorflow
- Language: Python
- Homepage:
- Size: 4.01 MB
- Stars: 104
- Watchers: 13
- Forks: 30
- Open Issues: 14
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- Awesome-Tensorflow2 - Fei-Wang/insightface
README
# Insightface-tf
### Intro
- This repositories is a reimplementation of Insightface([github](https://github.com/deepinsight/insightface))
- Training code is included, you can use your own data to train models
- We are trying to use new features and Hight Level APIs in TesnsorFlow, such as Keras, Eager Execution, tf.data and so on. The code can even run successful under TF2.0 with a little changes
- The recognition([github-recognition](https://github.com/Fei-Wang/insightface/tree/master/recognition)) with tf-1.14 has been reimplemented and the RetinaFace-tf will be upload soon### TODO List
- recognition
- Backbones
- _ResNet_v1 [done]_
- Losses
- _Arcface loss [done]_
- _Cosface loss [done]_
- _Sphereface loss [done]_
- _Triplet loss [done]_
- _Center loss [done]_
- _Training code [done]_
- _Evaluate [done]_
- Freeze to pb model [todo]
- RetinaFace [todo]### Running Environment
- TensorFlow1.14
- python 3.7
- numpy, pyyaml, matplotlib (Anaconda 3 recommended)