A PyTorch Implementation of SphereFace. The code can be trained on CASIA-Webface and the best accuracy on LFW is 99.22%.
SphereFace: Deep Hypersphere Embedding for Face Recognition
python train.py
# lfw.tgz to lfw.zip
tar zxf lfw.tgz; cd lfw; zip -r ../lfw.zip *; cd ..
# lfw evaluation
python lfw_eval.py --model model/sphere20a_20171020.pth
| Model name | LFW accuracy | Training dataset |
|---|---|---|
| 20171020 | 0.9922 | CASIA-WebFace |
LightningFSL: Few-Shot Learning with Pytorch-Lightning In this repo, a number of pytorch-lightning implementations of FSL algorithms are provided, inc
StyleTransfer - Open source style transfer project, based on VGG19
CompilerGym is a library of easy to use and performant reinforcement learning environments for compiler tasks
DeepXDE Voting on whether we should have a Slack channel for discussion. DeepXDE is a library for scientific machine learning. Use DeepXDE if you need
ECAENet: EfficientNet with Efficient Channel Attention for Plant Species Recognition (SCI:Q3) (Journal of Intelligent & Fuzzy Systems)
Documentation TensorFlow is an end-to-end open source platform for machine learning. It has a comprehensive, flexible ecosystem of tools, libraries, a
ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinement Recently, the power of unconditional image synthesis has significantly advanced th
Self-Guided Contrastive Learning for BERT Sentence Representations This repository is dedicated for releasing the implementation of the models utilize
HTSeq DEVS: https://github.com/htseq/htseq DOCS: https://htseq.readthedocs.io A Python library to facilitate programmatic analysis of data from high-t
Defocus Map Estimation and Deblurring from a Single Dual-Pixel Image This repository is an implementation of the method described in the following pap
Look Who's Talking: Active Speaker Detection in the Wild Dependencies pip install -r requirements.txt In addition to the Python dependencies, ffmpeg
ContextNet ContextNet has CNN-RNN-transducer architecture and features a fully convolutional encoder that incorporates global context information into
Point Cloud ToolBox This point cloud processing tool library can be used to process point clouds, 3d meshes, and voxels. Environment python 3.7.5 Dep
Blender add-ons for SMPL skeleton's poses and trans There are two blender add-ons for SMPL skeleton's poses and trans.The first is for making an offli
GAN JAX - A toy project to generate images from GANs with JAX This project aims to bring the power of JAX, a Python framework developped by Google and
large-scale-ITE-UM-benchmark This repository contains code and data to reproduce the results of the paper "A Large Scale Benchmark for Individual Trea
Rendering of live Jupyter notebooks with interactive widgets. Introduction Voilà turns Jupyter notebooks into standalone web applications. Unlike the
iGAN: Interactive Image Generation via Generative Adversarial Networks Project | Youtube | Paper Recent projects: [pix2pix]: Torch implementation for
This is the face property train code of project face-detection-project
moporgic/TDL2048+ TDL2048+ is a highly optimized temporal difference (TD) learning framework for 2048. Features Many common methods related to 2048 ar
76 Dec 11, 2022
9 Dec 13, 2021
721 Jan 03, 2023
1.4k Dec 29, 2022
4 Dec 22, 2022
170.1k Jan 04, 2023
967 Jan 04, 2023
16 Dec 04, 2022
57 Dec 20, 2022
21 Dec 15, 2022
60 Dec 08, 2022
24 Nov 24, 2022
40 Dec 09, 2022
154 Jan 04, 2023
14 Nov 29, 2022
10 Nov 19, 2022
4.5k Jan 03, 2023
3.9k Dec 23, 2022
2 Oct 18, 2021
5 Nov 23, 2022