Home / Python / Deep Learning

face detection and alignment

SSHA, SSH with Alignment Result How To Use 0. install mxnet and opencv for python version 1. clone SSHA git clone https://github.com/ElegantGod/SSHA 2. make cython cd S
Information
Category: Python / Deep Learning
Watchers: 10
Star: 144
Fork: 35
Last update: Jun 22, 2022
Resource links
https://github.com/ElegantGod/SSHA

SSHA, SSH with Alignment

Result

img0 img1 img2

How To Use

0. install mxnet and opencv for python version

1. clone SSHA

git clone https://github.com/ElegantGod/SSHA

2. make cython

cd SSHA && make

3. run it

python test_kpoint.py

FDDB

fddb

Reference:

Insightface

7 Open More issues
Closed

Training code ?

Do you release the training code of SSH with Alignment ?

opened Nov 12, 2018 by bruinxiong 4
Closed

Great work!

Hi, congrats for the great work!

Would you mind adding a bit of documentations of how to run it, what the dependencies are and general info on how to contribute to the project?

It would help a lot of people 👍

opened Oct 19, 2018 by mattmezza 2
Closed

Which dataset you use for training ？

hi,the pretrain model has very good performance on some image,it was a brilliant work. which dataset you use for the detection loss and which dataset you use for the key point loss?

opened Feb 22, 2019 by codeVerySlow 0
Open

detect is slow,Have you done a speed test?

env： gtx1080，cuda10

Our detection is second level，also 1face .

test1：

python test_kpoint.py [11:21:45] src/nnvm/legacy_json_util.cc:209: Loading symbol saved by previous version v1.3.0. Attempting to upgrade... [11:21:45] src/nnvm/legacy_json_util.cc:217: Symbol successfully upgraded! (900, 1200, 3) data.shape: (1, 3, 910, 1210) getting 1.0 32 0 9 (1, 3, 910, 1210) [11:21:48] src/operator/nn/./cudnn/./cudnn_algoreg-inl.h:97: Running performance tests to find the best convolution algorithm, this can take a while... (set the environment variable MXNET_CUDNN_AUTOTUNE_DEFAULT to 0 to disable) [11:21:54] src/operator/nn/./cudnn/./cudnn_algoreg-inl.h:97: Running performance tests to find the best convolution algorithm, this can take a while... (set the environment variable MXNET_CUDNN_AUTOTUNE_DEFAULT to 0 to disable) getting 1.0 16 3 9 (1, 3, 910, 1210) getting 1.0 8 6 9 (1, 3, 910, 1210) ('detection uses', 7.341606, 'seconds') ('find', 81, 'faces')

test2：

[11:27:31] src/nnvm/legacy_json_util.cc:209: Loading symbol saved by previous version v1.3.0. Attempting to upgrade... [11:27:31] src/nnvm/legacy_json_util.cc:217: Symbol successfully upgraded! (1160, 2000, 3) ('resize to', (936, 1608, 3)) data.shape: (1, 3, 936, 1608) getting 1.0 32 0 9 (1, 3, 936, 1608) [11:27:34] src/operator/nn/./cudnn/./cudnn_algoreg-inl.h:97: Running performance tests to find the best convolution algorithm, this can take a while... (set the environment variable MXNET_CUDNN_AUTOTUNE_DEFAULT to 0 to disable) [11:27:41] src/operator/nn/./cudnn/./cudnn_algoreg-inl.h:97: Running performance tests to find the best convolution algorithm, this can take a while... (set the environment variable MXNET_CUDNN_AUTOTUNE_DEFAULT to 0 to disable) getting 1.0 16 3 9 (1, 3, 936, 1608) getting 1.0 8 6 9 (1, 3, 936, 1608) ('detection uses', 8.548407, 'seconds') ('find', 13, 'faces')

test3：

[11:28:50] src/nnvm/legacy_json_util.cc:209: Loading symbol saved by previous version v1.3.0. Attempting to upgrade... [11:28:50] src/nnvm/legacy_json_util.cc:217: Symbol successfully upgraded! (972, 1094, 3) data.shape: (1, 3, 982, 1104) getting 1.0 32 0 9 (1, 3, 982, 1104) [11:28:54] src/operator/nn/./cudnn/./cudnn_algoreg-inl.h:97: Running performance tests to find the best convolution algorithm, this can take a while... (set the environment variable MXNET_CUDNN_AUTOTUNE_DEFAULT to 0 to disable) [11:29:00] src/operator/nn/./cudnn/./cudnn_algoreg-inl.h:97: Running performance tests to find the best convolution algorithm, this can take a while... (set the environment variable MXNET_CUDNN_AUTOTUNE_DEFAULT to 0 to disable) getting 1.0 16 3 9 (1, 3, 982, 1104) getting 1.0 8 6 9 (1, 3, 982, 1104) ('detection uses', 7.417773, 'seconds') ('find', 15, 'faces')

test4：

[13:47:35] src/nnvm/legacy_json_util.cc:209: Loading symbol saved by previous version v1.3.0. Attempting to upgrade... [13:47:35] src/nnvm/legacy_json_util.cc:217: Symbol successfully upgraded! (720, 856, 3) data.shape: (1, 3, 730, 866) getting 1.0 32 0 9 (1, 3, 730, 866) [13:47:39] src/operator/nn/./cudnn/./cudnn_algoreg-inl.h:97: Running performance tests to find the best convolution algorithm, this can take a while... (set the environment variable MXNET_CUDNN_AUTOTUNE_DEFAULT to 0 to disable) [13:47:44] src/operator/nn/./cudnn/./cudnn_algoreg-inl.h:97: Running performance tests to find the best convolution algorithm, this can take a while... (set the environment variable MXNET_CUDNN_AUTOTUNE_DEFAULT to 0 to disable) getting 1.0 16 3 9 (1, 3, 730, 866) getting 1.0 8 6 9 (1, 3, 730, 866) ('detection uses', 5.2321, 'seconds') ('find', 1, 'faces')

opened Dec 11, 2019 by dgc1 0
Open

How deploy to windows system

Thanks for your sharing. l have a problem when l want to deploy this to windows system, how to complie cython file in windows system? Can you help me, Thanks.

opened Sep 16, 2019 by 12345ayu 0
Open

why cv2.copyMakeBorder ?

Thanks for your sharing I want to ask why you do "cv2.copyMakeBorder" before detect in test_kpoint.py? I have no idea. Could you teach me? Thanks.

opened Jun 11, 2019 by robby258312 0
Open

How to train?

which dataset?how to train?

opened Mar 13, 2019 by FelixZhang7 0
Open

Check failed: e == CUDNN_STATUS_SUCCESS (2 vs. 0) cuDNN: CUDNN_STATUS_ALLOC_FAILED

hi thanks the great job. I have a problem when i wanna to inference the detector. follow is the error info:

"mxnet.base.MXNetError: [16:26:09] src/operator/nn/./cudnn/cudnn_convolution-inl.h:713: Check failed: e == CUDNN_STATUS_SUCCESS (2 vs. 0) cuDNN: CUDNN_STATUS_ALLOC_FAILED"

Do you have any idea about this?

opened Dec 6, 2018 by xibinyue 0
Open

Awful job

Dear author: I want to know what dataset and landmarks annotation form of you project, pleas tell me??

opened Nov 1, 2018 by wanjinchang 1

Contents

    ChanChiChoi papers about Face Detection; Face Alignment; Face Recognition && Face Identification && Face Verification && Face Representation; Face Reconstruction; Face Tracking; Face Super-Resolution && Face Deblurring; Face Generation && Face Synthesis; Face Transfer; Face Anti-Spoofing; Face Retrieval;
    SajjadAemmi Face Alignment using python
    a-akram-98 Face Library is a 100% python open source package for accurate and real-time face detection and recognition. The package is built over OpenCV and using famous models and algorithms for face detection and recognition tasks. Make face detection and recognition with only one line of code. The Library doesn't use heavy frameworks like TensorFlow, Keras and PyTorch so it makes it perfect for production.
    791136190 ncnn在Android的一个测试，包含了人脸检测(face detection)，人脸属性(face attributes)，人脸识别(face recognition)。
    vitoralbiero img2pose: Face Alignment and Detection via 6DoF, Face Pose Estimation
    tpys face detection alignment recognition reconstruction ...
    deepinx The MXNet Implementation of Stacked Hourglass and Stacked SAT for Robust 2D and 3D Face Alignment
    1996scarlet [ECCV 2020] Reimplementation of "Towards Fast, Accurate and Stable 3D Dense Face Alignment", face mesh, head pose, landmarks, and more.
    1adrianb :fire: 2D and 3D Face alignment library build using pytorch
    ShownX A collection of face related papers
    shaoanlu A collection of deep learning frameworks ported to Keras for face analysis.
    husaynhakeem A real-time face detection Android library
    THU-KEG Entity Alignment toolkit (EAkit), a lightweight, easy-to-use and highly extensible PyTorch implementation of many entity alignment algorithms.
    cuixing158 Lightweight face detection and recognition library, which can be recognized in real time on jetson/pc devices.
    aryarohit07 A memory efficient Android image transformation library providing cropping above Face Detection (Face Centering) for Picasso.
    blankWorld MTCNN Face Detection & Alignment
    Rock-100 Implementations of PCN (an accurate real-time rotation-invariant face detector) and other face-related algorithms
    Rock-100 Implementations of PCN (an accurate real-time rotation-invariant face detector) and other face-related algorithms
    esimov Pure Go face detection, pupil/eyes localization and facial landmark points detection library
    bairdzhang Source code for Robust Face Detection via Learning Small Faces on Hard Images
    Linzaer 💎 Detect , track and extract the optimal face in multi-target faces (exclude side face and select the optimal face).
    Share this repo

    Related Repos


    Deep Learning
    837
    An implementation of chunked, compressed, N-dimensional arrays for Python.
    zarr-developers Zarr Latest Release Package Status License Build Status Coverage Downloads Gitter Citation What is it? Zarr is a Python package providing an implement
     
    Deep Learning
    317
    Serverless proxy for Spark cluster
    Hydrospheredata Hydrosphere Mist Hydrosphere Mist is a serverless proxy for Spark cluster. Mist provides a new functional programming framework and deployment model f
     
    Deep Learning
    2.5k
    Distributed Tensorflow, Keras and PyTorch on Apache Spark/Flink & Ray
    intel-analytics Distributed TensorFlow, PyTorch, Keras and BigDL on Apache Spark & Ray Analytics Zoo is an open source Big Data AI platform, and includes the followin
     
    Deep Learning
    10
    Black-Scholes StarkNet Library
    araghava Cairo Black-Scholes Library Black-Scholes library implemented as a Cairo smart contract. All inputs, outputs, and internal calculations use 27-digit f
     
    Deep Learning
    5
    Motoko library to help create an append-only logger actor
    ninegua IC Logger This motoko library provides a module to help create an append-only logger actor. Usage You can use this library with the vessel package man
     
    Deep Learning
    4
    LeetCode_Solution
    ashishpatel26 LeetCode_Solution LeetCode: https://leetcode.com/problemset/all/ # Title Difficulty Colab Code 1 Two Sum Easy 2 Add Two Numbers Medium 3 Longest Subst
     
    Deep Learning
    4
    OCR-D wrapper for detectron2 based segmentation models
    bertsky ocrd_detectron2 OCR-D wrapper for detectron2 based segmentation models Introduction Installation Usage OCR-D processor interface ocrd-detectron2-segm
     
    Deep Learning
    134
    Check for LDAP protections regarding the relay of NTLM authentication
    zyn3rgy LDAP Relay Scan A tool to check Domain Controllers for LDAP server protections regarding the relay of NTLM authentication. If you're interested in the
     
    Deep Learning
    66
    Fuzzware's main repository. Start here to install.
    fuzzware-fuzzer Fuzzware Fuzzware is a project for automated, self-configuring fuzzing of firmware images. The idea of this project is to configure the memory ranges
     
    Deep Learning
    35
    Time Weighted Asset Mints
    abigger87 TWAM • Time Weighted Asset Mints A minting harness enabling time-weighted assets to determine minting prices. How it works Requirements: maxMintingAmo
     
    Deep Learning
    33
    A complete, self-contained example for training ImageNet at state-of-the-art speed with FF...
    libffcv ffcv ImageNet Training A minimal, single-file PyTorch ImageNet training script designed for hackability. Run train_imagenet.py to get... ...high accur
     
    Deep Learning
    33
    เอกสารประกอบการสอนทุกเนื้อหาในช่องยูทูป KongRuksiam Official
    kongruksiamza 📖 เอกสารประกอบการสอน (PDF) 🔏 Blockchain & Smart Contract Blockchain เบื้องต้น Smart Contract & Solidity เบื้องต้น 💻 Programming เขียนโปรแกรมภาษา Ja
     
    Deep Learning
    34
    Omnivore A Single Model for Many Visual Modalities
    facebookresearch Omnivore: A Single Model for Many Visual Modalities [paper][website] OMNIVORE is a single vision model for many different visual modalities. It learns
     
    Deep Learning
    30
    Python implementation of the Lox language from Robert Nystrom's Crafting Interpreters
    dabeaz pylox Python implementation of the Lox language from Robert Nystrom's Crafting Interpreters. https://craftinginterpreters.com. This only implements th
     
    Deep Learning
    29
    ParaGen is a PyTorch deep learning framework for parallel sequence generation.
    bytedance ParaGen ParaGen is a PyTorch deep learning framework for parallel sequence generation. Apart from sequence generation, ParaGen also enhances various N