add quantized module
add deploy module
quantized module is from https://github.com/woolpeeker/qqquantize.git
deploy module is from https://github.com/deepinsight/insightface/, python-package, deploy
-
git clone qqquantize module into root directory,
-
use tools/load_images_from_bin.py generate dataset from insightface .bin or .rec files.
-
use train.py train a model
-
use train_quant.py quantize the model
-
tools_deploy目录下面有转换onnx和onnx转换caffe的代码 先执行output_quantized_onnx.py生成onnx文件,然后用onnx2caffe里的convertCaffe.py将onnx文件转换为caffe文件
2019.07.14
Currently, I have graduated from campus and doing another kind of job. So this project may not be updated again.
The implementation of popular face recognition algorithms in pytorch framework, including arcface, cosface and sphereface and so on.
All codes are evaluated on Pytorch 0.4.0 with Python 3.6, Ubuntu 16.04.10, CUDA 9.1 and CUDNN 7.1. Partially evaluated on Pytorch 1.0.
For CNN training, I use CASIA-WebFace and Cleaned MS-Celeb-1M, aligned by MTCNN with the size of 112x112. For performance testing, I report the results on LFW, AgeDB-30, CFP-FP, MegaFace rank1 identification and verification.
For AgeDB-30 and CFP-FP, the aligned images and evaluation images pairs are restored from the mxnet binary file provided by insightface, tools are available in this repository. You should install a mxnet-cpu first for the image parsing, just do ' pip install mxnet ' is ok.
LFW @ BaiduNetdisk, AgeDB-30 @ BaiduNetdisk, CFP_FP @ BaiduNetdisk
MobileFaceNet: Struture described in MobileFaceNet
ResNet50: Original resnet structure
ResNet50-IR: CNN described in ArcFace paper
SEResNet50-IR: CNN described in ArcFace paper
Small Protocol: trained with CASIA-WebFace of data size: 453580/10575
Large Protocol: trained with DeepGlint MS-Celeb-1M of data size: 3923399/86876
Model Type | Loss | LFW | AgeDB-30 | CFP-FP | Model Size | protocol |
---|---|---|---|---|---|---|
MobileFaceNet | ArcFace | 99.23 | 93.26 | 94.34 | 4MB | small |
ResNet50-IR | ArcFace | 99.42 | 94.45 | 95.34 | 170MB | small |
SEResNet50-IR | ArcFace | 99.43 | 94.50 | 95.43 | 171MB | small |
MobileFaceNet | ArcFace | 99.58 | 96.57 | 92.90 | 4MB | large |
ResNet50-IR | ArcFace | 99.82 | 98.07 | 95.34 | 170MB | large |
SEResNet50-IR | ArcFace | 99.80 | 98.13 | 95.60 | 171MB | large |
ResNet100-IR | ArcFace | 99.83 | 98.28 | 96.41 | 256MB | large |
There exists an odd result fact that when training under small protocol, CFP-FP performances better than AgeDB-30, while when training with large scale dataset, CFP-FP performances worse than AgeDB-30.
Model Type | Loss | MF Acc. | MF Ver. | MF Acc.@R | MF Ver.@R | SIZE | protocol |
---|---|---|---|---|---|---|---|
MobileFaceNet | ArcFace | 69.10 | 84.23 | 81.15 | 85.86 | 4MB | small |
ResNet50-IR | ArcFace | 74.31 | 88.23 | 87.44 | 89.56 | 170MB | small |
SEResNet50-IR | ArcFace | 74.37 | 88.32 | 88.30 | 89.65 | 171MB | small |
MobileFaceNet | ArcFace | 74.95 | 88.77 | 89.47 | 91.03 | 4MB | large |
ResNet50-IR | ArcFace | 79.61 | 96.02 | 96.58 | 96.78 | 170MB | large |
SEResNet50-IR | ArcFace | 79.91 | 96.10 | 97.01 | 97.60 | 171MB | large |
ResNet100-IR | ArcFace | 80.40 | 96.94 | 97.60 | 98.05 | 256MB | large |
- Download the source code to your machine.
- Prepare the train dataset and train list, test dataset and test verification pairs.
- Set your own dataset path and any other parameters in train.py.
- Run train.py file, test accuracy will print into log file during training process.
- Every evaluate file can work independently for the model test process. just set your own args in the file.
Visdom support for loss and accuracy during training process.
Softmax Loss vs Softmax_Center Loss. Left: softmax training set. Right: softmax + center loss training set.
MuggleWang/CosFace_pytorch
Xiaoccer/MobileFaceNet_Pytorch
TreB1eN/InsightFace_Pytorch
deepinsight/insightface
KaiyangZhou/pytorch-center-loss
tengshaofeng/ResidualAttentionNetwork-pytorch
- Report the test results on DeepGlint Trillion Pairs Challenge.
- Add C++ api for fast deployment with pytorch 1.0.
- Train the ResNet100-based model.