face.evoLVe
1.0.0
| Pengarang | Jian Zhao |
|---|---|
| Beranda | https://zhaoj9014.github.io |
Kode Face.Evolve dirilis di bawah lisensi MIT.
✅ CLOSED 02 September 2021 : Baidu Paddlepaddle secara resmi menggabungkan wajah. Berungkap untuk memfasilitasi penelitian dan aplikasi pada analitik terkait wajah (pengumuman resmi).
✅ CLOSED 03 July 2021 : Memberikan kode pelatihan untuk kerangka kerja Paddlepaddle.
✅ CLOSED 04 July 2019 : Kami akan membagikan beberapa dataset yang tersedia untuk umum tentang deteksi anti-spoofing/liveness untuk memfasilitasi penelitian dan analitik terkait.
✅ CLOSED 07 June 2019 : Kami melatih model IR-152 yang berkinerja lebih baik pada MS-Celeb-1m_align_112x112, dan akan segera merilis model tersebut.
✅ CLOSED 23 May 2019 : Kami berbagi tiga set data yang tersedia untuk umum untuk memfasilitasi penelitian tentang pengakuan wajah dan analitik yang heterogen. Silakan merujuk ke SEC. Data Zoo untuk detailnya.
✅ CLOSED 23 Jan 2019 : Kami membagikan daftar nama dan daftar yang tumpang tindih dari beberapa set data pengenalan wajah yang banyak digunakan untuk membantu para peneliti/insinyur dengan cepat menghapus bagian yang tumpang tindih antara kumpulan data pribadi mereka dan kumpulan data publik. Silakan merujuk ke SEC. Data Zoo untuk detailnya.
✅ CLOSED 23 Jan 2019 : Skema pelatihan terdistribusi saat ini dengan multi-GPU di bawah Pytorch dan platform utama lainnya sejajar dengan tulang punggung di seluruh GPU sambil mengandalkan master tunggal untuk menghitung lapisan bottleneck terakhir (sepenuhnya terhubung/softmax). Ini bukan masalah untuk pengakuan wajah konvensional dengan jumlah identitas sedang. Namun, ia berjuang dengan pengakuan wajah skala besar, yang membutuhkan pengakuan jutaan identitas di dunia nyata. Master hampir tidak dapat memegang lapisan akhir yang terlalu besar sementara para budak masih memiliki sumber komputasi yang berlebihan, yang mengarah ke pelatihan batch kecil atau bahkan pelatihan yang gagal. Untuk mengatasi masalah ini, kami mengembangkan skema pelatihan terdistribusi yang sangat elektron, efektif dan efisien dengan multi-GPU di bawah Pytorch, tidak hanya mendukung tulang punggung, tetapi juga kepala dengan lapisan wajah berskala besar yang terhubung sepenuhnya, untuk berkinerja tinggi. Kami akan menambahkan dukungan ini ke dalam repo kami.
✅ CLOSED 22 Jan 2019 : Kami telah merilis dua API ekstraksi fitur untuk mengekstraksi fitur dari model pra-terlatih, diimplementasikan dengan fungsi pytorch build-in dan OpenCV, masing-masing. Silakan periksa ./util/extract_feature_v1.py dan ./util/extract_feature_v2.py .
✅ CLOSED 22 Jan 2019 : Kami menyempurnakan model IR-50 kami yang dirilis pada data wajah Asia pribadi kami, yang akan segera dirilis untuk memfasilitasi pengenalan wajah Asia berkinerja tinggi.
✅ CLOSED 21 Jan 2019 : Kami melatih model IR-50 yang berkinerja lebih baik pada MS-Celeb-1m_align_112x112, dan akan segera menggantikan model saat ini.
?
?
pip install torch torchvision )pip install mxnet-cu90 )pip install tensorflow-gpu )pip install tensorboardX )pip install opencv-python )pip install bcolz )Meskipun tidak diperlukan, untuk kinerja optimal, sangat disarankan untuk menjalankan kode menggunakan GPU yang diaktifkan CUDA. Kami menggunakan 4-8 nvidia tesla p40 secara paralel.
?
git clone https://github.com/ZhaoJ9014/face.evoLVe.PyTorch.git .mkdir data checkpoint log di direktori yang sesuai untuk menyimpan data/val/val/uji Anda, pos pemeriksaan dan log pelatihan. ./data/db_name/
-> id1/
-> 1.jpg
-> ...
-> id2/
-> 1.jpg
-> ...
-> ...
-> ...
-> ...
?
./align from PIL import Image
from detector import detect_faces
from visualization_utils import show_results
img = Image . open ( 'some_img.jpg' ) # modify the image path to yours
bounding_boxes , landmarks = detect_faces ( img ) # detect bboxes and landmarks for all faces in the image
show_results ( img , bounding_boxes , landmarks ) # visualize the resultssource_root dengan struktur direktori seperti yang ditunjukkan dalam penggunaan Sec., Dan menyimpan hasil yang selaras dengan folder baru dest_root dengan struktur direktori yang sama): python face_align.py -source_root [source_root] -dest_root [dest_root] -crop_size [crop_size]
# python face_align.py -source_root './data/test' -dest_root './data/test_Aligned' -crop_size 112
*.DS_Store yang dapat merusak data Anda, karena mereka akan secara otomatis dihapus saat Anda menjalankan skrip.source_root , dest_root dan crop_size ke nilai -nilai Anda sendiri saat Anda menjalankan face_align.py ; 2) Lewati min_face_size yang disesuaikan, thresholds dan nilai nms_thresholds ke fungsi detect_faces dari detector.py agar sesuai dengan persyaratan praktis Anda; 3) Jika Anda menemukan kecepatan menggunakan API Alignment Face agak lambat, Anda dapat memanggil API mengubah ukuran wajah untuk mengulangi gambar yang pertama -tama ukurannya lebih besar dari ambang batas (tentukan argumen source_root , dest_root dan min_side ke nilai -nilai Anda sendiri) sebelum memanggil API Alignment Face: python face_resize.py
./balancemin_num sampel dalam root set pelatihan dengan struktur direktori seperti yang ditunjukkan dalam penggunaan Sec. Untuk keseimbangan data dan pelatihan model yang efektif): python remove_lowshot.py -root [root] -min_num [min_num]
# python remove_lowshot.py -root './data/train' -min_num 10
root dan min_num untuk nilai -nilai Anda sendiri saat Anda menjalankan remove_lowshot.py .☕
Folder: ./
API Konfigurasi (Konfigurasikan pengaturan keseluruhan Anda untuk pelatihan & validasi) config.py :
import torch
configurations = {
1 : dict (
SEED = 1337 , # random seed for reproduce results
DATA_ROOT = '/media/pc/6T/jasonjzhao/data/faces_emore' , # the parent root where your train/val/test data are stored
MODEL_ROOT = '/media/pc/6T/jasonjzhao/buffer/model' , # the root to buffer your checkpoints
LOG_ROOT = '/media/pc/6T/jasonjzhao/buffer/log' , # the root to log your train/val status
BACKBONE_RESUME_ROOT = './' , # the root to resume training from a saved checkpoint
HEAD_RESUME_ROOT = './' , # the root to resume training from a saved checkpoint
BACKBONE_NAME = 'IR_SE_50' , # support: ['ResNet_50', 'ResNet_101', 'ResNet_152', 'IR_50', 'IR_101', 'IR_152', 'IR_SE_50', 'IR_SE_101', 'IR_SE_152']
HEAD_NAME = 'ArcFace' , # support: ['Softmax', 'ArcFace', 'CosFace', 'SphereFace', 'Am_softmax']
LOSS_NAME = 'Focal' , # support: ['Focal', 'Softmax']
INPUT_SIZE = [ 112 , 112 ], # support: [112, 112] and [224, 224]
RGB_MEAN = [ 0.5 , 0.5 , 0.5 ], # for normalize inputs to [-1, 1]
RGB_STD = [ 0.5 , 0.5 , 0.5 ],
EMBEDDING_SIZE = 512 , # feature dimension
BATCH_SIZE = 512 ,
DROP_LAST = True , # whether drop the last batch to ensure consistent batch_norm statistics
LR = 0.1 , # initial LR
NUM_EPOCH = 125 , # total epoch number (use the firt 1/25 epochs to warm up)
WEIGHT_DECAY = 5e-4 , # do not apply to batch_norm parameters
MOMENTUM = 0.9 ,
STAGES = [ 35 , 65 , 95 ], # epoch stages to decay learning rate
DEVICE = torch . device ( "cuda:0" if torch . cuda . is_available () else "cpu" ),
MULTI_GPU = True , # flag to use multiple GPUs; if you choose to train with single GPU, you should first run "export CUDA_VISILE_DEVICES=device_id" to specify the GPU card you want to use
GPU_ID = [ 0 , 1 , 2 , 3 ], # specify your GPU ids
PIN_MEMORY = True ,
NUM_WORKERS = 0 ,
),
} API Train & Validasi (semua orang tentang Pelatihan & Validasi, IE , Paket Impor, Hyperparameters & Loader Data, Model & Kehilangan & Pengoptimal, Kereta & Validasi & Simpan Pokter -pos) train.py . Karena MS-Celeb-1m berfungsi sebagai imagenet dalam pengajuan pengenalan wajah, kami melakukan pra-pelatihan pada model. Model pada MS-Celeb-1m dan melakukan validasi pada LFW, CFP_FF, CFP_FP, AgEDB, CalFW, CPLFW dan VGGFACE2_FP. Mari selami detail bersama langkah demi langkah.
import torch
import torch . nn as nn
import torch . optim as optim
import torchvision . transforms as transforms
import torchvision . datasets as datasets
from config import configurations
from backbone . model_resnet import ResNet_50 , ResNet_101 , ResNet_152
from backbone . model_irse import IR_50 , IR_101 , IR_152 , IR_SE_50 , IR_SE_101 , IR_SE_152
from head . metrics import ArcFace , CosFace , SphereFace , Am_softmax
from loss . focal import FocalLoss
from util . utils import make_weights_for_balanced_classes , get_val_data , separate_irse_bn_paras , separate_resnet_bn_paras , warm_up_lr , schedule_lr , perform_val , get_time , buffer_val , AverageMeter , accuracy
from tensorboardX import SummaryWriter
from tqdm import tqdm
import os cfg = configurations [ 1 ]
SEED = cfg [ 'SEED' ] # random seed for reproduce results
torch . manual_seed ( SEED )
DATA_ROOT = cfg [ 'DATA_ROOT' ] # the parent root where your train/val/test data are stored
MODEL_ROOT = cfg [ 'MODEL_ROOT' ] # the root to buffer your checkpoints
LOG_ROOT = cfg [ 'LOG_ROOT' ] # the root to log your train/val status
BACKBONE_RESUME_ROOT = cfg [ 'BACKBONE_RESUME_ROOT' ] # the root to resume training from a saved checkpoint
HEAD_RESUME_ROOT = cfg [ 'HEAD_RESUME_ROOT' ] # the root to resume training from a saved checkpoint
BACKBONE_NAME = cfg [ 'BACKBONE_NAME' ] # support: ['ResNet_50', 'ResNet_101', 'ResNet_152', 'IR_50', 'IR_101', 'IR_152', 'IR_SE_50', 'IR_SE_101', 'IR_SE_152']
HEAD_NAME = cfg [ 'HEAD_NAME' ] # support: ['Softmax', 'ArcFace', 'CosFace', 'SphereFace', 'Am_softmax']
LOSS_NAME = cfg [ 'LOSS_NAME' ] # support: ['Focal', 'Softmax']
INPUT_SIZE = cfg [ 'INPUT_SIZE' ]
RGB_MEAN = cfg [ 'RGB_MEAN' ] # for normalize inputs
RGB_STD = cfg [ 'RGB_STD' ]
EMBEDDING_SIZE = cfg [ 'EMBEDDING_SIZE' ] # feature dimension
BATCH_SIZE = cfg [ 'BATCH_SIZE' ]
DROP_LAST = cfg [ 'DROP_LAST' ] # whether drop the last batch to ensure consistent batch_norm statistics
LR = cfg [ 'LR' ] # initial LR
NUM_EPOCH = cfg [ 'NUM_EPOCH' ]
WEIGHT_DECAY = cfg [ 'WEIGHT_DECAY' ]
MOMENTUM = cfg [ 'MOMENTUM' ]
STAGES = cfg [ 'STAGES' ] # epoch stages to decay learning rate
DEVICE = cfg [ 'DEVICE' ]
MULTI_GPU = cfg [ 'MULTI_GPU' ] # flag to use multiple GPUs
GPU_ID = cfg [ 'GPU_ID' ] # specify your GPU ids
PIN_MEMORY = cfg [ 'PIN_MEMORY' ]
NUM_WORKERS = cfg [ 'NUM_WORKERS' ]
print ( "=" * 60 )
print ( "Overall Configurations:" )
print ( cfg )
print ( "=" * 60 )
writer = SummaryWriter ( LOG_ROOT ) # writer for buffering intermedium results train_transform = transforms . Compose ([ # refer to https://pytorch.org/docs/stable/torchvision/transforms.html for more build-in online data augmentation
transforms . Resize ([ int ( 128 * INPUT_SIZE [ 0 ] / 112 ), int ( 128 * INPUT_SIZE [ 0 ] / 112 )]), # smaller side resized
transforms . RandomCrop ([ INPUT_SIZE [ 0 ], INPUT_SIZE [ 1 ]]),
transforms . RandomHorizontalFlip (),
transforms . ToTensor (),
transforms . Normalize ( mean = RGB_MEAN ,
std = RGB_STD ),
])
dataset_train = datasets . ImageFolder ( os . path . join ( DATA_ROOT , 'imgs' ), train_transform )
# create a weighted random sampler to process imbalanced data
weights = make_weights_for_balanced_classes ( dataset_train . imgs , len ( dataset_train . classes ))
weights = torch . DoubleTensor ( weights )
sampler = torch . utils . data . sampler . WeightedRandomSampler ( weights , len ( weights ))
train_loader = torch . utils . data . DataLoader (
dataset_train , batch_size = BATCH_SIZE , sampler = sampler , pin_memory = PIN_MEMORY ,
num_workers = NUM_WORKERS , drop_last = DROP_LAST
)
NUM_CLASS = len ( train_loader . dataset . classes )
print ( "Number of Training Classes: {}" . format ( NUM_CLASS ))
lfw , cfp_ff , cfp_fp , agedb , calfw , cplfw , vgg2_fp , lfw_issame , cfp_ff_issame , cfp_fp_issame , agedb_issame , calfw_issame , cplfw_issame , vgg2_fp_issame = get_val_data ( DATA_ROOT ) BACKBONE_DICT = { 'ResNet_50' : ResNet_50 ( INPUT_SIZE ),
'ResNet_101' : ResNet_101 ( INPUT_SIZE ),
'ResNet_152' : ResNet_152 ( INPUT_SIZE ),
'IR_50' : IR_50 ( INPUT_SIZE ),
'IR_101' : IR_101 ( INPUT_SIZE ),
'IR_152' : IR_152 ( INPUT_SIZE ),
'IR_SE_50' : IR_SE_50 ( INPUT_SIZE ),
'IR_SE_101' : IR_SE_101 ( INPUT_SIZE ),
'IR_SE_152' : IR_SE_152 ( INPUT_SIZE )}
BACKBONE = BACKBONE_DICT [ BACKBONE_NAME ]
print ( "=" * 60 )
print ( BACKBONE )
print ( "{} Backbone Generated" . format ( BACKBONE_NAME ))
print ( "=" * 60 )
HEAD_DICT = { 'ArcFace' : ArcFace ( in_features = EMBEDDING_SIZE , out_features = NUM_CLASS , device_id = GPU_ID ),
'CosFace' : CosFace ( in_features = EMBEDDING_SIZE , out_features = NUM_CLASS , device_id = GPU_ID ),
'SphereFace' : SphereFace ( in_features = EMBEDDING_SIZE , out_features = NUM_CLASS , device_id = GPU_ID ),
'Am_softmax' : Am_softmax ( in_features = EMBEDDING_SIZE , out_features = NUM_CLASS , device_id = GPU_ID )}
HEAD = HEAD_DICT [ HEAD_NAME ]
print ( "=" * 60 )
print ( HEAD )
print ( "{} Head Generated" . format ( HEAD_NAME ))
print ( "=" * 60 ) LOSS_DICT = { 'Focal' : FocalLoss (),
'Softmax' : nn . CrossEntropyLoss ()}
LOSS = LOSS_DICT [ LOSS_NAME ]
print ( "=" * 60 )
print ( LOSS )
print ( "{} Loss Generated" . format ( LOSS_NAME ))
print ( "=" * 60 ) if BACKBONE_NAME . find ( "IR" ) >= 0 :
backbone_paras_only_bn , backbone_paras_wo_bn = separate_irse_bn_paras ( BACKBONE ) # separate batch_norm parameters from others; do not do weight decay for batch_norm parameters to improve the generalizability
_ , head_paras_wo_bn = separate_irse_bn_paras ( HEAD )
else :
backbone_paras_only_bn , backbone_paras_wo_bn = separate_resnet_bn_paras ( BACKBONE ) # separate batch_norm parameters from others; do not do weight decay for batch_norm parameters to improve the generalizability
_ , head_paras_wo_bn = separate_resnet_bn_paras ( HEAD )
OPTIMIZER = optim . SGD ([{ 'params' : backbone_paras_wo_bn + head_paras_wo_bn , 'weight_decay' : WEIGHT_DECAY }, { 'params' : backbone_paras_only_bn }], lr = LR , momentum = MOMENTUM )
print ( "=" * 60 )
print ( OPTIMIZER )
print ( "Optimizer Generated" )
print ( "=" * 60 ) if BACKBONE_RESUME_ROOT and HEAD_RESUME_ROOT :
print ( "=" * 60 )
if os . path . isfile ( BACKBONE_RESUME_ROOT ) and os . path . isfile ( HEAD_RESUME_ROOT ):
print ( "Loading Backbone Checkpoint '{}'" . format ( BACKBONE_RESUME_ROOT ))
BACKBONE . load_state_dict ( torch . load ( BACKBONE_RESUME_ROOT ))
print ( "Loading Head Checkpoint '{}'" . format ( HEAD_RESUME_ROOT ))
HEAD . load_state_dict ( torch . load ( HEAD_RESUME_ROOT ))
else :
print ( "No Checkpoint Found at '{}' and '{}'. Please Have a Check or Continue to Train from Scratch" . format ( BACKBONE_RESUME_ROOT , HEAD_RESUME_ROOT ))
print ( "=" * 60 ) if MULTI_GPU :
# multi-GPU setting
BACKBONE = nn . DataParallel ( BACKBONE , device_ids = GPU_ID )
BACKBONE = BACKBONE . to ( DEVICE )
else :
# single-GPU setting
BACKBONE = BACKBONE . to ( DEVICE ) DISP_FREQ = len ( train_loader ) // 100 # frequency to display training loss & acc
NUM_EPOCH_WARM_UP = NUM_EPOCH // 25 # use the first 1/25 epochs to warm up
NUM_BATCH_WARM_UP = len ( train_loader ) * NUM_EPOCH_WARM_UP # use the first 1/25 epochs to warm up
batch = 0 # batch index for epoch in range ( NUM_EPOCH ): # start training process
if epoch == STAGES [ 0 ]: # adjust LR for each training stage after warm up, you can also choose to adjust LR manually (with slight modification) once plaueau observed
schedule_lr ( OPTIMIZER )
if epoch == STAGES [ 1 ]:
schedule_lr ( OPTIMIZER )
if epoch == STAGES [ 2 ]:
schedule_lr ( OPTIMIZER )
BACKBONE . train () # set to training mode
HEAD . train ()
losses = AverageMeter ()
top1 = AverageMeter ()
top5 = AverageMeter ()
for inputs , labels in tqdm ( iter ( train_loader )):
if ( epoch + 1 <= NUM_EPOCH_WARM_UP ) and ( batch + 1 <= NUM_BATCH_WARM_UP ): # adjust LR for each training batch during warm up
warm_up_lr ( batch + 1 , NUM_BATCH_WARM_UP , LR , OPTIMIZER )
# compute output
inputs = inputs . to ( DEVICE )
labels = labels . to ( DEVICE ). long ()
features = BACKBONE ( inputs )
outputs = HEAD ( features , labels )
loss = LOSS ( outputs , labels )
# measure accuracy and record loss
prec1 , prec5 = accuracy ( outputs . data , labels , topk = ( 1 , 5 ))
losses . update ( loss . data . item (), inputs . size ( 0 ))
top1 . update ( prec1 . data . item (), inputs . size ( 0 ))
top5 . update ( prec5 . data . item (), inputs . size ( 0 ))
# compute gradient and do SGD step
OPTIMIZER . zero_grad ()
loss . backward ()
OPTIMIZER . step ()
# dispaly training loss & acc every DISP_FREQ
if (( batch + 1 ) % DISP_FREQ == 0 ) and batch != 0 :
print ( "=" * 60 )
print ( 'Epoch {}/{} Batch {}/{} t '
'Training Loss {loss.val:.4f} ({loss.avg:.4f}) t '
'Training Prec@1 {top1.val:.3f} ({top1.avg:.3f}) t '
'Training Prec@5 {top5.val:.3f} ({top5.avg:.3f})' . format (
epoch + 1 , NUM_EPOCH , batch + 1 , len ( train_loader ) * NUM_EPOCH , loss = losses , top1 = top1 , top5 = top5 ))
print ( "=" * 60 )
batch += 1 # batch index
# training statistics per epoch (buffer for visualization)
epoch_loss = losses . avg
epoch_acc = top1 . avg
writer . add_scalar ( "Training_Loss" , epoch_loss , epoch + 1 )
writer . add_scalar ( "Training_Accuracy" , epoch_acc , epoch + 1 )
print ( "=" * 60 )
print ( 'Epoch: {}/{} t '
'Training Loss {loss.val:.4f} ({loss.avg:.4f}) t '
'Training Prec@1 {top1.val:.3f} ({top1.avg:.3f}) t '
'Training Prec@5 {top5.val:.3f} ({top5.avg:.3f})' . format (
epoch + 1 , NUM_EPOCH , loss = losses , top1 = top1 , top5 = top5 ))
print ( "=" * 60 )
# perform validation & save checkpoints per epoch
# validation statistics per epoch (buffer for visualization)
print ( "=" * 60 )
print ( "Perform Evaluation on LFW, CFP_FF, CFP_FP, AgeDB, CALFW, CPLFW and VGG2_FP, and Save Checkpoints..." )
accuracy_lfw , best_threshold_lfw , roc_curve_lfw = perform_val ( MULTI_GPU , DEVICE , EMBEDDING_SIZE , BATCH_SIZE , BACKBONE , lfw , lfw_issame )
buffer_val ( writer , "LFW" , accuracy_lfw , best_threshold_lfw , roc_curve_lfw , epoch + 1 )
accuracy_cfp_ff , best_threshold_cfp_ff , roc_curve_cfp_ff = perform_val ( MULTI_GPU , DEVICE , EMBEDDING_SIZE , BATCH_SIZE , BACKBONE , cfp_ff , cfp_ff_issame )
buffer_val ( writer , "CFP_FF" , accuracy_cfp_ff , best_threshold_cfp_ff , roc_curve_cfp_ff , epoch + 1 )
accuracy_cfp_fp , best_threshold_cfp_fp , roc_curve_cfp_fp = perform_val ( MULTI_GPU , DEVICE , EMBEDDING_SIZE , BATCH_SIZE , BACKBONE , cfp_fp , cfp_fp_issame )
buffer_val ( writer , "CFP_FP" , accuracy_cfp_fp , best_threshold_cfp_fp , roc_curve_cfp_fp , epoch + 1 )
accuracy_agedb , best_threshold_agedb , roc_curve_agedb = perform_val ( MULTI_GPU , DEVICE , EMBEDDING_SIZE , BATCH_SIZE , BACKBONE , agedb , agedb_issame )
buffer_val ( writer , "AgeDB" , accuracy_agedb , best_threshold_agedb , roc_curve_agedb , epoch + 1 )
accuracy_calfw , best_threshold_calfw , roc_curve_calfw = perform_val ( MULTI_GPU , DEVICE , EMBEDDING_SIZE , BATCH_SIZE , BACKBONE , calfw , calfw_issame )
buffer_val ( writer , "CALFW" , accuracy_calfw , best_threshold_calfw , roc_curve_calfw , epoch + 1 )
accuracy_cplfw , best_threshold_cplfw , roc_curve_cplfw = perform_val ( MULTI_GPU , DEVICE , EMBEDDING_SIZE , BATCH_SIZE , BACKBONE , cplfw , cplfw_issame )
buffer_val ( writer , "CPLFW" , accuracy_cplfw , best_threshold_cplfw , roc_curve_cplfw , epoch + 1 )
accuracy_vgg2_fp , best_threshold_vgg2_fp , roc_curve_vgg2_fp = perform_val ( MULTI_GPU , DEVICE , EMBEDDING_SIZE , BATCH_SIZE , BACKBONE , vgg2_fp , vgg2_fp_issame )
buffer_val ( writer , "VGGFace2_FP" , accuracy_vgg2_fp , best_threshold_vgg2_fp , roc_curve_vgg2_fp , epoch + 1 )
print ( "Epoch {}/{}, Evaluation: LFW Acc: {}, CFP_FF Acc: {}, CFP_FP Acc: {}, AgeDB Acc: {}, CALFW Acc: {}, CPLFW Acc: {}, VGG2_FP Acc: {}" . format ( epoch + 1 , NUM_EPOCH , accuracy_lfw , accuracy_cfp_ff , accuracy_cfp_fp , accuracy_agedb , accuracy_calfw , accuracy_cplfw , accuracy_vgg2_fp ))
print ( "=" * 60 )
# save checkpoints per epoch
if MULTI_GPU :
torch . save ( BACKBONE . module . state_dict (), os . path . join ( MODEL_ROOT , "Backbone_{}_Epoch_{}_Batch_{}_Time_{}_checkpoint.pth" . format ( BACKBONE_NAME , epoch + 1 , batch , get_time ())))
torch . save ( HEAD . state_dict (), os . path . join ( MODEL_ROOT , "Head_{}_Epoch_{}_Batch_{}_Time_{}_checkpoint.pth" . format ( HEAD_NAME , epoch + 1 , batch , get_time ())))
else :
torch . save ( BACKBONE . state_dict (), os . path . join ( MODEL_ROOT , "Backbone_{}_Epoch_{}_Batch_{}_Time_{}_checkpoint.pth" . format ( BACKBONE_NAME , epoch + 1 , batch , get_time ())))
torch . save ( HEAD . state_dict (), os . path . join ( MODEL_ROOT , "Head_{}_Epoch_{}_Batch_{}_Time_{}_checkpoint.pth" . format ( HEAD_NAME , epoch + 1 , batch , get_time ()))) Sekarang, Anda dapat mulai bermain dengan wajah. Menyeluk dan menjalankan train.py . Informasi ramah pengguna akan muncul di terminal Anda:
Tentang konfigurasi keseluruhan:
Tentang jumlah kelas pelatihan:
Tentang detail tulang punggung:
Tentang detail kepala:
Tentang detail kerugian:
Tentang detail pengoptimal:
Tentang pelatihan resume:
Tentang Status Pelatihan & Statistik (ketika indeks batch mencapai DISP_FREQ atau di akhir setiap zaman):
Tentang statistik validasi & simpan pos pemeriksaan (di akhir setiap zaman):
Pantau hunian GPU on-the-fly dengan watch -d -n 0.01 nvidia-smi .
Silakan merujuk ke SEC. Model Zoo untuk bobot model tertentu dan kinerja yang sesuai.
Fitur Ekstraksi API (Fitur Ekstrak dari model pra-terlatih) ./util/extract_feature_v1.py (diimplementasikan dengan fungsi pytorch build-in) dan ./util/extract_feature_v2.py (diimplementasikan dengan OpenCV).
Visualisasikan Statistik Pelatihan & Validasi dengan Tensorboardx (lihat Sec. Model Zoo):
tensorboard --logdir /media/pc/6T/jasonjzhao/buffer/log
?
| Database | Versi | #Identitas | #Gambar | #Bingkai | #Video | Tautan unduh |
|---|---|---|---|---|---|---|
| Lfw | Mentah | 5.749 | 13.233 | - | - | Google Drive, Baidu Drive |
| Lfw | Align_250x250 | 5.749 | 13.233 | - | - | Google Drive, Baidu Drive |
| Lfw | Align_112x112 | 5.749 | 13.233 | - | - | Google Drive, Baidu Drive |
| Calfw | Mentah | 4.025 | 12.174 | - | - | Google Drive, Baidu Drive |
| Calfw | Align_112x112 | 4.025 | 12.174 | - | - | Google Drive, Baidu Drive |
| CPLFW | Mentah | 3.884 | 11.652 | - | - | Google Drive, Baidu Drive |
| CPLFW | Align_112x112 | 3.884 | 11.652 | - | - | Google Drive, Baidu Drive |
| Casia-Webface | RAW_V1 | 10.575 | 494.414 | - | - | Baidu Drive |
| Casia-Webface | RAW_V2 | 10.575 | 494.414 | - | - | Google Drive, Baidu Drive |
| Casia-Webface | Membersihkan | 10.575 | 455.594 | - | - | Google Drive, Baidu Drive |
| MS-Celeb-1m | Membersihkan | 100.000 | 5.084.127 | - | - | Google Drive |
| MS-Celeb-1m | Align_112x112 | 85.742 | 5.822.653 | - | - | Google Drive |
| Vggface2 | Membersihkan | 8.631 | 3.086.894 | - | - | Google Drive |
| Vggface2_fp | Align_112x112 | - | - | - | - | Google Drive, Baidu Drive |
| Agedb | Mentah | 570 | 16.488 | - | - | Google Drive, Baidu Drive |
| Agedb | Align_112x112 | 570 | 16.488 | - | - | Google Drive, Baidu Drive |
| IJB-A | Membersihkan | 500 | 5.396 | 20.369 | 2.085 | Google Drive, Baidu Drive |
| Ijb-b | Mentah | 1.845 | 21.798 | 55.026 | 7.011 | Google Drive |
| CFP | Mentah | 500 | 7.000 | - | - | Google Drive, Baidu Drive |
| CFP | Align_112x112 | 500 | 7.000 | - | - | Google Drive, Baidu Drive |
| Umdfaces | Align_112x112 | 8.277 | 367.888 | - | - | Google Drive, Baidu Drive |
| Celeba | Mentah | 10.177 | 202.599 | - | - | Google Drive, Baidu Drive |
| CACD-VS | Mentah | 2.000 | 163.446 | - | - | Google Drive, Baidu Drive |
| Ytf | Align_344x344 | 1.595 | - | 3.425 | 621.127 | Google Drive, Baidu Drive |
| Deepglint | Align_112x112 | 180.855 | 6.753.545 | - | - | Google Drive |
| Utkface | Align_200x200 | - | 23.708 | - | - | Google Drive, Baidu Drive |
| Buaa-visnir | Align_287x287 | 150 | 5.952 | - | - | Baidu Drive, PW: XMBC |
| Casia nir-vis 2.0 | Align_128x128 | 725 | 17.580 | - | - | Baidu Drive, PW: 883B |
| Oulu-Casia | Mentah | 80 | 65.000 | - | - | Baidu Drive, PW: XXP5 |
| NUAA-IMPOSTERDB | Mentah | 15 | 12.614 | - | - | Baidu Drive, PW: IF3N |
| CASIA-SURF | Mentah | 1.000 | - | - | 21.000 | Baidu Drive, PW: IZB3 |
| CASIA-FASD | Mentah | 50 | - | - | 600 | Baidu Drive, PW: H5un |
| Casia-mfsd | Mentah | 50 | - | - | 600 | |
| Replay-serangan | Mentah | 50 | - | - | 1.200 | |
| WebFace260M | Mentah | 24m | 2m | - | https://www.face-benchmark.org/ |
unzip casia-maxpy-clean.zip
cd casia-maxpy-clean
zip -F CASIA-maxpy-clean.zip --out CASIA-maxpy-clean_fix.zip
unzip CASIA-maxpy-clean_fix.zip
import numpy as np
import bcolz
import os
def get_pair ( root , name ):
carray = bcolz . carray ( rootdir = os . path . join ( root , name ), mode = 'r' )
issame = np . load ( '{}/{}_list.npy' . format ( root , name ))
return carray , issame
def get_data ( data_root ):
agedb_30 , agedb_30_issame = get_pair ( data_root , 'agedb_30' )
cfp_fp , cfp_fp_issame = get_pair ( data_root , 'cfp_fp' )
lfw , lfw_issame = get_pair ( data_root , 'lfw' )
vgg2_fp , vgg2_fp_issame = get_pair ( data_root , 'vgg2_fp' )
return agedb_30 , cfp_fp , lfw , vgg2_fp , agedb_30_issame , cfp_fp_issame , lfw_issame , vgg2_fp_issame
agedb_30 , cfp_fp , lfw , vgg2_fp , agedb_30_issame , cfp_fp_issame , lfw_issame , vgg2_fp_issame = get_data ( DATA_ROOT )MS-Celeb-1M_Top1M_MID2Name.tsv (Google Drive, Baidu Drive), VGGface2_ID2Name.csv (Google Drive, Baidu Drive), VGGface2_FaceScrub_Overlap.txt (Google Drive, Baid Drive), VGGface2_LFW_Overlap.txt . CASIA-WebFace_ID2Name.txt (Google Drive, Baidu Drive), CASIA-WebFace_FaceScrub_Overlap.txt (Google Drive, Baidu Drive), CASIA-WebFace_LFW_Overlap.txt (Google Drive, Baidu Drive), FaceScrub_Name.txt (Google Drive, Baidu Drive), LFW_Name.txt (Google Drive, Baidu Drive), LFW_Log.txt (Google Drive, Baidu Drive) untuk membantu para peneliti/insinyur dengan cepat menghapus bagian yang tumpang tindih antara kumpulan data pribadi mereka dan kumpulan data publik.?
Model
| Tulang punggung | Kepala | Kehilangan | Data pelatihan | Tautan unduh |
|---|---|---|---|---|
| IR-50 | Arcface | Fokus | Ms-celeb-1m_align_112x112 | Google Drive, Baidu Drive |
Pengaturan
INPUT_SIZE: [112, 112]; RGB_MEAN: [0.5, 0.5, 0.5]; RGB_STD: [0.5, 0.5, 0.5]; BATCH_SIZE: 512 (drop the last batch to ensure consistent batch_norm statistics); Initial LR: 0.1; NUM_EPOCH: 120; WEIGHT_DECAY: 5e-4 (do not apply to batch_norm parameters); MOMENTUM: 0.9; STAGES: [30, 60, 90]; Augmentation: Random Crop + Horizontal Flip; Imbalanced Data Processing: Weighted Random Sampling; Solver: SGD; GPUs: 4 NVIDIA Tesla P40 in Parallel
Statistik Pelatihan & Validasi
Pertunjukan
| Lfw | CFP_FF | CFP_FP | Agedb | Calfw | CPLFW | Vggface2_fp |
|---|---|---|---|---|---|---|
| 99.78 | 99.69 | 98.14 | 97.53 | 95.87 | 92.45 | 95.22 |
Model
| Tulang punggung | Kepala | Kehilangan | Data pelatihan | Tautan unduh |
|---|---|---|---|---|
| IR-50 | Arcface | Fokus | Data wajah pribadi Asia | Google Drive, Baidu Drive |
Pengaturan
INPUT_SIZE: [112, 112]; RGB_MEAN: [0.5, 0.5, 0.5]; RGB_STD: [0.5, 0.5, 0.5]; BATCH_SIZE: 1024 (drop the last batch to ensure consistent batch_norm statistics); Initial LR: 0.01 (initialize weights from the above model pre-trained on MS-Celeb-1M_Align_112x112); NUM_EPOCH: 80; WEIGHT_DECAY: 5e-4 (do not apply to batch_norm parameters); MOMENTUM: 0.9; STAGES: [20, 40, 60]; Augmentation: Random Crop + Horizontal Flip; Imbalanced Data Processing: Weighted Random Sampling; Solver: SGD; GPUs: 8 NVIDIA Tesla P40 in Parallel
Kinerja (Harap lakukan evaluasi pada dataset benchmark wajah Asia Anda sendiri)
Model
| Tulang punggung | Kepala | Kehilangan | Data pelatihan | Tautan unduh |
|---|---|---|---|---|
| IR-152 | Arcface | Fokus | Ms-celeb-1m_align_112x112 | Baidu Drive, PW: B197 |
Pengaturan
INPUT_SIZE: [112, 112]; RGB_MEAN: [0.5, 0.5, 0.5]; RGB_STD: [0.5, 0.5, 0.5]; BATCH_SIZE: 256 (drop the last batch to ensure consistent batch_norm statistics); Initial LR: 0.01; NUM_EPOCH: 120; WEIGHT_DECAY: 5e-4 (do not apply to batch_norm parameters); MOMENTUM: 0.9; STAGES: [30, 60, 90]; Augmentation: Random Crop + Horizontal Flip; Imbalanced Data Processing: Weighted Random Sampling; Solver: SGD; GPUs: 4 NVIDIA Geforce RTX 2080 Ti in Parallel
Statistik Pelatihan & Validasi
Pertunjukan
| Lfw | CFP_FF | CFP_FP | Agedb | Calfw | Cplfw | Vggface2_fp |
|---|---|---|---|---|---|---|
| 99.82 | 99.83 | 98.37 | 98.07 | 96.03 | 93.05 | 95.50 |
?
2017 No.1 di ICCV 2017 MS-Celeb-1m Pengenalan Wajah Skala Besar Hard Set/Random Set/Low-Shot Learning Tantangan. Wechat News, Nus ECE News, poster NUS ECE, Sertifikat Penghargaan untuk Track-1, Sertifikat Penghargaan untuk Track-2, upacara penghargaan.
2017 No.1 di National Institute of Standard and Technology (NIST) IARPA Janus Benchmark A (IJB-A) Tantangan Verifikasi dan Tantangan Verifikasi yang tidak dibatasi. Berita WeChat.
Kinerja canggih
?
?
Silakan berkonsultasi dan mempertimbangkan mengutip makalah berikut:
@article{wu20223d,
title={3D-Guided Frontal Face Generation for Pose-Invariant Recognition},
author={Wu, Hao and Gu, Jianyang and Fan, Xiaojin and Li, He and Xie, Lidong and Zhao, Jian},
journal={T-IST},
year={2022}
}
@article{wang2021face,
title={Face.evoLVe: A High-Performance Face Recognition Library},
author={Wang, Qingzhong and Zhang, Pengfei and Xiong, Haoyi and Zhao, Jian},
journal={arXiv preprint arXiv:2107.08621},
year={2021}
}
@article{tu2021joint,
title={Joint Face Image Restoration and Frontalization for Recognition},
author={Tu, Xiaoguang and Zhao, Jian and Liu, Qiankun and Ai, Wenjie and Guo, Guodong and Li, Zhifeng and Liu, Wei and Feng, Jiashi},
journal={T-CSVT},
year={2021}
}
@article{zhao2020towards,
title={Towards age-invariant face recognition},
author={Zhao, Jian and Yan, Shuicheng and Feng, Jiashi},
journal={T-PAMI},
year={2020}
}
@article{zhao2019recognizing,
title={Recognizing Profile Faces by Imagining Frontal View},
author={Zhao, Jian and Xing, Junliang and Xiong, Lin and Yan, Shuicheng and Feng, Jiashi},
journal={IJCV},
pages={1--19},
year={2019}
}
@inproceedings{zhao2019multi,
title={Multi-Prototype Networks for Unconstrained Set-based Face Recognition},
author={Zhao, Jian and Li, Jianshu and Tu, Xiaoguang and Zhao, Fang and Xin, Yuan and Xing, Junliang and Liu, Hengzhu and Yan, Shuicheng and Feng, Jiashi},
booktitle={IJCAI},
year={2019}
}
@inproceedings{zhao2019look,
title={Look Across Elapse: Disentangled Representation Learning and Photorealistic Cross-Age Face Synthesis for Age-Invariant Face Recognition},
author={Zhao, Jian and Cheng, Yu and Cheng, Yi and Yang, Yang and Lan, Haochong and Zhao, Fang and Xiong, Lin and Xu, Yan and Li, Jianshu and Pranata, Sugiri and others},
booktitle={AAAI},
year={2019}
}
@article{zhao20183d,
title={3D-Aided Dual-Agent GANs for Unconstrained Face Recognition},
author={Zhao, Jian and Xiong, Lin and Li, Jianshu and Xing, Junliang and Yan, Shuicheng and Feng, Jiashi},
journal={T-PAMI},
year={2018}
}
@inproceedings{zhao2018towards,
title={Towards Pose Invariant Face Recognition in the Wild},
author={Zhao, Jian and Cheng, Yu and Xu, Yan and Xiong, Lin and Li, Jianshu and Zhao, Fang and Jayashree, Karlekar and Pranata, Sugiri and Shen, Shengmei and Xing, Junliang and others},
booktitle={CVPR},
pages={2207--2216},
year={2018}
}
@inproceedings{zhao3d,
title={3D-Aided Deep Pose-Invariant Face Recognition},
author={Zhao, Jian and Xiong, Lin and Cheng, Yu and Cheng, Yi and Li, Jianshu and Zhou, Li and Xu, Yan and Karlekar, Jayashree and Pranata, Sugiri and Shen, Shengmei and others},
booktitle={IJCAI},
pages={1184--1190},
year={2018}
}
@inproceedings{zhao2018dynamic,
title={Dynamic Conditional Networks for Few-Shot Learning},
author={Zhao, Fang and Zhao, Jian and Yan, Shuicheng and Feng, Jiashi},
booktitle={ECCV},
pages={19--35},
year={2018}
}
@inproceedings{zhao2017dual,
title={Dual-agent gans for photorealistic and identity preserving profile face synthesis},
author={Zhao, Jian and Xiong, Lin and Jayashree, Panasonic Karlekar and Li, Jianshu and Zhao, Fang and Wang, Zhecan and Pranata, Panasonic Sugiri and Shen, Panasonic Shengmei and Yan, Shuicheng and Feng, Jiashi},
booktitle={NeurIPS},
pages={66--76},
year={2017}
}
@inproceedings{zhao122017marginalized,
title={Marginalized cnn: Learning deep invariant representations},
author={Zhao12, Jian and Li, Jianshu and Zhao, Fang and Yan13, Shuicheng and Feng, Jiashi},
booktitle={BMVC},
year={2017}
}
@inproceedings{cheng2017know,
title={Know you at one glance: A compact vector representation for low-shot learning},
author={Cheng, Yu and Zhao, Jian and Wang, Zhecan and Xu, Yan and Jayashree, Karlekar and Shen, Shengmei and Feng, Jiashi},
booktitle={ICCVW},
pages={1924--1932},
year={2017}
}
@inproceedings{wangconditional,
title={Conditional Dual-Agent GANs for Photorealistic and Annotation Preserving Image Synthesis},
author={Wang, Zhecan and Zhao, Jian and Cheng, Yu and Xiao, Shengtao and Li, Jianshu and Zhao, Fang and Feng, Jiashi and Kassim, Ashraf},
booktitle={BMVCW},
}
