face.evoLVe
1.0.0
| 作者 | Jian Zhao |
|---|---|
| 首页 | https://zhaoj9014.github.io |
face.evolve守则是根据MIT许可发布的。
✅ CLOSED 02 September 2021 ：百度桨板正式合并了面部。
✅ CLOSED 03 July 2021 ：为PaddlePaddle框架提供训练代码。
✅ CLOSED 04 July 2019 ：我们将在面部反欺骗/LIVISET检测上共享几个公开可用的数据集，以促进相关研究和分析。
✅ CLOSED 07 June 2019 ：我们正在MS-CELEB-1M_ALIGN_112X112上训练一个表现更好的IR-152模型，并将尽快发布该模型。
✅ CLOSED 23 May 2019 ：我们共享三个公开可用的数据集，以促进有关面部识别和分析的研究。请参考SEC。数据动物园以获取详细信息。
✅ CLOSED 23 Jan 2019 ：我们共享几个广泛使用的面部识别数据集的名称列表和配对重叠列表，以帮助研究人员/工程师快速删除其自己的私人数据集和公共数据集之间的重叠部分。请参考SEC。数据动物园以获取详细信息。
✅ CLOSED 23 Jan 2019 ：当前在Pytorch和其他主流平台下使用多GPU的分布式训练架构与多GPU的主链相似，同时依靠单个主人来计算最终的瓶颈（完全连接/软的max）层。对于具有适度身份的常规面部识别而言，这不是问题。但是，它在大规模的面部识别中挣扎，这需要认识到现实世界中数百万个身份。主人几乎无法持有超大的最后一层，而奴隶仍然拥有冗余的计算资源，从而导致小批量培训甚至训练失败。为了解决这个问题，我们正在使用Pytorch下的多GPU开发高度，有效，有效的分布式培训模式，不仅支持主链，而且还支持具有完全连接（SoftMax）层的头部，以促进高表现的大型大型面部识别。我们将将此支持添加到我们的回购中。
✅ CLOSED 22 Jan 2019 ：我们发布了两个功能提取API，用于从预训练模型中提取特征，分别使用Pytorch Build-In功能和OpenCV实现。请检查./util/extract_feature_v1.py和./util/extract_feature_v2.py 。
✅ CLOSED 22 Jan 2019 ：我们正在微调发布的Assia Face Data上发布的IR-50模型，该模型将很快发布，以促进高性能的亚洲面部识别。
✅ CLOSED 21 Jan 2019 ：我们正在MS-CELEB-1M_ALIGN_112X112上训练一个表现更好的IR-50模型，并将很快替换当前模型。
？
？
pip install torch torchvision ）pip install mxnet-cu90 ）pip install tensorflow-gpu ）pip install tensorboardX ）pip install opencv-python ）pip install bcolz ）虽然不需要，但为了获得最佳性能，强烈建议使用启用CUDA的GPU运行代码。我们并行使用了4-8个Nvidia tesla P40。
？
git clone https://github.com/ZhaoJ9014/face.evoLVe.PyTorch.git 。mkdir data checkpoint log以存储您的火车/Val/测试数据，检查点和培训日志。 ./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中执行面部检测，具有里程碑式的定位和与仿射转换的对齐方式，如Sec。使用中所示的目录结构，并将对齐结果存储到具有相同目录结构的新文件夹dest_root中）： 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文件可能会破坏您的数据，因为在运行脚本时将自动删除它们。face_align.py时指定source_root ， dest_root和crop_size的参数; 2）将定制的min_face_size ， thresholds和nms_thresholds值传递到detector.py的detect_faces函数，以符合您的实际要求； 3）如果您发现使用face Arignment API的速度有点慢，则可以调用面部大小API，首先调整较小尺寸大于阈值的图像大小（在调用source_root ， dest_root和min_side的参数为您自己的值之前，请在调用face Api Api： python face_resize.py
./balanceroot中删除少于min_num样本的低弹药类，并带有目录结构，如SEC中所示的数据平衡和有效模型培训所示）： python remove_lowshot.py -root [root] -min_num [min_num]
# python remove_lowshot.py -root './data/train' -min_num 10
remove_lowshot.py时，将root和min_num的参数指定为您自己的值。☕
文件夹： ./
配置API（配置您的整体设置以进行培训和验证） 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 ,
),
}火车和验证API（所有有关培训和验证的人，即，进口软件包，超参数和数据加载器，模型与损失与优化器，火车和验证以及保存检查点） train.py 。由于MS-CELEB-1M在面部识别中充当成像网，因此我们在MS-CELEB-1M上预先训练了face.evolve模型，并在LFW，CFP_FF，CFP_FP，CFP_FP，AGEDB，CALFW，CALFW，CPLFW，CPLFW和VGGFAW和VGGFACE2_FP上执行验证。让我们一起研究细节。
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 ())))现在，您可以开始使用face.evolve并运行train.py 。用户友好的信息将在您的终端上弹出：
关于整体配置：
关于培训课程的数量：
关于骨干细节：
关于头部细节：
关于损失细节：
关于优化器详细信息：
关于简历培训：
关于培训状态和统计数据（当批次索引到达DISP_FREQ或每个时期结束时）：
关于验证统计和保存检查点（在每个时期的末尾）：
用watch -d -n 0.01 nvidia-smi监视Fly GPU占用。
请参考SEC。特定模型权重和相应性能的模型动物园。
功能提取API（从预训练模型中提取功能） ./util/extract_feature_v1.py extract_feature_v1.py（使用Pytorch build-In-In函数实施）和./util/extract_feature_v2.py （用OpenCV实施）。
使用TensorBoardX可视化培训和验证统计信息（请参阅第二节模型动物园）：
tensorboard --logdir /media/pc/6T/jasonjzhao/buffer/log
？
| 数据库 | 版本 | ＃身份 | ＃图像 | ＃框架 | ＃视频 | 下载链接 |
|---|---|---|---|---|---|---|
| LFW | 生的 | 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 |
| 小牛 | 生的 | 4,025 | 12,174 | - | - | Google Drive，Baidu Drive |
| 小牛 | Align_112x112 | 4,025 | 12,174 | - | - | Google Drive，Baidu Drive |
| CPLFW | 生的 | 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 | - | - | 百度开车 |
| casia-webface | RAW_V2 | 10,575 | 494,414 | - | - | Google Drive，Baidu Drive |
| casia-webface | 干净的 | 10,575 | 455,594 | - | - | Google Drive，Baidu Drive |
| MS-CELEB-1M | 干净的 | 100,000 | 5,084,127 | - | - | Google Drive |
| MS-CELEB-1M | Align_112x112 | 85,742 | 5,822,653 | - | - | Google Drive |
| vggface2 | 干净的 | 8,631 | 3,086,894 | - | - | Google Drive |
| vggface2_fp | Align_112x112 | - | - | - | - | Google Drive，Baidu Drive |
| 老化 | 生的 | 570 | 16,488 | - | - | Google Drive，Baidu Drive |
| 老化 | Align_112x112 | 570 | 16,488 | - | - | Google Drive，Baidu Drive |
| ijb-a | 干净的 | 500 | 5,396 | 20,369 | 2,085 | Google Drive，Baidu Drive |
| IJB-B | 生的 | 1,845 | 21,798 | 55,026 | 7,011 | Google Drive |
| CFP | 生的 | 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 | 生的 | 10,177 | 202,599 | - | - | Google Drive，Baidu Drive |
| CACD-VS | 生的 | 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 | 生的 | 80 | 65,000 | - | - | Baidu Drive，PW：XXP5 |
| nuaa-imposterdb | 生的 | 15 | 12,614 | - | - | Baidu Drive，PW：IF3N |
| 卡西亚河 | 生的 | 1,000 | - | - | 21,000 | Baidu Drive，PW：IZB3 |
| casia-fasd | 生的 | 50 | - | - | 600 | Baidu Drive，PW：H5UN |
| CASIA-MFSD | 生的 | 50 | - | - | 600 | |
| 重播攻击 | 生的 | 50 | - | - | 1200 | |
| Webface260m | 生的 | 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, Baidu Drive), VGGface2_LFW_Overlap.txt (Google Drive, Baidu Drive), 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）帮助研究人员/工程师快速删除其自己的私人数据集和公共数据集之间的重叠零件。？
模型
| 骨干 | 头 | 损失 | 培训数据 | 下载链接 |
|---|---|---|---|---|
| IR-50 | 弧形 | 焦点 | MS-CELEB-1M_ALIGN_112X112 | Google Drive，Baidu Drive |
环境
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
培训和验证统计
表现
| LFW | CFP_FF | CFP_FP | 老化 | 小牛 | CPLFW | vggface2_fp |
|---|---|---|---|---|---|---|
| 99.78 | 99.69 | 98.14 | 97.53 | 95.87 | 92.45 | 95.22 |
模型
| 骨干 | 头 | 损失 | 培训数据 | 下载链接 |
|---|---|---|---|---|
| IR-50 | 弧形 | 焦点 | 私人亚洲面对数据 | Google Drive，Baidu Drive |
环境
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
绩效（请按您自己的亚洲面对基准数据集进行评估）
模型
| 骨干 | 头 | 损失 | 培训数据 | 下载链接 |
|---|---|---|---|---|
| IR-152 | 弧形 | 焦点 | MS-CELEB-1M_ALIGN_112X112 | Baidu Drive，PW：B197 |
环境
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
培训和验证统计
表现
| LFW | CFP_FF | CFP_FP | 老化 | 小牛 | CPLFW | vggface2_fp |
|---|---|---|---|---|---|---|
| 99.82 | 99.83 | 98.37 | 98.07 | 96.03 | 93.05 | 95.50 |
？
2017年ICCV 2017 MS-CELEB-1M大规模面部识别硬设置/随机设置/低射击学习挑战。微信新闻，NUS ECE新闻，NUS ECE海报，Track-1奖励证书，Track-2的奖励证书，颁奖典礼。
2017年国家标准技术研究所（NIST）IARPA JANUS BENCHMARC A（IJB-A）无约束的面部验证挑战和识别挑战的第一号。微信新闻。
最先进的表现
？
？
请咨询并考虑引用以下论文：
@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},
}
