'net_state_dict': margin.state_dict()
},
os.path.join(save_dir,
'Iter_%06d_margin.ckpt' % total_iters))
# evaluate accuracy
if total_iters % 3000 == 0:
model.eval()
for phase in ['LFW', 'CFP_FP', 'AgeDB30']:
featureLs, featureRs = getFeature(model,
dataloaders[phase],
device,
flip=args.flip)
ACCs, threshold = evaluation_10_fold(featureLs,
featureRs,
dataset[phase],
method=args.method)
print(
'Epoch {}/{},{} average acc:{:.4f} average threshold:{:.4f}'
.format(epoch, args.epoch - 1, phase,
np.mean(ACCs) * 100, np.mean(threshold)))
if best_acc[phase] <= np.mean(ACCs) * 100:
best_acc[phase] = np.mean(ACCs) * 100
best_iters[phase] = total_iters
with open(test_logging_file, 'a') as f:
f.write(
'Epoch {}/{}, {} average acc:{:.4f} average threshold:{:.4f}'
.format(epoch, args.epoch - 1, phase,
np.mean(ACCs) * 100, np.mean(threshold)) +
'\n')
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
# from face_model import MobileFaceNet, l2_norm
from collections import namedtuple
dataloaders , dataset_sizes, dataset = load_test_data(50)
Genotype = namedtuple('Genotype', 'normal normal_concat reduce reduce_concat')
genotype = Genotype(normal=[('skip_connect', 1), ('sep_conv_3x3', 0), ('sep_conv_3x3', 0), ('skip_connect', 1), ('sep_conv_3x3', 1), ('sep_conv_3x3', 3), ('sep_conv_3x3', 1), ('dil_conv_5x5', 4)], normal_concat=range(2, 6), reduce=[('sep_conv_3x3', 0), ('skip_connect', 1), ('dil_conv_5x5', 2), ('max_pool_3x3', 1), ('sep_conv_3x3', 2), ('sep_conv_3x3', 1), ('sep_conv_5x5', 0), ('sep_conv_3x3', 3)], reduce_concat=range(2, 6))
from face_search.model_search_ms1m import Network
model =NetworkImageNet(48, 85742, 14, genotype).to(device)
# print(model)/data/face_recognition/1MobileFaceNet_Tutorial_Pytorch-master1/saving_Faces_emore_ckpt/Iter_009000_margin.ckpt
checkpoint=torch.load('best_arc64\Iter_725000_model.ckpt')
# model = MobileFaceNet(512).to(device)
# state_dict = torch.load('arc_center_focal\Iter_555000_model.ckpt')['net_state_dict']
# from collections import OrderedDict
# new_state_dict = OrderedDict()
# for k, v in state_dict.items():
# name = k[7:] # remove `module.`
# new_state_dict[name] = v
# load params
model.load_state_dict(state_dict)
# print(state_dict)
# model.drop_path_prob = 0
model.eval()
for phase in ['LFW', 'CFP_FP', 'AgeDB30','privacy']:
featureLs, featureRs = getFeature(model, dataloaders[phase], device, flip = True)
# ACCs, threshold = evaluation_10_fold(featureLs, featureRs, dataset[phase], method = 'l2_distance')
ACCs, threshold = evaluation_10_fold(featureLs, featureRs, dataset[phase], method = 'cos_distance')
print('Epoch {}/{}，{} average acc:{:.4f} average threshold:{:.4f}'.format(1, 1, phase, np.mean(ACCs) * 100, np.mean(threshold)))