def main():
# Views the training images and displays the distance on anchor-negative and anchor-positive
test_display_triplet_distance = True
# print the experiment configuration
print('\nparsed options:\n{}\n'.format(vars(args)))
print('\nNumber of Classes:\n{}\n'.format(len(train_dir.classes)))
# instantiate model and initialize weights
model = FaceModel(embedding_size=args.embedding_size,
num_classes=len(train_dir.classes),
pretrained=False)
model.to(device)
triplet_loss = TripletMarginLoss(args.margin)
optimizer = create_optimizer(model, args.lr)
# optionally resume from a checkpoint
if args.resume:
if os.path.isfile(args.resume):
print('=> loading checkpoint {}'.format(args.resume))
checkpoint = torch.load(args.resume)
args.start_epoch = checkpoint['epoch']
checkpoint = torch.load(args.resume)
model.load_state_dict(checkpoint['state_dict'])
else:
print('=> no checkpoint found at {}'.format(args.resume))
start = args.start_epoch
end = start + args.epochs
for epoch in range(start, end):
print(80 * '=')
print('Epoch [{}/{}]'.format(epoch, end - 1))
time0 = time.time()
own_train(train_loader, model, triplet_loss, optimizer, epoch,
data_size)
print(f' Execution time = {time.time() - time0}')
print(80 * '=')
if test_display_triplet_distance:
display_triplet_distance(model, train_loader,
LOG_DIR + "/train_{}".format(epoch))
print(80 * '=')
time0 = time.time()
own_test(test_loader, model, epoch)
print(f' Execution time = {time.time() - time0}')
print(80 * '=')
if test_display_triplet_distance:
display_triplet_distance_test(model, test_loader,
LOG_DIR + "/test_{}".format(epoch))
def main():
#img = Image.open('./1.jpg')
#img_array=np.asarray(img)
#print (img_array.shape)
# Get cropped and prewhitened image tensor
#print(img_cropped.shape)
test_display_triplet_distance = True
# print the experiment configuration
print('\nparsed options:\n{}\n'.format(vars(args)))
print('\nNumber of Classes:\n{}\n'.format(len(train_dir.classes)))
# instantiate model and initialize weights
# optionally resume from a checkpoint
if args.resume:
if os.path.isfile(args.resume):
print('=> loading checkpoint {}'.format(args.resume))
checkpoint = torch.load(args.resume)
args.start_epoch = checkpoint['epoch']
else:
checkpoint = None
print('=> no checkpoint found at {}'.format(args.resume))
model = InceptionResnetV1(fine_turn=1,
pretrained=None,
num_classes=len(train_dir.classes),
device=device)
state_dict = {}
cached_file1 = "./20180408-102900-casia-webface-logits.pt"
cached_file2 = "20180408-102900-casia-webface-features.pt"
state_dict.update(torch.load(cached_file1))
state_dict.update(torch.load(cached_file2))
model.load_state_dict(state_dict)
if args.cuda:
model.cuda()
optimizer = create_optimizer(model, args.lr)
start = args.start_epoch
end = start + args.epochs
test(test_loader, model)
display_triplet_distance_test(model, test_loader,
LOG_DIR + "/test_{}".format(1))
"""for epoch in range(start, end):
def main():
#test_display_triplet_distance= True
'''
why test_display_triplet_distance= True in center loss.py?????
'''
test_display_triplet_distance = True
# print the experiment configuration
print('\nparsed options:\n{}\n'.format(vars(args)))
print('\nNumber of Classes:\n{}\n'.format(str(6400)))
num_classes = 6400
# optionally resume from a checkpoint
if args.resume:
if os.path.isfile(args.resume):
print('=> loading checkpoint {}'.format(args.resume))
checkpoint = torch.load(args.resume)
args.start_epoch = checkpoint['epoch']
else:
checkpoint = None
print('=> no checkpoint found at {}'.format(args.resume))
#print(checkpoint)
# instantiate model and initialize weights
#model = FaceModelSoftmax(embedding_size=args.embedding_size,num_classes=len(train_dir.classes),checkpoint=checkpoint)
model = FaceModelSoftmax(embedding_size=args.embedding_size,
num_classes=num_classes,
checkpoint=checkpoint)
if args.cuda:
#print("you are using gpu")
model.cuda()
optimizer = create_optimizer(model, args.lr)
start = args.start_epoch
end = start + args.epochs
for epoch in range(start, end):
train(train_loader, model, optimizer, epoch)
test(test_loader, model, epoch)
testaccuracy(testaccuracy_loader, model, epoch)
testRecall(testaccuracy_loader, model, epoch)
if test_display_triplet_distance:
display_triplet_distance_test(model, test_loader,
LOG_DIR + "/test_{}".format(epoch))
display_triplet_distance(model, train_loader,
LOG_DIR + "/train_{}".format(epoch))
def main():
# Views the training images and displays the distance on anchor-negative and anchor-positive
test_display_triplet_distance = True
# print the experiment configuration
print('\nparsed options:\n{}\n'.format(vars(args)))
print('\nNumber of Classes:\n{}\n'.format(len(train_dir.classes)))
# instantiate model and initialize weights
# embedding_net = EmbeddingNetL2()
# model = TripletNet(embedding_net)
model = FaceModel(embedding_size=args.embedding_size,
num_classes=len(train_dir.classes),
pretrained=False)
if args.cuda:
model.cuda()
optimizer = create_optimizer(model, args.lr)
# optionally resume from a checkpoint
if args.resume:
if os.path.isfile(args.resume):
print('=> loading checkpoint {}'.format(args.resume))
checkpoint = torch.load(args.resume)
args.start_epoch = checkpoint['epoch']
checkpoint = torch.load(args.resume)
model.load_state_dict(checkpoint['state_dict'])
else:
print('=> no checkpoint found at {}'.format(args.resume))
start = args.start_epoch
end = start + args.epochs
for epoch in range(start, end):
train(train_loader, model, optimizer, epoch)
test(test_loader, model, epoch)
if test_display_triplet_distance:
display_triplet_distance(model, train_loader, LOG_DIR + "/train_{}".format(epoch))
display_triplet_distance_test(model, test_loader, LOG_DIR + "/test_{}".format(epoch))
def main_loop():
test_display_triplet_distance= True
# print the experiment configuration
# print('\nparsed options:\n{}\n'.format(vars(args))
# print('\nNumber of Classes:\n{}\n'.format(len(train_dir.classes)))
# instantiate model and initialize weights
# optionally resume from a checkpoint
checkpoint = None
if resume:
if os.path.isfile(resume_path):
print('=> loading checkpoint {}'.format(resume_path))
checkpoint = torch.load(resume_path)
args['start_epoch'] = checkpoint['epoch']
else:
checkpoint = None
print('=> no checkpoint found at {}'.format(resume_path))
model = FaceModelCenter(embedding_size=embedding_size,num_classes=len(train_dir.classes)
,checkpoint=checkpoint)
if cuda:
model.cuda()
optimizer = create_optimizer(model, lr)
start = start_epoch
end = start + int(epochs)
print(model)
for epoch in range(start, end):
train(train_loader, model, optimizer, epoch)
test(test_loader, model, epoch)
if test_display_triplet_distance:
display_triplet_distance_test(model,test_loader,LOG_DIR+"/test_{}".format(epoch))
model = FaceModel(embedding_size=args.embedding_size,num_classes=len(train_dir.classes))
if args.cuda:
model.cuda()
optimizer = create_optimizer(model, args.lr)
start = args.start_epoch
end = start + args.epochs
for epoch in range(start, end):
train(train_loader, model, optimizer, epoch)
test(test_loader, model, epoch)
testaccuracy(testaccuracy_loader, model, epoch)
if test_display_triplet_distance:
display_triplet_distance_test(model,test_loader,LOG_DIR+"/test_{}".format(epoch))
def accuracy(output, target, topk=(1,)):
"""Computes the precision@k for the specified values of k"""
maxk = max(topk)
batch_size = target.size(0)
_, pred = output.topk(maxk, 1, True, True)
pred = pred.t()
correct = pred.eq(target.view(1, -1).expand_as(pred))
res = []
for k in topk: