def __init__(self,
data_name,
img_dir,
bit,
visdom=True,
batch_size=128,
cuda=True,
**kwargs):
super(PRDH, self).__init__("PRDH", data_name, bit, batch_size, visdom,
cuda)
self.train_data, self.valid_data = single_data(data_name,
img_dir,
batch_size=batch_size,
**kwargs)
self.loss_store = [
"inter loss", 'intra loss', 'decorrelation loss',
'regularization loss', 'loss'
]
self.parameters = {'gamma': 1, 'lambda': 1}
self.max_epoch = 500
self.lr = {'img': 10**(-1.5), 'txt': 10**(-1.5)}
self.lr_decay_freq = 1
self.lr_decay = (10**(-1.5) - 1e-6) / self.max_epoch
self.num_train = len(self.train_data)
self.img_model = cnnf.get_cnnf(bit)
self.txt_model = MLP.MLP(self.train_data.get_tag_length(),
bit,
leakRelu=False)
self.F_buffer = torch.randn(self.num_train, bit)
self.G_buffer = torch.randn(self.num_train, bit)
self.train_L = self.train_data.get_all_label()
self.ones = torch.ones(batch_size, 1)
self.ones_ = torch.ones(self.num_train - batch_size, 1)
if cuda:
self.img_model = self.img_model.cuda()
self.txt_model = self.txt_model.cuda()
self.train_L = self.train_L.cuda()
self.F_buffer = self.F_buffer.cuda()
self.G_buffer = self.G_buffer.cuda()
self.ones = self.ones.cuda()
self.ones_ = self.ones_.cuda()
self.Sim = calc_neighbor(self.train_L, self.train_L)
self.B = torch.sign(self.F_buffer + self.G_buffer)
optimizer_img = SGD(self.img_model.parameters(), lr=self.lr['img'])
optimizer_txt = SGD(self.txt_model.parameters(), lr=self.lr['txt'])
self.optimizers = [optimizer_img, optimizer_txt]
self._init()
def __init__(self,
data_name: str,
val_freq: int,
img_dir: str,
bit: int,
visdom=True,
batch_size=128,
cuda=True,
**kwargs):
super(CMHH, self).__init__("CMHH", data_name, bit, batch_size, visdom,
cuda)
self.train_data, self.valid_data = single_data(data_name,
img_dir,
batch_size=batch_size,
**kwargs)
self.loss_store = ['focal loss', 'quantization loss', 'loss']
self.parameters = {'gamma': 2, 'alpha': 0.5, 'beta': 0.5, 'lambda': 0}
self.lr = {'img': 0.02, 'txt': 0.2}
self.lr_decay_freq = 15
self.lr_decay = 0.5
self.val_freq = val_freq
self.num_train = len(self.train_data)
self.img_model = alexnet.get_alexnet(bit=bit)
self.txt_model = MLP.MLP(self.train_data.get_tag_length(), bit)
self.train_label = self.train_data.get_all_label()
self.F_buffer = torch.randn(self.num_train, bit)
self.G_buffer = torch.randn(self.num_train, bit)
if cuda:
self.img_model = self.img_model.cuda()
self.txt_model = self.txt_model.cuda()
self.train_label = self.train_label.cuda()
self.F_buffer = self.F_buffer.cuda()
self.G_buffer = self.G_buffer.cuda()
self.B = torch.sign(self.F_buffer + self.G_buffer)
optimizer_img = SGD(self.img_model.parameters(),
lr=self.lr['img'],
momentum=0.9)
optimizer_txt = SGD(self.txt_model.parameters(),
lr=self.lr['txt'],
momentum=0.9)
self.optimizers = [optimizer_img, optimizer_txt]
self._init()
def __init__(self,
data_name: str,
img_dir: str,
bit: int,
visdom=True,
batch_size=128,
cuda=True,
**kwargs):
super(CHN, self).__init__("CHN", data_name, bit, batch_size, visdom,
cuda)
self.train_data, self.valid_data = single_data(data_name,
img_dir,
batch_size=batch_size,
**kwargs)
self.loss_store = ['cosine loss', 'quantization loss', 'loss']
self.parameters = {'beta': 0.8, 'lambda': 0.01}
self.lr = {'img': 0.01, 'txt': 1}
self.lr_decay_freq = 10
self.lr_decay = 0.5
self.num_train = len(self.train_data)
self.img_model = cnnf.get_cnnf(bit)
self.txt_model = MLP.MLP(self.train_data.get_tag_length(), bit)
self.F_buffer = torch.randn(self.num_train, bit)
self.G_buffer = torch.randn(self.num_train, bit)
self.train_L = self.train_data.get_all_label()
if cuda:
self.img_model = self.img_model.cuda()
self.txt_model = self.txt_model.cuda()
self.train_L = self.train_L.cuda()
self.F_buffer = self.F_buffer.cuda()
self.G_buffer = self.G_buffer.cuda()
optimizer_img = SGD(self.img_model.parameters(),
lr=self.lr['img'],
momentum=0.9)
optimizer_txt = SGD(self.txt_model.parameters(),
lr=self.lr['txt'],
momentum=0.9)
self.optimizers = [optimizer_img, optimizer_txt]
self._init()