def __init__(self, opt):
self.opt = opt
absa_dataset = ABSADatesetReader(dataset=opt.dataset,
embed_dim=opt.embed_dim,
use_bert=True,
max_len=70)
self.train_data_loader = BucketIterator(data=absa_dataset.train_data,
batch_size=opt.batch_size,
shuffle=True,
max_len=90)
self.test_data_loader = BucketIterator(data=absa_dataset.test_data,
batch_size=opt.batch_size,
shuffle=False,
max_len=90)
self.model = opt.model_class(absa_dataset.embedding_matrix,
opt).to(opt.device)
self._print_args()
self.global_f1 = 0.
if torch.cuda.is_available():
print('cuda memory allocated:',
torch.cuda.memory_allocated(device=opt.device.index))
def __init__(self, opt):
self.opt = opt
absa_dataset = ABSADatesetReader(dataset=opt.dataset,
embed_dim=opt.embed_dim)
self.train_data_loader = BucketIterator(data=absa_dataset.train_data,
batch_size=opt.batch_size,
shuffle=True)
self.test_data_loader = BucketIterator(data=absa_dataset.test_data,
batch_size=opt.batch_size,
shuffle=False)
self.model = opt.model_class(absa_dataset.embedding_matrix,
opt).to(opt.device)
# # self.model = opt.model_class(absa_dataset.embedding_matrix, opt)
#
# # multi-gpu training (should be after apex fp16 initialization)
# if opt.n_gpu > 1:
# self.model = torch.nn.DataParallel(self.model)
#
# # Distributed training (should be after apex fp16 initialization)
# if opt.local_rank != -1:
# self.model = torch.nn.parallel.DistributedDataParallel(self.model, device_ids=[opt.local_rank],
# output_device=opt.local_rank,
# find_unused_parameters=True)
# self.model.to(opt.device)
self._print_args()
self.global_f1 = 0.
if torch.cuda.is_available():
print('cuda memory allocated:',
torch.cuda.memory_allocated(device=opt.device.index))
def __init__(self, opt, post_vocab):
self.opt = opt
absa_dataset = ABSADatesetReader(dataset=opt.dataset,
embed_dim=opt.embed_dim,
post_vocab=args['post_vocab'])
self.train_data_loader = BucketIterator(data=absa_dataset.train_data,
batch_size=opt.batch_size,
shuffle=True)
self.test_data_loader = BucketIterator(data=absa_dataset.test_data,
batch_size=opt.batch_size,
shuffle=False)
common_adj = absa_dataset.common_adj
fre_embedding = absa_dataset.fre_embedding
if torch.cuda.is_available():
common_adj = common_adj.cuda()
fre_embedding = fre_embedding.cuda()
self.model = opt.model_class(absa_dataset.embedding_matrix, common_adj,
fre_embedding, post_vocab,
opt).to(opt.device)
self._print_args()
self.global_f1 = 0.
if torch.cuda.is_available():
print('cuda memory allocated:',
torch.cuda.memory_allocated(device=opt.device.index))
def __init__(self, opt):
self.opt = opt
absa_dataset = ABSADatesetReader(dataset=opt.dataset, embed_dim=opt.embed_dim, max_seq_len=opt.max_seq_len)
self.train_data_loader = DataLoader(dataset=absa_dataset.train_data, batch_size=opt.batch_size, shuffle=True)
self.test_data_loader = DataLoader(dataset=absa_dataset.test_data, batch_size=len(absa_dataset.test_data), shuffle=False)
self.final_data_loader = DataLoader(dataset=absa_dataset.final_data, batch_size=len(absa_dataset.final_data), shuffle=False)
self.model = opt.model_class(absa_dataset.embedding_matrix, opt).to(opt.device)
self._init_and_print_parameters()
def __init__(self, opt):
self.opt = opt
absa_dataset = ABSADatesetReader(dataset=opt.dataset, embed_dim=opt.embed_dim)
self.train_data_loader = BucketIterator(data=absa_dataset.train_data, batch_size=opt.batch_size, shuffle=True)
self.test_data_loader = BucketIterator(data=absa_dataset.test_data, batch_size=opt.batch_size, shuffle=False)
self.model = opt.model_class(absa_dataset.embedding_matrix, opt).to(opt.device)
self._print_args()
self.global_f1 = 0.
def __init__(self, opt):
self.opt = opt
absa_dataset = ABSADatesetReader(dataset=opt.dataset, embed_dim=opt.embed_dim)
valset_len = int(len(absa_dataset.train_data) * 0.1)
self.train_data_loader = BucketIterator(data=absa_dataset.train_data[:-valset_len], batch_size=opt.batch_size, shuffle=True)
self.val_data_loader = BucketIterator(data=absa_dataset.train_data[-valset_len:], batch_size=opt.batch_size, shuffle=False)
bert = BertModel.from_pretrained('bert-base-chinese') #中文预训练模型，如果要套ALBERT，得把ALBERT封装好，在这里导入，并把模型参数都改掉
self.model = nn.DataParallel(opt.model_class(bert, opt).to(opt.device))
self._print_args()
def __init__(self, opt):
self.opt = opt
print('> training arguments:')
for arg in vars(opt):
print('>>> {0}: {1}'.format(arg, getattr(opt, arg)))
if opt.dataset in ['restaurant', 'laptop']:
self.my_dataset = ABSADatesetReader(dataset=opt.dataset,
embed_dim=opt.embed_dim,
max_seq_len=opt.max_seq_len)
self.train_data_loader = DataLoader(
dataset=self.my_dataset.train_data,
batch_size=opt.batch_size,
shuffle=True)
self.dev_data_loader = DataLoader(
dataset=self.my_dataset.test_data,
batch_size=len(self.my_dataset.test_data),
shuffle=False)
self.test_data_loader = DataLoader(
dataset=self.my_dataset.test_data,
batch_size=len(self.my_dataset.test_data),
shuffle=False)
elif opt.dataset in ['zol_cellphone']:
self.my_dataset = ZOLDatesetReader(
dataset=opt.dataset,
embed_dim=opt.embed_dim,
max_seq_len=opt.max_seq_len,
cnn_model_name=opt.cnn_model_name)
self.train_data_loader = DataLoader(
dataset=self.my_dataset.train_data,
batch_size=opt.batch_size,
shuffle=True)
self.dev_data_loader = DataLoader(dataset=self.my_dataset.dev_data,
batch_size=len(
self.my_dataset.dev_data),
shuffle=False)
self.test_data_loader = DataLoader(
dataset=self.my_dataset.test_data,
batch_size=len(self.my_dataset.test_data),
shuffle=False)
self.idx2word = self.my_dataset.idx2word
self.writer = SummaryWriter(log_dir=opt.logdir)
self.model = opt.model_class(self.my_dataset.embedding_matrix,
opt).to(opt.device)
self.reset_parameters()
def __init__(self, opt):
self.opt = opt
absa_dataset = ABSADatesetReader(dataset=opt.dataset,
embed_dim=opt.embed_dim,
max_seq_len=opt.max_seq_len)
self.train_data_loader = DataLoader(dataset=absa_dataset.train_data,
batch_size=opt.batch_size,
shuffle=True)
self.test_data_loader = DataLoader(dataset=absa_dataset.test_data,
batch_size=opt.batch_size,
shuffle=False)
self.model = opt.model_class(absa_dataset.embedding_matrix,
opt).to(opt.device)
print("cuda memory allocated:", torch.cuda.memory_allocated(device=0))
self._print_args()
def __init__(self, args):
self.args = args
torch.manual_seed(self.args.seed)
if self.args.device == "cuda":
torch.cuda.set_device(self.args.gpu)
torch.cuda.manual_seed(self.args.seed)
np.random.seed(self.args.seed)
random.seed(self.args.seed)
print('> training arguments:')
for arg in vars(args):
print('>>> {0}: {1}'.format(arg, getattr(args, arg)))
absa_dataset = ABSADatesetReader(dataset=args.dataset,
embed_dim=args.embed_dim,
max_seq_len=args.max_seq_len)
if self.args.dev > 0.0:
random.shuffle(absa_dataset.train_data.data)
dev_num = int(len(absa_dataset.train_data.data) * self.args.dev)
absa_dataset.dev_data.data = absa_dataset.train_data.data[:dev_num]
absa_dataset.train_data.data = absa_dataset.train_data.data[
dev_num:]
# print(len(absa_dataset.train_data.data), len(absa_dataset.dev_data.data))
self.train_data_loader = DataLoader(dataset=absa_dataset.train_data,
batch_size=args.batch_size,
shuffle=True)
if self.args.dev > 0.0:
self.dev_data_loader = DataLoader(dataset=absa_dataset.dev_data,
batch_size=len(
absa_dataset.dev_data),
shuffle=False)
self.test_data_loader = DataLoader(dataset=absa_dataset.test_data,
batch_size=len(
absa_dataset.test_data),
shuffle=False)
self.mdl = args.model_class(
self.args,
embedding_matrix=absa_dataset.embedding_matrix,
aspect_embedding_matrix=absa_dataset.aspect_embedding_matrix)
self.reset_parameters()
self.mdl.encoder.weight.requires_grad = True
self.mdl.encoder_aspect.weight.requires_grad = True
self.mdl.to(device)
self.criterion = nn.CrossEntropyLoss()
def __init__(self, opt):
self.opt = opt
print('> training arguments:')
for arg in vars(opt):
print('>>> {0}: {1}'.format(arg, getattr(opt, arg)))
if not os.path.exists(opt.checkpoint):
os.mkdir(opt.checkpoint)
# torch.manual_seed(opt.rand_seed)
# torch.cuda.manual_seed_all(opt.rand_seed)
transform = transforms.Compose([
transforms.RandomCrop(
opt.crop_size
), #args.crop_size, by default it is set to be 224
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize((0.485, 0.456, 0.406), (0.229, 0.224, 0.225))
])
absa_dataset = ABSADatesetReader(transform, dataset=opt.dataset, embed_dim=opt.embed_dim, max_seq_len=opt.max_seq_len, \
path_image=opt.path_image)
self.train_data_loader = DataLoader(dataset=absa_dataset.train_data,
batch_size=opt.batch_size,
shuffle=True)
self.dev_data_loader = DataLoader(dataset=absa_dataset.dev_data,
batch_size=opt.batch_size,
shuffle=False)
self.test_data_loader = DataLoader(dataset=absa_dataset.test_data,
batch_size=opt.batch_size,
shuffle=False)
#self.writer = SummaryWriter(log_dir=opt.logdir)
print('building model')
net = getattr(resnet, 'resnet152')()
net.load_state_dict(
torch.load(os.path.join(opt.resnet_root, 'resnet152.pth')))
self.encoder = myResnet(net, opt.fine_tune_cnn,
self.opt.device).to(device)
self.model = opt.model_class(absa_dataset.embedding_matrix,
opt).to(device)
self.reset_parameters()
def __init__(self,
module_class,
model_name,
dataset='twitter',
embed_dim=100,
max_seq_len=40,
batch_size=128):
absa_dataset = ABSADatesetReader(dataset=dataset,
embed_dim=embed_dim,
max_seq_len=max_seq_len)
self.train_data_loader = DataLoader(dataset=absa_dataset.train_data,
batch_size=batch_size,
shuffle=True)
self.test_data_loader = DataLoader(dataset=absa_dataset.test_data,
batch_size=len(
absa_dataset.test_data),
shuffle=False)
self.writer = SummaryWriter(log_dir='{0}_logs'.format(model_name))
self.model = module_class(absa_dataset.embedding_matrix).to(device)
def __init__(self, opt):
self.opt = opt
print('> training arguments:')
for arg in vars(opt):
print('>>> {0}: {1}'.format(arg, getattr(opt, arg)))
absa_dataset = ABSADatesetReader(dataset=opt.dataset,
embed_dim=opt.embed_dim,
max_seq_len=opt.max_seq_len)
self.train_data_loader = DataLoader(dataset=absa_dataset.train_data,
batch_size=opt.batch_size,
shuffle=True)
self.test_data_loader = DataLoader(dataset=absa_dataset.test_data,
batch_size=len(
absa_dataset.test_data),
shuffle=False)
self.writer = SummaryWriter(log_dir=opt.logdir)
self.model = opt.model_class(absa_dataset.embedding_matrix,
opt).to(device)
self.reset_parameters()
def __init__(self, opt):
self.opt = opt
print('> training arguments:')
for arg in vars(opt):
print('>>> {0}: {1}'.format(arg, getattr(opt, arg)))
absa_dataset = ABSADatesetReader(dataset=opt.dataset,
embed_dim=opt.embed_dim,
max_seq_len=opt.max_seq_len,
fold_num=opt.fold_num)
self.train_data_loader = DataLoader(dataset=absa_dataset.train_data,
batch_size=opt.batch_size,
shuffle=True)
self.test_data_loader = DataLoader(dataset=absa_dataset.test_data,
batch_size=opt.batch_size,
shuffle=False)
if opt.checkpoint_path != "":
self.model = torch.load(opt.checkpoint_path)
else:
self.model = opt.model_class(absa_dataset.embedding_matrix,
opt).to(device)
self.reset_parameters()