def __init__(self, opt):
self.opt = opt
fname = {
'cr': {
'train': './datasets/cr/train.csv',
'test': './datasets/cr/dev.csv'
},
'mr': {
'train': './datasets/mr/train.csv',
'test': './datasets/mr/dev.csv'
},
'mpqa': {
'train': './datasets/mpqa/train.csv',
'test': './datasets/mpqa/dev.csv'
},
'subj': {
'train': './datasets/subj/train.csv',
'test': './datasets/subj/dev.csv'
},
'sst2': {
'train': './datasets/sst2/train.csv',
'test': './datasets/sst2/test.csv'
},
'TREC': {
'train': './datasets/TREC/train.csv',
'test': './datasets/TREC/test.csv'
},
}
if os.path.exists(opt.dataset + '_word2idx.pkl'):
print("loading {0} tokenizer...".format(opt.dataset))
with open(opt.dataset + '_word2idx.pkl', 'rb') as f:
word2idx = pickle.load(f)
self.tokenizer = Tokenizer(word2idx=word2idx)
else:
print("reading {0} dataset...".format(opt.dataset))
text = ABSADatesetReader.__read_text__(
[fname[opt.dataset]['train'], fname[opt.dataset]['test']])
self.tokenizer = Tokenizer()
self.tokenizer.fit_on_text(text)
with open(opt.dataset + '_word2idx.pkl', 'wb') as f:
pickle.dump(self.tokenizer.word2idx, f)
embedding_matrix = build_embedding_matrix(self.tokenizer.word2idx,
opt.embed_dim, opt.dataset)
self.model = opt.model_class(embedding_matrix, opt).to(opt.device)
print('loading model {0} ...'.format(opt.model_name))
self.model.load_state_dict(torch.load(opt.state_dict_path))
self.model = self.model
# switch model to evaluation mode
self.model.eval()
torch.autograd.set_grad_enabled(False)
def __init__(self, opt):
self.opt = opt
fname = {
'twitter': {
'train': './datasets/acl-14-short-data/train.raw',
'test': './datasets/acl-14-short-data/test.raw'
},
'rest14': {
'train': './datasets/semeval14/restaurant_train.raw',
'test': './datasets/semeval14/restaurant_test.raw'
},
'lap14': {
'train': './datasets/semeval14/laptop_train.raw',
'test': './datasets/semeval14/laptop_test.raw'
},
'rest15': {
'train': './datasets/semeval15/restaurant_train.raw',
'test': './datasets/semeval15/restaurant_test.raw'
},
'rest16': {
'train': './datasets/semeval16/restaurant_train.raw',
'test': './datasets/semeval16/restaurant_test.raw'
},
}
if os.path.exists(opt.dataset + '_word2idx.pkl'):
print("loading {0} tokenizer...".format(opt.dataset))
with open(opt.dataset + '_word2idx.pkl', 'rb') as f:
word2idx = pickle.load(f)
self.tokenizer = Tokenizer(word2idx=word2idx)
else:
print("reading {0} dataset...".format(opt.dataset))
text = ABSADatesetReader.__read_text__(
[fname[opt.dataset]['train'], fname[opt.dataset]['test']])
self.tokenizer = Tokenizer()
self.tokenizer.fit_on_text(text)
with open(opt.dataset + '_word2idx.pkl', 'wb') as f:
pickle.dump(self.tokenizer.word2idx, f)
embedding_matrix = build_embedding_matrix(self.tokenizer.word2idx,
opt.embed_dim, opt.dataset)
self.model = opt.model_class(embedding_matrix, opt).to(opt.device)
print('loading model {0} ...'.format(opt.model_name))
self.model.load_state_dict(torch.load(opt.state_dict_path))
self.model = self.model
# switch model to evaluation mode
self.model.eval()
torch.autograd.set_grad_enabled(False)