# In[8]:
import importlib
# In[9]:
importlib.reload(tsentiLoader)
# In[10]:
train_reader = tsentiLoader.tSentiReader(train_set[:10000], 20, tt)
valid_reader = tsentiLoader.tSentiReader(train_set[10000:10100], 20, tt)
test_reader = tsentiLoader.tSentiReader(test_set, 20, tt)
# In[44]:
class SentimentModel(nn.Module):
"""
Input: the outputs of bert
Model: BiLSTM
Output: sentence embedding
"""
def __init__( self,
bert ,
bert = bb.cuda()
transformer = transformer.cuda()
task_embedding = task_embedding.cuda()
senti_cls = nn.Linear(768, 2).cuda()
rdm_model = RDM_Model(768, 300, 256, 0.2).cuda()
rdm_classifier = nn.Linear(256, 2).cuda()
cm_model = CM_Model(300, 256, 2).cuda()
# In[13]:
# #### 各个任务的数据
train_file = "./trainingandtestdata/training.1600000.processed.noemoticon.csv"
test_file = "./trainingandtestdata/testdata.manual.2009.06.14.csv"
train_set, test_set = tsentiLoader.load_data(train_file, test_file)
senti_train_reader = tsentiLoader.tSentiReader(train_set[:10000], 20, tt)
senti_train_reader.label = np.delete(senti_train_reader.label, 1, axis=2)
senti_valid_reader = tsentiLoader.tSentiReader(train_set[10000:10500], 20, tt)
senti_valid_reader.label = np.delete(senti_valid_reader.label, 1, axis=2)
load_data_fast()
if torch.cuda.device_count() > 1:
# device_ids = [int(device_id) for device_id in sys.argv[1].split(",")]
device_ids = list(range(len(sys.argv[1].split(","))))
bert = nn.DataParallel(bert, device_ids=device_ids)
transformer = nn.DataParallel(transformer, device_ids=device_ids)
device_name = "cuda:%d" % device_ids[0]
device = torch.device(device_name)
bert.to(device)
rdm_model = RDM_Model(768, 300, 256, 0.2).cuda()
rdm_classifier = nn.Linear(256, 2).cuda()
cm_model = CM_Model(300, 256, 2).cuda()
rdm_classifier = nn.Linear(256, 2).cuda()
cm_log_dir = "MTLERD"
subj_file = "./rotten_imdb/subj.data"
obj_file = "./rotten_imdb/obj.data"
tr, dev, te = SubjObjLoader.load_data(subj_file, obj_file)
subj_train_reader = SubjObjLoader.SubjObjReader(tr, 20, tokenizer)
train_file = "./trainingandtestdata/training.1600000.processed.noemoticon.csv"
test_file = "./trainingandtestdata/testdata.manual.2009.06.14.csv"
train_set, test_set = tsentiLoader.load_data(train_file, test_file)
senti_train_reader = tsentiLoader.tSentiReader(train_set[:10000], 20,
tokenizer)
senti_train_reader.label = np.delete(senti_train_reader.label, 1, axis=2)
load_data_fast()
if torch.cuda.device_count() > 1:
# device_ids = [int(device_id) for device_id in sys.argv[1].split(",")]
device_ids = list(range(len(sys.argv[1].split(","))))
bert = nn.DataParallel(bert, device_ids=device_ids)
transformer = nn.DataParallel(transformer, device_ids=device_ids)
device_name = "cuda:%d" % device_ids[0]
device = torch.device(device_name)
bert.to(device)
transformer.to(device)