word2id = {}
for word in tokens:
word2id[word] = id
id += 1
args.embed_num = len(tokens)
args.class_num = 2
args.kernel_sizes = [int(k) for k in args.kernel_sizes.split(',')]
#print("\nParameters:")
#for attr, value in sorted(args.__dict__.items()):
# print("\t{}={}".format(attr.upper(), value))
model = CNN_Text(args)
if torch.cuda.is_available():
model.cuda()
optimizer = torch.optim.Adam(model.parameters(), lr=args.lr)
report_interval = 5000
for epoch in range(1, args.epochs + 1):
train_batch_i = 0
batch_counter = 0
accumulated_loss = 0
train_sents_scaned = 0
train_num_correct = 0
model.train()
print('--' * 20)
start_time = time.time()
train_data = np.array(train_data)
train_labels = np.array(train_labels)
rand_idx = np.random.permutation(len(train_data))
use_cuda = torch.cuda.is_available()
#get data
train_loader = Data.DataLoader(dataset=CustomDataset(path="train.json",
balance=False),
batch_size=BATCH_SIZE,
shuffle=True)
test_loader = Data.DataLoader(dataset=CustomDataset(path="test.json",
balance=False),
batch_size=BATCH_SIZE,
shuffle=True)
#initialize model
cnn = CNN_Text()
if use_cuda:
cnn = cnn.cuda()
optimizer = torch.optim.Adam(cnn.parameters(), lr=LR, weight_decay=0.0005)
#train
for epoch in range(EPOCH):
print("epoch :")
if epoch % 5 == 0:
test(cnn, test_loader, use_cuda)
for step, data in enumerate(train_loader):
vec, lens, label = data
#print(vec.shape)
if use_cuda:
vec = vec.cuda()
label = label.cuda()
output = cnn(vec)
label = label.to(dtype=torch.int64)