def train(args):
data = InputData(args.input, args.min_count, args.sample)
output_file_name = args.output
emb_size = len(data.word2id)
emb_dimension = args.dim
batch_size = args.mb
window_size = args.window
n_negs = args.n_negs
iteration = args.iters
initial_lr = args.lr
use_cuda = args.cuda
skip_gram_model = SkipGramModel(emb_size, emb_dimension)
if use_cuda: skip_gram_model = skip_gram_model.cuda()
optimizer = optim.SGD(skip_gram_model.parameters(), lr=initial_lr)
pair_count = data.evaluate_pair_count(window_size)
batch_count = iteration * pair_count / batch_size
process_bar = tqdm(range(int(batch_count)))
# skip_gram_model.save_embedding(
# data.id2word, 'begin_embedding.txt', use_cuda)
for i in process_bar:
pos_pairs = data.get_batch_pairs(batch_size, window_size)
neg_v = data.get_neg_v_neg_sampling(pos_pairs, n_negs)
pos_u = [pair[0] for pair in pos_pairs]
pos_v = [pair[1] for pair in pos_pairs]
pos_u = torch.LongTensor(pos_u)
pos_v = torch.LongTensor(pos_v)
neg_v = torch.LongTensor(neg_v)
if use_cuda:
pos_u = pos_u.cuda()
pos_v = pos_v.cuda()
neg_v = neg_v.cuda()
optimizer.zero_grad()
loss = skip_gram_model(pos_u, pos_v, neg_v)
loss.backward()
optimizer.step()
process_bar.set_description(
"\rLoss: %0.8f, lr: %0.6f" %
(loss.item(), optimizer.param_groups[0]['lr']))
if i * batch_size % 100000 == 0:
lr = initial_lr * (1.0 - 1.0 * i / batch_count)
for param_group in optimizer.param_groups:
param_group['lr'] = lr
skip_gram_model.save_embedding(data.id2word, output_file_name, use_cuda)
def predictFlow(np_arr, model):
input_data = InputData(np_arr, removePOffset=True, makeDimLess=True)
input_arr, target_arr = input_data.input, input_data.target
input_tr = torch.tensor(input_arr)
input_batch = input_tr.unsqueeze(0)
print('Running inference')
output_batch = model(input_batch.float())
output_tr = output_batch.squeeze(0)
output_arr = output_tr.detach().numpy()
print('Saving output')
saveOutput(output_arr, target_arr)
return 1
batch_size = 32
print("*** [Testing] ***")
print("Dataset: [{}]".format(conf["dataset"]))
print("test_data_path: [{}]".format(conf["test_data_path"]))
print("anomaly_class: [{}]".format(anoCls))
print("batch_size: [{}]".format(batch_size))
print("model_ticket: [{}]".format(model_ticket))
print("dropout: [{}]".format(dropout))
print(
"===================================================================")
if is_training == True:
if conf["dataset"] != "MNIST":
cb_ob = InputData(conf["train_data_path"], conf["valid_data_path"],
conf["anomaly_data_path"], None)
else:
cb_ob = InputMNISTData()
cb_ob.load_input_data(anoCls)
MODEL = model2(batch_size=batch_size,
max_iters=max_iters,
repeat=data_repeat,
dropout=dropout,
model_path=model_path,
data_ob=cb_ob,
log_dir=root_log_dir,
output_dir=output_dir,
learnrate_init=learn_rate_init,
dataset_name=dataset_name,
anoCls=anoCls,
