def main(args):
model_class = get_model_class(args.model)
model_class.add_config(argparser)
args = argparser.parse_args()
args.run_id = datetime.datetime.now().strftime("%Y_%m_%d_%H_%M_%S")
root_dir = os.path.dirname(os.path.realpath(__file__))
# only use generated run_path if none provided by user
if args.run_path is None:
args.run_path = os.path.join(root_dir, args.run_dir, args.run_id)
if not os.path.exists(args.run_path):
os.makedirs(args.run_path)
global outputManager
outputManager = OutputManager(args.run_path)
outputManager.say(args)
#if not os.path.exists(args.run_dir):
# os.makedirs(args.run_dir)
#assert os.path.isdir(args.run_dir)
#assert not os.path.exists(args.run_path)
#os.makedirs(args.run_path)
outputManager.say("\nRun ID: {}\nRun Path: {}\n\n".format(
args.run_id, args.run_path))
train_corpus_path = os.path.dirname(args.train) + "/corpus.tsv.gz"
train_corpus = Corpus(
[tuple([train_corpus_path,
os.path.dirname(args.train)])])
valid_corpus_path = os.path.dirname(args.eval) + "/corpus.tsv.gz"
valid_corpus = Corpus(
[tuple([valid_corpus_path,
os.path.dirname(args.eval)])])
outputManager.say("Corpus loaded.\n")
embs = load_embedding(args.embedding) if args.embedding else None
embedding_layer = EmbeddingLayer(args.n_d, ['<s>', '</s>'], embs)
model = model_class(embedding_layer, args)
if args.cuda:
model.cuda()
outputManager.say("\n{}\n\n".format(model))
outputManager.say(model.state_dict().keys())
needs_grad = lambda x: x.requires_grad
optimizer = optim.Adam(filter(needs_grad, model.parameters()), lr=args.lr)
outputManager.say(optimizer.state_dict())
if args.load_model:
outputManager.say("Loading pretrained model")
model.load_state_dict(torch.load(args.load_model))
else:
outputManager.say("Training will begin from scratch")
best_dev = 0
iter_cnt = 0
current_dev = evaluate(iter_cnt, args.eval + "/dev", model, valid_corpus,
args)
evaluate(iter_cnt, args.eval + "/test", model, valid_corpus, args, False)
for epoch in range(args.max_epoch):
iter_cnt = train(iter_cnt, model, train_corpus, args, optimizer)
current_dev = evaluate(iter_cnt, args.eval + "/dev", model,
valid_corpus, args)
if current_dev > best_dev:
best_dev = current_dev
evaluate(iter_cnt, args.eval + "/test", model, valid_corpus, args,
False)
outputManager.say("\n")
if args.save_model:
torch.save(model.state_dict(), args.save_model)
torch.save(model, args.save_model + '-complete')
def main(args):
model_class = get_model_class(args.model)
model_class.add_config(argparser)
ClassificationD.add_config(argparser)
args, _ = argparser.parse_known_args()
args.run_id = datetime.datetime.now().strftime("%Y_%m_%d_%H_%M_%S")
root_dir = os.path.dirname(os.path.realpath(__file__))
# only use generated run_path if none provided by user
if args.run_path is None:
args.run_path = os.path.join(root_dir, args.run_dir, args.run_id)
if not os.path.exists(args.run_path):
os.makedirs(args.run_path)
global outputManager
outputManager = OutputManager(args.run_path)
outputManager.say(args)
outputManager.say("\nRun ID: {}\nRun Path: {}\n\n".format(
args.run_id, args.run_path))
train_corpus_path = os.path.dirname(args.train) + "/corpus.tsv.gz"
cross_train_corpus_path = os.path.dirname(
args.cross_train) + "/corpus.tsv.gz"
train_corpus = Corpus([
tuple([train_corpus_path,
os.path.dirname(args.train)]),
tuple([cross_train_corpus_path,
os.path.dirname(args.cross_train)])
])
valid_corpus_path = os.path.dirname(args.eval) + "/corpus.tsv.gz"
valid_corpus = Corpus(
[tuple([valid_corpus_path,
os.path.dirname(args.eval)])])
outputManager.say("Corpus loaded.\n")
embs = load_embedding(args.embedding) if args.embedding else None
embedding_layer = EmbeddingLayer(args.n_d, ['<s>', '</s>'], embs)
model = model_class(embedding_layer, args)
if args.wasserstein:
domain_d = WassersteinD(model, args)
args.lambda_d = -args.lambda_d
else:
domain_d = ClassificationD(model, args)
if args.cuda:
model.cuda()
domain_d.cuda()
outputManager.say("\n{}\n\n".format(model))
outputManager.say("\n{}\n\n".format(domain_d))
needs_grad = lambda x: x.requires_grad
optimizer_encoder = optim.Adam(filter(needs_grad, model.parameters()),
lr=args.lr)
optimizer_domain_d = optim.Adam(filter(needs_grad, domain_d.parameters()),
lr=-args.lr2)
best_dev = 0
iter_cnt = 0
for epoch in range(args.max_epoch):
iter_cnt = train(iter_cnt, model, domain_d, train_corpus, args,
optimizer_encoder, optimizer_domain_d)
current_dev = evaluate(iter_cnt, args.eval + "/dev", model,
valid_corpus, args)
if current_dev > best_dev:
best_dev = current_dev
evaluate(iter_cnt, args.eval + "/test", model, valid_corpus, args,
False)
outputManager.say("\n")
if args.save_model:
torch.save(model.state_dict(), args.save_model)
torch.save(model, args.save_model + '-complete')
def main(args):
model_class = get_model_class(args.model)
model_class.add_config(argparser)
args = argparser.parse_args()
say(args)
args.run_id = random.randint(0, 10**9)
args.run_path = "{}/{}".format(args.run_dir, args.run_id)
#if not os.path.exists(args.run_dir):
# os.makedirs(args.run_dir)
#assert os.path.isdir(args.run_dir)
#assert not os.path.exists(args.run_path)
#os.makedirs(args.run_path)
say("\nRun ID: {}\nRun Path: {}\n\n".format(args.run_id, args.run_path))
train_corpus_path = os.path.dirname(args.train) + "/corpus.tsv.gz"
train_corpus = Corpus(
[tuple([train_corpus_path,
os.path.dirname(args.train)])])
valid_corpus_path = os.path.dirname(args.eval) + "/corpus.tsv.gz"
valid_corpus = Corpus(
[tuple([valid_corpus_path,
os.path.dirname(args.eval)])])
say("Corpus loaded.\n")
embs = load_embedding(args.embedding) if args.embedding else None
embedding_layer = EmbeddingLayer(args.n_d, ['<s>', '</s>'], embs)
model = model_class(embedding_layer, args)
if args.cuda:
model.cuda()
say("\n{}\n\n".format(model))
print model.state_dict().keys()
needs_grad = lambda x: x.requires_grad
optimizer = optim.Adam(filter(needs_grad, model.parameters()), lr=args.lr)
if args.load_model:
print "Loading pretrained model"
model.load_state_dict(torch.load(args.load_model))
else:
print "Training will begin from scratch"
best_dev = 0
iter_cnt = 0
current_dev = evaluate(iter_cnt, args.eval + "/dev", model, valid_corpus,
args)
evaluate(iter_cnt, args.eval + "/test", model, valid_corpus, args, False)
for epoch in range(args.max_epoch):
iter_cnt = train(iter_cnt, model, train_corpus, args, optimizer)
current_dev = evaluate(iter_cnt, args.eval + "/dev", model,
valid_corpus, args)
if current_dev > best_dev:
best_dev = current_dev
evaluate(iter_cnt, args.eval + "/test", model, valid_corpus, args,
False)
say("\n")
if args.save_model:
torch.save(model.state_dict(), args.save_model)
def main(args):
model_class = get_model_class(args.model)
model_class.add_config(argparser)
ClassificationD.add_config(argparser)
args, _ = argparser.parse_known_args()
say(args)
args.run_id = random.randint(0, 10**9)
args.run_path = "{}/{}".format(args.run_dir, args.run_id)
#if not os.path.exists(args.run_dir):
# os.makedirs(args.run_dir)
#assert os.path.isdir(args.run_dir)
#assert not os.path.exists(args.run_path)
#os.makedirs(args.run_path)
say("\nRun ID: {}\nRun Path: {}\n\n".format(args.run_id, args.run_path))
train_corpus_path = os.path.dirname(args.train) + "/corpus.tsv.gz"
cross_train_corpus_path = os.path.dirname(
args.cross_train) + "/corpus.tsv.gz"
train_corpus = Corpus([
tuple([train_corpus_path,
os.path.dirname(args.train)]),
tuple([cross_train_corpus_path,
os.path.dirname(args.cross_train)])
])
valid_corpus_path = os.path.dirname(args.eval) + "/corpus.tsv.gz"
valid_corpus = Corpus(
[tuple([valid_corpus_path,
os.path.dirname(args.eval)])])
say("Corpus loaded.\n")
embs = load_embedding(args.embedding) if args.embedding else None
embedding_layer = EmbeddingLayer(args.n_d, ['<s>', '</s>'], embs)
model = model_class(embedding_layer, args)
if args.wasserstein:
domain_d = WassersteinD(model, args)
args.lambda_d = -args.lambda_d
else:
domain_d = ClassificationD(model, args)
if args.cuda:
model.cuda()
domain_d.cuda()
say("\n{}\n\n".format(model))
say("\n{}\n\n".format(domain_d))
needs_grad = lambda x: x.requires_grad
optimizer_encoder = optim.Adam(filter(needs_grad, model.parameters()),
lr=args.lr)
optimizer_domain_d = optim.Adam(filter(needs_grad, domain_d.parameters()),
lr=-args.lr2)
best_dev = 0
iter_cnt = 0
for epoch in range(args.max_epoch):
iter_cnt = train(iter_cnt, model, domain_d, train_corpus, args,
optimizer_encoder, optimizer_domain_d)
current_dev = evaluate(iter_cnt, args.eval + "/dev", model,
valid_corpus, args)
if current_dev > best_dev:
best_dev = current_dev
evaluate(iter_cnt, args.eval + "/test", model, valid_corpus, args,
False)
say("\n")
if args.save_model:
torch.save(model.state_dict(), args.save_model)