def main(config):
prepare_dirs_loggers(config, os.path.basename(__file__))
corpus_client = corpora.NormMultiWozCorpus(config)
dial_corpus = corpus_client.get_corpus()
train_dial, valid_dial, test_dial = dial_corpus
sample_shape = config.batch_size, config.state_noise_dim, config.action_noise_dim
# evaluator = evaluators.BleuEvaluator("os.path.basename(__file__)")
evaluator = MultiWozEvaluator('SysWoz')
# create data loader that feed the deep models
train_feed = data_loaders.BeliefDbDataLoaders("Train", train_dial, config)
valid_feed = data_loaders.BeliefDbDataLoaders("Valid", valid_dial, config)
test_feed = data_loaders.BeliefDbDataLoaders("Test", test_dial, config)
model = GanRnnAgent(corpus_client, config)
load_context_encoder(
model, os.path.join(config.log_dir, config.encoder_sess, "model_lirl"))
if config.forward_only:
test_file = os.path.join(
config.log_dir, config.load_sess,
"{}-test-{}.txt".format(get_time(), config.gen_type))
dump_file = os.path.join(config.log_dir, config.load_sess,
"{}-z.pkl".format(get_time()))
model_file = os.path.join(config.log_dir, config.load_sess, "model")
else:
test_file = os.path.join(
config.session_dir,
"{}-test-{}.txt".format(get_time(), config.gen_type))
dump_file = os.path.join(config.session_dir,
"{}-z.pkl".format(get_time()))
model_file = os.path.join(config.session_dir, "model")
if config.use_gpu:
model.cuda()
print("Evaluate initial model on Validate set")
engine.disc_validate(model, valid_feed, config, sample_shape)
print("Start training")
if config.forward_only is False:
try:
engine.gan_train(model, train_feed, valid_feed, test_feed, config,
evaluator)
except KeyboardInterrupt:
print("Training stopped by keyboard.")
print("Trainig Done! Start Testing")
model.load_state_dict(torch.load(model_file))
engine.disc_validate(model, valid_feed, config, sample_shape)
engine.disc_validate(model, test_feed, config, sample_shape)
# dialog_utils.generate_with_adv(model, test_feed, config, None, num_batch=None)
# selected_clusters, index_cluster_id_train = utt_utils.latent_cluster(model, train_feed, config, num_batch=None)
# _, index_cluster_id_test = utt_utils.latent_cluster(model, test_feed, config, num_batch=None)
# _, index_cluster_id_valid = utt_utils.latent_cluster(model, valid_feed, config, num_batch=None)
# selected_outs = dialog_utils.selective_generate(model, test_feed, config, selected_clusters)
# print(len(selected_outs))
'''
def main(config):
prepare_dirs_loggers(config, os.path.basename(__file__))
corpus_client = corpora.DailyDialogCorpus(config)
dial_corpus = corpus_client.get_corpus()
train_dial, valid_dial, test_dial = dial_corpus['train'],\
dial_corpus['valid'],\
dial_corpus['test']
evaluator = evaluators.BleuEvaluator("CornellMovie")
# create data loader that feed the deep models
train_feed = data_loaders.DailyDialogLoader("Train", train_dial, config)
valid_feed = data_loaders.DailyDialogLoader("Valid", valid_dial, config)
test_feed = data_loaders.DailyDialogLoader("Test", test_dial, config)
model = sent_models.DiVAE(corpus_client, config)
if config.forward_only:
test_file = os.path.join(config.log_dir, config.load_sess,
"{}-test-{}.txt".format(get_time(), config.gen_type))
dump_file = os.path.join(config.log_dir, config.load_sess,
"{}-z.pkl".format(get_time()))
model_file = os.path.join(config.log_dir, config.load_sess, "model")
else:
test_file = os.path.join(config.session_dir,
"{}-test-{}.txt".format(get_time(), config.gen_type))
dump_file = os.path.join(config.session_dir, "{}-z.pkl".format(get_time()))
model_file = os.path.join(config.session_dir, "model")
if config.use_gpu:
model.cuda()
if config.forward_only is False:
try:
engine.train(model, train_feed, valid_feed,
test_feed, config, evaluator, gen=utt_utils.generate)
except KeyboardInterrupt:
print("Training stopped by keyboard.")
config.batch_size = 50
model.load_state_dict(torch.load(model_file))
engine.validate(model, test_feed, config)
utt_utils.sweep(model, test_feed, config, num_batch=50)
with open(os.path.join(dump_file), "wb") as f:
print("Dumping test to {}".format(dump_file))
utt_utils.dump_latent(model, test_feed, config, f, num_batch=None)
with open(os.path.join(test_file), "wb") as f:
print("Saving test to {}".format(test_file))
utt_utils.generate(model, test_feed, config, evaluator, num_batch=None, dest_f=f)
def main(config):
corpus_client = getattr(corpora, config.corpus_client)(config)
corpus_client.vocab, corpus_client.rev_vocab, corpus_client.unk_id = load_vocab(
config.vocab)
prepare_dirs_loggers(config, os.path.basename(__file__))
dial_corpus = corpus_client.get_corpus()
train_dial, valid_dial, test_dial = (dial_corpus['train'],
dial_corpus['valid'],
dial_corpus['test'])
evaluator = evaluators.BleuEvaluator("CornellMovie")
# create data loader that feed the deep models
train_feed = data_loaders.SMDDialogSkipLoader("Train", train_dial, config)
valid_feed = data_loaders.SMDDialogSkipLoader("Valid", valid_dial, config)
test_feed = data_loaders.SMDDialogSkipLoader("Test", test_dial, config)
model = dialog_models.VAE(corpus_client, config)
if config.forward_only:
test_file = os.path.join(
config.log_dir, config.load_sess,
"{}-test-{}.txt".format(get_time(), config.gen_type))
dump_file = os.path.join(config.log_dir, config.load_sess,
"{}-z.pkl".format(get_time()))
model_file = os.path.join(config.log_dir, config.load_sess, "model")
else:
test_file = os.path.join(
config.session_dir,
"{}-test-{}.txt".format(get_time(), config.gen_type))
dump_file = os.path.join(config.session_dir,
"{}-z.pkl".format(get_time()))
model_file = os.path.join(config.session_dir, "model")
if config.use_gpu:
model.cuda()
if config.forward_only is False:
try:
engine.train(model,
train_feed,
valid_feed,
test_feed,
config,
evaluator,
gen=dialog_utils.generate_vae)
except KeyboardInterrupt:
print("Training stopped by keyboard.")
def main(config):
prepare_dirs_loggers(config, os.path.basename(__file__))
manualSeed=config.seed
random.seed(manualSeed)
torch.manual_seed(manualSeed)
np.random.seed(manualSeed)
sample_shape = config.batch_size, config.state_noise_dim, config.action_noise_dim
# evaluator = evaluators.BleuEvaluator(os.path.basename(__file__))
evaluator = False
train_feed = WoZGanDataLoaders("train", config)
valid_feed = WoZGanDataLoaders("val", config)
test_feed = WoZGanDataLoaders("test", config)
# action2name = load_action2name(config)
action2name = None
corpus_client = None
# model = GanAgent_AutoEncoder(corpus_client, config, action2name)
# model = GanAgent_AutoEncoder_Encode(corpus_client, config, action2name)
# model = GanAgent_AutoEncoder_State(corpus_client, config, action2name)
if config.gan_type=='wgan':
model = WGanAgent_VAE_State(corpus_client, config, action2name)
else:
model = GanAgent_VAE_State(corpus_client, config, action2name)
logger.info(summary(model, show_weights=False))
model.discriminator.apply(weights_init)
model.generator.apply(weights_init)
model.vae.apply(weights_init)
if config.forward_only:
test_file = os.path.join(config.log_dir, config.load_sess,
"{}-test-{}.txt".format(get_time(), config.gen_type))
dump_file = os.path.join(config.log_dir, config.load_sess,
"{}-z.pkl".format(get_time()))
model_file = os.path.join(config.log_dir, config.load_sess, "model")
else:
test_file = os.path.join(config.session_dir,
"{}-test-{}.txt".format(get_time(), config.gen_type))
dump_file = os.path.join(config.session_dir, "{}-z.pkl".format(get_time()))
model_file = os.path.join(config.session_dir, "model")
vocab_file = os.path.join(config.session_dir, "vocab.json")
if config.use_gpu:
model.cuda()
pred_list = []
generator_samples = []
print("Evaluate initial model on Validate set")
model.eval()
# policy_validate_for_human(model,valid_feed, config, sample_shape)
disc_validate(model, valid_feed, config, sample_shape)
_, sample_batch = gen_validate(model,valid_feed, config, sample_shape, -1)
generator_samples.append([-1, sample_batch])
machine_data, human_data = build_fake_data(model, valid_feed, config, sample_shape)
model.train()
print("Start VAE training")
# # this is for the training of VAE. If you already have a pretrained model, you can skip this step.
# if config.forward_only is False:
# try:
# engine.vae_train(model, train_feed, valid_feed, test_feed, config)
# except KeyboardInterrupt:
# print("Training stopped by keyboard.")
# print("AutoEncoder Training Done ! ")
# load_model_vae(model, config)
# this is a pretrained vae model, you can load it to the current model. TODO: move path todata_args
path='./logs/2019-09-06T10:50:18.034181-mwoz_gan_vae.py'
load_model_vae(model, path)
print("Start GAN training")
if config.forward_only is False:
try:
engine.gan_train(model, machine_data, train_feed, valid_feed, test_feed, config, evaluator, pred_list, generator_samples)
except KeyboardInterrupt:
print("Training stopped by keyboard.")
print("Reward Model Training Done ! ")
print("Saved path: {}".format(model_file))
def main(config):
corpus_client = getattr(corpora, config.corpus_client)(config)
corpus_client.vocab, corpus_client.rev_vocab, corpus_client.unk_id = load_vocab(
config.vocab)
prepare_dirs_loggers(config, os.path.basename(__file__))
dial_corpus = corpus_client.get_corpus()
train_dial, valid_dial, test_dial = (dial_corpus['train'],
dial_corpus['valid'],
dial_corpus['test'])
evaluator = evaluators.BleuEvaluator("CornellMovie")
# create data loader that feed the deep models
train_feed = data_loaders.SMDDialogSkipLoader("Train", train_dial, config)
valid_feed = data_loaders.SMDDialogSkipLoader("Valid", valid_dial, config)
test_feed = data_loaders.SMDDialogSkipLoader("Test", test_dial, config)
model = dialog_models.StED(corpus_client, config)
if config.forward_only:
test_file = os.path.join(
config.log_dir, config.load_sess,
"{}-test-{}.txt".format(get_time(), config.gen_type))
dump_file = os.path.join(config.log_dir, config.load_sess,
"{}-z.pkl".format(get_time()))
model_file = os.path.join(config.log_dir, config.load_sess, "model")
else:
test_file = os.path.join(
config.session_dir,
"{}-test-{}.txt".format(get_time(), config.gen_type))
dump_file = os.path.join(config.session_dir,
"{}-z.pkl".format(get_time()))
model_file = os.path.join(config.session_dir, "model")
if config.use_gpu:
model.cuda()
if not config.forward_only:
try:
engine.train(model,
train_feed,
valid_feed,
test_feed,
config,
evaluator,
gen=dialog_utils.generate_with_adv)
except KeyboardInterrupt:
print("Training stopped by keyboard.")
config.batch_size = 10
model.load_state_dict(torch.load(model_file))
engine.validate(model, valid_feed, config)
engine.validate(model, test_feed, config)
dialog_utils.generate_with_adv(model, test_feed, config, None, num_batch=0)
selected_clusters = utt_utils.latent_cluster(model,
train_feed,
config,
num_batch=None)
selected_outs = dialog_utils.selective_generate(model, test_feed, config,
selected_clusters)
print(len(selected_outs))
with open(os.path.join(dump_file + '.json'), 'wb') as f:
json.dump(selected_clusters, f, indent=2)
with open(os.path.join(dump_file + '.out.json'), 'wb') as f:
json.dump(selected_outs, f, indent=2)
with open(os.path.join(dump_file), "wb") as f:
print("Dumping test to {}".format(dump_file))
dialog_utils.dump_latent(model, test_feed, config, f, num_batch=None)
with open(os.path.join(test_file), "wb") as f:
print("Saving test to {}".format(test_file))
dialog_utils.gen_with_cond(model,
test_feed,
config,
num_batch=None,
dest_f=f)
with open(os.path.join(test_file + '.txt'), "wb") as f:
print("Saving test to {}".format(test_file))
dialog_utils.generate(model,
test_feed,
config,
evaluator,
num_batch=None,
dest_f=f)
def main(config):
prepare_dirs_loggers(config, os.path.basename(__file__))
corpus_client = corpora.NormMultiWozCorpus(config)
dial_corpus = corpus_client.get_corpus()
train_dial, valid_dial, test_dial = dial_corpus
# evaluator = evaluators.BleuEvaluator("os.path.basename(__file__)")
evaluator = MultiWozEvaluator('SysWoz')
# create data loader that feed the deep models
train_feed = data_loaders.BeliefDbDataLoaders("Train", train_dial, config)
valid_feed = data_loaders.BeliefDbDataLoaders("Valid", valid_dial, config)
test_feed = data_loaders.BeliefDbDataLoaders("Test", test_dial, config)
model = dialog_models.AeED(corpus_client, config)
if config.forward_only:
test_file = os.path.join(
config.log_dir, config.load_sess,
"{}-test-{}.txt".format(get_time(), config.gen_type))
dump_file = os.path.join(config.log_dir, config.load_sess,
"{}-z.pkl".format(get_time()))
model_file = os.path.join(config.log_dir, config.load_sess, "model")
else:
test_file = os.path.join(
config.session_dir,
"{}-test-{}.txt".format(get_time(), config.gen_type))
dump_file = os.path.join(config.session_dir,
"{}-z.pkl".format(get_time()))
model_file = os.path.join(config.session_dir, "model")
if config.use_gpu:
model.cuda()
if config.forward_only is False:
try:
engine.train(model,
train_feed,
valid_feed,
test_feed,
config,
evaluator,
gen=dialog_utils.generate_with_adv)
except KeyboardInterrupt:
print("Training stopped by keyboard.")
config.batch_size = 10
model.load_state_dict(torch.load(model_file))
logger.info("Test Bleu:")
dialog_utils.generate(model, test_feed, config, evaluator,
test_feed.num_batch, False)
engine.validate(model, valid_feed, config)
engine.validate(model, test_feed, config)
dialog_utils.generate_with_adv(model,
test_feed,
config,
None,
num_batch=None)
cluster_name_id = None
action_count = 0
selected_clusters, index_cluster_id_train, cluster_name_id, action_count = utt_utils.latent_cluster(
model, train_feed, config, None, 0, num_batch=None)
_, index_cluster_id_test, cluster_name_id, action_count = utt_utils.latent_cluster(
model,
test_feed,
config,
cluster_name_id,
action_count,
num_batch=None)
_, index_cluster_id_valid, cluster_name_id, action_count = utt_utils.latent_cluster(
model,
valid_feed,
config,
cluster_name_id,
action_count,
num_batch=None)
selected_outs = dialog_utils.selective_generate(model, test_feed, config,
selected_clusters)
print(len(selected_outs))
with open(os.path.join(dump_file + '.json'), 'wb') as f:
json.dump(selected_clusters, f, indent=2)
with open(os.path.join(dump_file + '.cluster_id.json.Train'), 'wb') as f:
json.dump(index_cluster_id_train, f, indent=2)
with open(os.path.join(dump_file + '.cluster_id.json.Test'), 'wb') as f:
json.dump(index_cluster_id_test, f, indent=2)
with open(os.path.join(dump_file + '.cluster_id.json.Valid'), 'wb') as f:
json.dump(index_cluster_id_valid, f, indent=2)
with open(os.path.join(dump_file + '.out.json'), 'wb') as f:
json.dump(selected_outs, f, indent=2)
with open(os.path.join(dump_file), "wb") as f:
print("Dumping test to {}".format(dump_file))
dialog_utils.dump_latent(model, test_feed, config, f, num_batch=None)
with open(os.path.join(test_file), "wb") as f:
print("Saving test to {}".format(test_file))
dialog_utils.gen_with_cond(model,
test_feed,
config,
num_batch=None,
dest_f=f)
with open(os.path.join(test_file + '.txt'), "wb") as f:
print("Saving test to {}".format(test_file))
dialog_utils.generate(model,
test_feed,
config,
evaluator,
num_batch=None,
dest_f=f)
print("All done. Have a nice day")
def main(config):
prepare_dirs_loggers(config, os.path.basename(__file__))
manualSeed=config.seed
random.seed(manualSeed)
torch.manual_seed(manualSeed)
np.random.seed(manualSeed)
sample_shape = config.batch_size, config.state_noise_dim, config.action_noise_dim
evaluator = evaluators.BleuEvaluator(os.path.basename(__file__))
train_feed = WoZGanDataLoaders("train", config)
valid_feed = WoZGanDataLoaders("val", config)
test_feed = WoZGanDataLoaders("test", config)
# action2name = load_action2name(config)
action2name = None
corpus_client = None
if config.gan_type=='gan' and config.input_type=='sat':
model = GanAgent_SAT_WoZ(corpus_client, config, action2name)
else:
raise ValueError("No such GAN types: {}".format(config.gan_type))
logger.info(summary(model, show_weights=False))
model.discriminator.apply(weights_init)
model.generator.apply(weights_init)
if config.state_type=='rnn':
load_context_encoder(model, os.path.join(config.log_dir, config.encoder_sess, "model_lirl"))
if config.forward_only:
test_file = os.path.join(config.log_dir, config.load_sess,
"{}-test-{}.txt".format(get_time(), config.gen_type))
dump_file = os.path.join(config.log_dir, config.load_sess,
"{}-z.pkl".format(get_time()))
model_file = os.path.join(config.log_dir, config.load_sess, "model")
else:
test_file = os.path.join(config.session_dir,
"{}-test-{}.txt".format(get_time(), config.gen_type))
dump_file = os.path.join(config.session_dir, "{}-z.pkl".format(get_time()))
model_file = os.path.join(config.session_dir, "model")
vocab_file = os.path.join(config.session_dir, "vocab.json")
if config.use_gpu:
model.cuda()
pred_list = []
generator_samples = []
print("Evaluate initial model on Validate set")
model.eval()
# policy_validate_for_human(model,valid_feed, config, sample_shape)
disc_validate(model, valid_feed, config, sample_shape)
_, sample_batch = gen_validate(model,valid_feed, config, sample_shape, -1)
generator_samples.append([-1, sample_batch])
machine_data, human_data = build_fake_data(model, valid_feed, config, sample_shape)
model.train()
print("Start training")
if config.forward_only is False:
try:
engine.gan_train(model, machine_data, train_feed, valid_feed, test_feed, config, evaluator, pred_list, generator_samples)
except KeyboardInterrupt:
print("Training stopped by keyboard.")
# save_data_for_tsne(human_data, machine_data, generator_samples, pred_list, config)
print("Training Done ! ")
'''
model.load_state_dict(torch.load(model_file))
print("Evaluate final model on Validate set")
model.eval()
policy_validate_for_human(model,valid_feed, config, sample_shape)
disc_validate(model, valid_feed, config, sample_shape)
gen_validate(model,valid_feed, config, sample_shape)
print("Evaluate final model on Test set")
policy_validate_for_human(model,test_feed, config, sample_shape)
disc_validate(model, test_feed, config, sample_shape)
gen_validate(model,test_feed, config, sample_shape)
'''
# dialog_utils.generate_with_adv(model, test_feed, config, None, num_batch=None)
# selected_clusters, index_cluster_id_train = utt_utils.latent_cluster(model, train_feed, config, num_batch=None)
# _, index_cluster_id_test = utt_utils.latent_cluster(model, test_feed, config, num_batch=None)
# _, index_cluster_id_valid = utt_utils.latent_cluster(model, valid_feed, config, num_batch=None)
# selected_outs = dialog_utils.selective_generate(model, test_feed, config, selected_clusters)
# print(len(selected_outs))
'''
def main(config):
prepare_dirs_loggers(config, os.path.basename(__file__))
manualSeed = config.seed
random.seed(manualSeed)
torch.manual_seed(manualSeed)
np.random.seed(manualSeed)
sample_shape = config.batch_size, config.state_noise_dim, config.action_noise_dim
evaluator = evaluators.BleuEvaluator(os.path.basename(__file__))
train_feed = WoZGanDataLoaders_StateActionEmbed("train", config)
valid_feed = WoZGanDataLoaders_StateActionEmbed("val", config)
test_feed = WoZGanDataLoaders_StateActionEmbed("test", config)
# action2name = load_action2name(config)
action2name = None
corpus_client = None
# model = GanAgent_VAE_StateActioneEmbed(corpus_client, config, action2name)
model = GanAgent_StateVaeActionSeg(corpus_client, config, action2name)
logger.info(summary(model, show_weights=False))
model.discriminator.apply(weights_init)
model.generator.apply(weights_init)
model.vae.apply(weights_init)
if config.forward_only:
test_file = os.path.join(
config.log_dir, config.load_sess,
"{}-test-{}.txt".format(get_time(), config.gen_type))
dump_file = os.path.join(config.log_dir, config.load_sess,
"{}-z.pkl".format(get_time()))
model_file = os.path.join(config.log_dir, config.load_sess, "model")
else:
test_file = os.path.join(
config.session_dir,
"{}-test-{}.txt".format(get_time(), config.gen_type))
dump_file = os.path.join(config.session_dir,
"{}-z.pkl".format(get_time()))
model_file = os.path.join(config.session_dir, "model")
vocab_file = os.path.join(config.session_dir, "vocab.json")
if config.use_gpu:
model.cuda()
pred_list = []
generator_samples = []
print("Evaluate initial model on Validate set")
model.eval()
# policy_validate_for_human(model,valid_feed, config, sample_shape)
disc_validate(model, valid_feed, config, sample_shape)
_, sample_batch = gen_validate(model, valid_feed, config, sample_shape, -1)
generator_samples.append([-1, sample_batch])
machine_data, human_data = build_fake_data(model, valid_feed, config,
sample_shape)
model.train()
print("Start training")
if config.forward_only is False:
try:
engine.vae_train(model, train_feed, valid_feed, test_feed, config)
except KeyboardInterrupt:
print("Training stopped by keyboard.")
print("AutoEncoder Training Done ! ")
load_model_vae(model, config)
# path='logs/2019-09-18T12:20:26.063708-mwoz_gan_vae_StateActionEmbed.py' # this is embed version
# path='logs/2019-09-18T12:24:45.517636-mwoz_gan_vae_StateActionEmbed.py' # this is embed_merged version
# path='logs/2019-09-18T17:21:35.420069-mwoz_gan_vae_StateActionEmbed.py' # this is state_vae action_seg version, without hotel domain
# load_model_vae(model, path)
if config.forward_only is False:
try:
engine.gan_train(model, machine_data, train_feed, valid_feed,
test_feed, config, evaluator, pred_list,
generator_samples)
except KeyboardInterrupt:
print("Training stopped by keyboard.")
print("Reward Model Training Done ! ")
print("Saved path: {}".format(model_file))
