def main(num):
# Generate configuration files depending on experiment being run
utils.generate_config_files("atomic", num)
# Loads the correct configuration file
config_file = "config/atomic/config_{}.json".format(num)
print(config_file)
# Read config file to option
config = cfg.read_config(cfg.load_config(config_file))
opt, meta = cfg.get_parameters(config)
# Set the random seeds
torch.manual_seed(opt.train.static.seed)
random.seed(opt.train.static.seed)
if config.gpu_mode:
torch.cuda.manual_seed_all(opt.train.static.seed)
# Where to find the data
splits = ["train", "dev", "test"]
opt.train.dynamic.epoch = 0
print("Loading Data")
categories = opt.data.categories
path = "data/atomic/processed/{}/{}.pickle".format(
opt.exp, utils.make_name_string(opt.data))
data_loader = data.make_data_loader(opt, categories)
loaded = data_loader.load_data(path)
print(data_loader.sequences["train"]["total"].size(0))
data_loader.opt = opt
data_loader.batch_size = opt.train.dynamic.bs
print("Done.")
# Initialize text_encoder
text_encoder = TextEncoder(config.encoder_path, config.bpe_path)
special = [data.start_token, data.end_token]
special += ["<{}>".format(cat) for cat in categories]
special += [data.blank_token]
text_encoder.encoder = data_loader.vocab_encoder
text_encoder.decoder = data_loader.vocab_decoder
opt.data.maxe1 = data_loader.max_event
opt.data.maxe2 = data_loader.max_effect
opt.data.maxr = data.atomic_data.num_delimiter_tokens["category"]
n_special = len(special)
n_ctx = opt.data.maxe1 + opt.data.maxe2
n_vocab = len(text_encoder.encoder) + n_ctx
print(data_loader.__dict__.keys())
opt.net.vSize = n_vocab
print("Building Model")
model = models.make_model(opt,
n_vocab,
n_ctx,
n_special,
load=(opt.net.init == "pt"))
print("Done.")
print("Files will be logged at: {}".format(
utils.make_name(opt, prefix="results/losses/", is_dir=True,
eval_=True)))
data_loader.reset_offsets("train")
# Get number of examples
data.set_max_sizes(data_loader)
if config.gpu_mode:
print("Pushing to GPU: {}".format(config.gpu_index))
cfg.device = config.gpu_index
cfg.do_gpu = True
torch.cuda.set_device(cfg.device)
if config.multigpu:
model = models.multi_gpu(model, config.gpu_indices).cuda()
else:
model.cuda(cfg.device)
print("Done.")
print("Training")
optimizer = OpenAIAdam(model.parameters(),
lr=opt.train.dynamic.lr,
schedule=opt.train.static.lrsched,
warmup=opt.train.static.lrwarm,
t_total=meta.iterations,
b1=opt.train.static.b1,
b2=opt.train.static.b2,
e=opt.train.static.e,
l2=opt.train.static.l2,
vector_l2=opt.train.static.vl2,
max_grad_norm=opt.train.static.clip)
scorers = ["bleu", "rouge", "cider"]
trainer = train.make_trainer(opt, meta, data_loader, model, optimizer)
trainer.set_evaluator(opt, model, data_loader)
trainer.run()
parser = argparse.ArgumentParser()
parser.add_argument("--generation_set_size", type=str, default='full', choices=["full", "human"])
parser.add_argument("--device", type=int, default=0)
parser.add_argument("--split", type=str, default="dev")
parser.add_argument("--beam", type=int, default=10)
parser.add_argument("--seed", type=int, default=42)
parser.add_argument("--experiment_num", type=str, default="0")
parser.add_argument("--model_name", type=str, default="models/conceptnet-generation/iteration-500-100000/transformer/rel_language-trainsize_100-devversion_12-maxe1_10-maxe2_15/model_transformer-nL_12-nH_12-hSize_768-edpt_0.1-adpt_0.1-rdpt_0.1-odpt_0.1-pt_gpt-afn_gelu-npos_1-demb_F-init_pt-vSize_40545/exp_generation-seed_123-es_0-l2_0.01-vl2_T-lrsched_warmup_linear-lrwarm_0.002-clip_1-loss_nll-b2_0.999-b1_0.9-e_1e-08/bs_1-trick_0-smax_40-sample_beam-numseq_1-gs_full-es_full-categories_None/1e-05_adam_64_13500.pickle")
parser.add_argument("--gen_len", type=int, default=100)
args = parser.parse_args()
split = args.split
# Generate configuration files depending on experiment being run
utils.generate_config_files("conceptnet", args.experiment_num, eval_mode=True)
# Loads the correct configuration file
config_file = "config/conceptnet/config_{}.json".format(args.experiment_num)
# Read config file to option
config = cfg.read_config(cfg.load_config(config_file))
cfg.device = args.device
eval_opt = cfg.get_eval_parameters(config)
model_stuff = data.load_checkpoint(args.model_name)
opt = model_stuff["opt"]
opt.eval.update(eval_opt)
# Set the random seeds
parser.add_argument("--k", type=int, default=10)
parser.add_argument("--seed", type=int, default=42)
parser.add_argument("--experiment_num", type=str, default="0")
parser.add_argument(
"--model_name",
type=str,
default=
"models/atomic-generation/iteration-500-50000/transformer/categories_oEffect#oReact#oWant#xAttr#xEffect#xIntent#xNeed#xReact#xWant-maxe1_17-maxe2_35-maxr_1/model_transformer-nL_12-nH_12-hSize_768-edpt_0.1-adpt_0.1-rdpt_0.1-odpt_0.1-pt_gpt-afn_gelu-init_pt-vSize_40542/exp_generation-seed_123-l2_0.01-vl2_T-lrsched_warmup_linear-lrwarm_0.002-clip_1-loss_nll-b2_0.999-b1_0.9-e_1e-08/bs_1-smax_40-sample_greedy-numseq_1-gs_1000-es_1000-categories_oEffect#oReact#oWant#xAttr#xEffect#xIntent#xNeed#xReact#xWant/6.25e-05_adam_64_22000.pickle"
)
parser.add_argument("--gen_len", type=int, default=100)
args = parser.parse_args()
split = args.split
# Generate configuration files depending on experiment being run
utils.generate_config_files("atomic", args.experiment_num, eval_mode=True)
# Loads the correct configuration file
config_file = "config/atomic/config_{}.json".format(args.experiment_num)
# Read config file to option
config = cfg.read_config(cfg.load_config(config_file))
cfg.device = config.gpu_index
eval_opt = cfg.get_eval_parameters(config)
model_stuff = data.load_checkpoint(args.model_name)
opt = model_stuff["opt"]
opt.eval.update(eval_opt)
opt.train.dynamic.epoch = 0
def main(num):
# Generate configuration files depending on experiment being run
utils.generate_config_files("conceptnet", num)
# Loads the correct configuration file
config_file = "config/conceptnet/config_{}.json".format(num)
print(config_file)
# Read config file to option
config = cfg.read_config(cfg.load_config(config_file))
opt, meta = cfg.get_parameters(config)
# config.gpu_mode = torch.cuda.is_available()
# Set the random seeds
torch.manual_seed(opt.train.static.seed)
random.seed(opt.train.static.seed)
if config.gpu_mode:
torch.cuda.manual_seed_all(opt.train.static.seed)
# Load the data
splits = ["train", "dev", "test"]
opt.train.dynamic.epoch = 0
print("Loading Data")
# Initialize path to pre-set data loader
path = "data/conceptnet/processed/{}/{}.pickle".format(
opt.exp, utils.make_name_string(opt.data))
# Make data loader
data_loader = data.make_data_loader(opt)
loaded = data_loader.load_data(path)
print(data_loader.sequences["train"]["total"].size(0))
data_loader.opt = opt
data_loader.batch_size = opt.train.dynamic.bs
print("Done.")
text_encoder = TextEncoder(config.encoder_path, config.bpe_path)
categories = data.conceptnet_data.conceptnet_relations
special = [data.start_token, data.end_token]
special += ["<{}>".format(cat) for cat in categories]
if loaded:
text_encoder.encoder = data_loader.vocab_encoder
text_encoder.decoder = data_loader.vocab_decoder
else:
for special_token in special:
text_encoder.decoder[len(encoder)] = special_token
text_encoder.encoder[special_token] = len(encoder)
data_loader.make_tensors(text_encoder, special)
# Set max size of different parts of relation
context_size_e1 = data_loader.max_e1
context_size_e2 = data_loader.max_e2
context_size_r = data_loader.max_r
opt.data.maxr = context_size_r
n_special = len(special)
n_ctx = context_size_e1 + context_size_r + context_size_e2
n_vocab = len(text_encoder.encoder) + n_ctx
print(data_loader.__dict__.keys())
opt.net.vSize = n_vocab
# Build Model
print("Building Model")
model = models.make_model(opt,
n_vocab,
n_ctx,
n_special,
load=(opt.net.init == "pt"))
print("Done.")
print("Files will be logged at: {}".format(
utils.make_name(opt, prefix="results/losses/", is_dir=True,
eval_=True)))
data_loader.reset_offsets("train", keys=["total"])
data.set_max_sizes(data_loader)
# Push to GPU
if config.gpu_mode:
print("Pushing to GPU: {}".format(config.gpu_index))
cfg.device = config.gpu_index
cfg.do_gpu = True
torch.cuda.set_device(cfg.device)
if config.multigpu:
model = models.multi_gpu(model, config.gpu_indices).cuda()
else:
model.cuda(cfg.device)
print("Done.")
print("Training")
optimizer = OpenAIAdam(model.parameters(),
lr=opt.train.dynamic.lr,
schedule=opt.train.static.lrsched,
warmup=opt.train.static.lrwarm,
t_total=meta.iterations,
b1=opt.train.static.b1,
b2=opt.train.static.b2,
e=opt.train.static.e,
l2=opt.train.static.l2,
vector_l2=opt.train.static.vl2,
max_grad_norm=opt.train.static.clip)
trainer = train.make_trainer(opt, meta, data_loader, model, optimizer)
print(data_loader.sequences["dev"]["total"].max())
trainer.set_generator(opt, model, data_loader)
trainer.set_evaluator(opt, model, data_loader)
trainer.run()