def step_one_test():
data_loader = DataLoader(args)
#Checkpoint.CHECKPOINT_DIR_NAME = "0120_0030"
Checkpoint.CHECKPOINT_DIR_NAME = args.checkpoint_dir_name
checkpoint_path = os.path.join("./experiment",
Checkpoint.CHECKPOINT_DIR_NAME, "best")
checkpoint = Checkpoint.load(checkpoint_path)
seq2seq = checkpoint.model
if args.cuda_use:
seq2seq = seq2seq.cuda()
seq2seq.eval()
evaluator = Evaluator(vocab_dict=data_loader.vocab_dict,
vocab_list=data_loader.vocab_list,
decode_classes_dict=data_loader.decode_classes_dict,
decode_classes_list=data_loader.decode_classes_list,
loss=NLLLoss(),
cuda_use=args.cuda_use)
name = args.run_flag
if name == 'test_23k':
test_temp_acc, test_ans_acc = evaluator.evaluate(
model=seq2seq,
data_loader=data_loader,
data_list=data_loader.math23k_test_list,
template_flag=True,
batch_size=64,
evaluate_type=0,
use_rule=False,
mode=args.mode,
post_flag=args.post_flag,
name_save=name)
print(test_temp_acc, test_ans_acc)
def gen_best_23_error():
data_loader = DataLoader()
Checkpoint.CHECKPOINT_DIR_NAME = args.checkpoint_dir_name
checkpoint_path = os.path.join("./experiment", Checkpoint.CHECKPOINT_DIR_NAME, 'best')
checkpoint = Checkpoint.load(checkpoint_path)
seq2seq = checkpoint.model
if args.cuda_use:
seq2seq = seq2seq.cuda()
seq2seq.eval()
emb_model = seq2seq.encoder.embedding
emb_np = emb_model.weight.cpu().data.numpy()
np.save("./data/rl_train_data/emb.npy", emb_np)
evaluator = Evaluator(vocab_dict = data_loader.vocab_dict,
vocab_list = data_loader.vocab_list,
decode_classes_dict = data_loader.decode_classes_dict,
decode_classes_list = data_loader.decode_classes_list,
loss = NLLLoss(),
cuda_use = args.cuda_use)
evaluator.gen_rl_data(model = seq2seq,
data_loader = data_loader,
data_list = data_loader.math23k_train_list,
template_flag = False,
batch_size = 16,
evaluate_type = 0,
use_rule = False,
mode = args.mode,
filename = args.load_name)
def step_three():
data_loader = DataLoader(args)
Checkpoint.CHECKPOINT_DIR_NAME = args.checkpoint_dir_name
checkpoint_path = os.path.join("./experiment",
Checkpoint.CHECKPOINT_DIR_NAME, "best")
checkpoint = Checkpoint.load(checkpoint_path)
seq2seq = checkpoint.model
if args.cuda_use:
seq2seq = seq2seq.cuda()
seq2seq.eval()
evaluator = Evaluator(vocab_dict=data_loader.vocab_dict,
vocab_list=data_loader.vocab_list,
decode_classes_dict=data_loader.decode_classes_dict,
decode_classes_list=data_loader.decode_classes_list,
loss=NLLLoss(),
cuda_use=args.cuda_use)
test_temp_acc, test_ans_acc = evaluator.evaluate(
model=seq2seq,
data_loader=data_loader,
data_list=data_loader.math57k_data_list,
template_flag=False,
batch_size=64,
evaluate_type=0,
use_rule=True,
mode=args.mode)
print(test_temp_acc, test_ans_acc)
def gen_math57k_error():
data_loader = DataLoader()
Checkpoint.CHECKPOINT_DIR_NAME = args.checkpoint_dir_name
checkpoint_path = os.path.join("./experiment", Checkpoint.CHECKPOINT_DIR_NAME, args.load_name)
checkpoint = Checkpoint.load(checkpoint_path)
seq2seq = checkpoint.model
if args.cuda_use:
seq2seq = seq2seq.cuda()
seq2seq.eval()
evaluator = Evaluator(vocab_dict = data_loader.vocab_dict,
vocab_list = data_loader.vocab_list,
decode_classes_dict = data_loader.decode_classes_dict,
decode_classes_list = data_loader.decode_classes_list,
loss = NLLLoss(),
cuda_use = args.cuda_use)
evaluator.gen_rl_data(model = seq2seq,
data_loader = data_loader,
data_list = data_loader.math57k_data_list,
template_flag = False,
batch_size = 16,
evaluate_type = 0,
use_rule = True,
mode = args.mode,
filename = args.load_name)
def test(args, test_dataset="test"):
seq2seq, data_loader = create_model(args)
resume_checkpoint = Checkpoint.load(model_only=True)
seq2seq.load_state_dict(resume_checkpoint.model)
if args.use_cuda:
seq2seq = seq2seq.cuda()
evaluator = Evaluator(
class_dict=data_loader.class_dict,
class_list=data_loader.class_list,
use_cuda=args.use_cuda
)
if test_dataset == "test":
test_dataset = data_loader.test_list
elif test_dataset == "train":
test_dataset = data_loader.train_list
seq2seq.eval()
with torch.no_grad():
test_temp_acc, test_ans_acc = evaluator.evaluate(
model=seq2seq,
data_loader=data_loader,
data_list=test_dataset,
template_flag=True,
template_len=False,
batch_size=1,
beam_width=args.beam,
test_log=args.test_log,
print_probability=True
)
logging.info(f"temp_acc: {test_temp_acc}, ans_acc: {test_ans_acc}")
return
def train(self, model, data_loader, batch_size, n_epoch, template_flag, \
resume=False, optimizer=None, mode=0, teacher_forcing_ratio=0, post_flag=False):
self.evaluator = Evaluator(
vocab_dict=self.vocab_dict,
vocab_list=self.vocab_list,
decode_classes_dict=self.decode_classes_dict,
decode_classes_list=self.decode_classes_list,
loss=NLLLoss(),
cuda_use=self.cuda_use)
if resume:
checkpoint_path = Checkpoint.get_certain_checkpoint(
"./experiment", "best")
resume_checkpoint = Checkpoint.load(checkpoint_path)
model = resume_checkpoint.model
self.optimizer = resume_checkpoint.optimizer
resume_optim = self.optimizer.optimizer
defaults = resume_optim.param_groups[0]
defaults.pop('params', None)
self.optimizer.optimizer = resume_optim.__class__(
model.parameters(), **defaults)
start_epoch = resume_checkpoint.epoch
start_step = resume_checkpoint.step
self.train_acc_list = resume_checkpoint.train_acc_list
self.test_acc_list = resume_checkpoint.test_acc_list
self.loss_list = resume_checkpoint.loss_list
else:
start_epoch = 1
start_step = 0
self.train_acc_list = []
self.test_acc_list = []
self.loss_list = []
model_opt = NoamOpt(
512, 1, 2000,
torch.optim.Adam(model.parameters(),
lr=0,
betas=(0.9, 0.98),
eps=1e-9))
if optimizer is None:
optimizer = Optimizer(optim.Adam(model.parameters()),
max_grad_norm=0)
self.optimizer = model_opt
self._train_epoches(data_loader=data_loader,
model=model,
batch_size=batch_size,
start_epoch=start_epoch,
start_step=start_step,
n_epoch=n_epoch,
mode=mode,
template_flag=template_flag,
teacher_forcing_ratio=teacher_forcing_ratio,
post_flag=post_flag)
def train(self,
model,
data_loader,
batch_size,
n_epoch,
resume=False,
optim_lr=1e-3,
optim_weight_decay=1e-5,
scheduler_step_size=60,
scheduler_gamma=0.6):
start_epoch = 1
start_step = 0
max_acc = 0
self.optimizer = optim.Adam(model.parameters(),
lr=optim_lr,
weight_decay=optim_weight_decay)
self.scheduler = optim.lr_scheduler.StepLR(
self.optimizer,
step_size=scheduler_step_size,
gamma=scheduler_gamma)
if resume:
resume_checkpoint = Checkpoint.load(model_only=False)
model.load_state_dict(resume_checkpoint.model)
resume_optimizer = resume_checkpoint.optimizer
resume_scheduler = resume_checkpoint.scheduler
if resume_optimizer is not None:
start_epoch = resume_checkpoint.epoch
start_step = resume_checkpoint.step
max_acc = resume_checkpoint.max_acc
self.optimizer.load_state_dict(resume_optimizer)
self.scheduler.load_state_dict(resume_scheduler)
self._train_epoches(data_loader=data_loader,
model=model,
batch_size=batch_size,
start_epoch=start_epoch,
start_step=start_step,
max_acc=max_acc,
n_epoch=n_epoch)
return
def step_one_test():
args = get_args()
print(args)
one_quest_test_list = read_data_json("./data/test.json")
print(one_quest_test_list)
#Checkpoint.CHECKPOINT_DIR_NAME = "0120_0030"
Checkpoint.CHECKPOINT_DIR_NAME = args.checkpoint_dir_name
checkpoint_path = os.path.join("./experiment",
Checkpoint.CHECKPOINT_DIR_NAME, "best")
print('-----', args.checkpoint_dir_name, checkpoint_path)
checkpoint = Checkpoint.load(checkpoint_path)
seq2seq = checkpoint.model
if args.cuda_use:
seq2seq = seq2seq.cuda()
data_loader = DataLoader(args)
seq2seq.eval()
evaluator = Evaluator(vocab_dict=data_loader.vocab_dict,
vocab_list=data_loader.vocab_list,
decode_classes_dict=data_loader.decode_classes_dict,
decode_classes_list=data_loader.decode_classes_list,
loss=NLLLoss(),
cuda_use=args.cuda_use)
name = args.run_flag
test_temp_acc, test_ans_acc = evaluator.evaluate(
model=seq2seq,
data_loader=data_loader,
data_list=one_quest_test_list,
template_flag=False, # todo: 这里改成了false
batch_size=64,
evaluate_type=0,
use_rule=False,
mode=args.mode,
post_flag=args.post_flag,
name_save=name)
print(test_temp_acc, test_ans_acc)