def test(**kwargs):
if 'dataset' not in kwargs:
opt = getattr(config, 'AmazonDigitalMusic_Config')()
else:
opt = getattr(config, kwargs['dataset'] + '_Config')()
opt.parse(kwargs)
assert(len(opt.pth_path) > 0)
random.seed(opt.seed)
np.random.seed(opt.seed)
torch.manual_seed(opt.seed)
if opt.use_gpu:
torch.cuda.manual_seed_all(opt.seed)
if len(opt.gpu_ids) == 0 and opt.use_gpu:
torch.cuda.set_device(opt.gpu_id)
model = Model(opt, getattr(models, opt.model))
if opt.use_gpu:
model.cuda()
if len(opt.gpu_ids) > 0:
model = nn.DataParallel(model, device_ids=opt.gpu_ids)
if model.net.num_fea != opt.num_fea:
raise ValueError(f"the num_fea of {opt.model} is error, please specific --num_fea={model.net.num_fea}")
model.load(opt.pth_path)
print(f"load model: {opt.pth_path}")
test_data = ReviewData(opt.data_root, mode="Test")
test_data_loader = DataLoader(test_data, batch_size=opt.batch_size, shuffle=False, collate_fn=collate_fn)
print(f"{now()}: test in the test datset")
predict_loss, test_mse, test_mae = predict(model, test_data_loader, opt)
def test(**kwargs):
if 'dataset' not in kwargs:
opt = getattr(config, 'Gourmet_Food_data_Config')()
else:
opt = getattr(config, kwargs['dataset'] + '_Config')()
opt.parse(kwargs)
logging.basicConfig(
filename=f"logs/{opt}.log",
filemode="w",
format="%(asctime)s %(name)s:%(levelname)s:%(message)s",
datefmt="%d-%m-%Y %H:%M:%S",
level=logging.DEBUG)
random.seed(opt.seed)
np.random.seed(opt.seed)
torch.manual_seed(opt.seed)
if opt.use_gpu:
torch.cuda.manual_seed_all(opt.seed)
if len(opt.gpu_ids) == 0 and opt.use_gpu:
torch.cuda.set_device(opt.gpu_id)
model = Model(opt, getattr(models, opt.model)).cuda()
print("load...")
model.load(
"./checkpoints/DPHP_Gourmet_Food_data_cfg-Gourmet_Food_data-poolatt-lr0.001-wd0.0005-drop0.1-id32-hidden100.pth"
)
test_data = ReviewData(opt.data_root, mode="Test")
test_data_loader = DataLoader(test_data,
batch_size=opt.batch_size,
shuffle=False,
collate_fn=collate_fn)
auc, corr, predict_loss = predict(model, test_data_loader, opt, logging)
def generate_conditional_sentence(**kwargs):
if 'dataset' not in kwargs:
opt = getattr(config, 'AmazonDigitalMusic_Config')()
else:
opt = getattr(config, kwargs['dataset'] + '_Config')()
opt.parse(kwargs)
assert(len(opt.pth_path) > 0)
random.seed(opt.seed)
np.random.seed(opt.seed)
torch.manual_seed(opt.seed)
if opt.use_gpu:
torch.cuda.manual_seed_all(opt.seed)
if len(opt.gpu_ids) == 0 and opt.use_gpu:
torch.cuda.set_device(opt.gpu_id)
model = Model(opt, getattr(models, opt.model))
if opt.use_gpu:
model.cuda()
if len(opt.gpu_ids) > 0:
model = nn.DataParallel(model, device_ids=opt.gpu_ids)
if model.net.num_fea != opt.num_fea:
raise ValueError(f"the num_fea of {opt.model} is error, please specific --num_fea={model.net.num_fea}")
model.load(opt.pth_path)
print(f"load model: {opt.pth_path}")
test_data = ReviewData(opt.data_root, mode="Test")
test_data_loader = DataLoader(test_data, batch_size=1, shuffle=False, collate_fn=collate_fn)
print(f"{now()}: generating conditional sentence...")
model.eval()
with torch.no_grad():
user_review_dict = np.load("./dataset/AmazonDigitalMusic/train/plainUserReviews.npy", allow_pickle=True).item()
item_review_dict = np.load("./dataset/AmazonDigitalMusic/train/plainItemReviews.npy", allow_pickle=True).item()
cnt = 10
for idx, (test_input, scores) in enumerate(test_data_loader):
if idx == cnt:
test_input = unpack_input(opt, test_input)
output = model(test_input, mode="Generate")
uid = test_input[2].item()
user_reviews = user_review_dict[uid]
iid = test_input[3].item()
item_reviews = item_review_dict[iid]
imp_user_review_id = output[0].cpu().numpy().squeeze()
imp_user_review_id = np.argmax(imp_user_review_id)
print(user_reviews[imp_user_review_id])
imp_item_review_id = output[1].cpu().numpy().squeeze()
imp_item_review_id = np.argmax(imp_item_review_id)
print(item_reviews[imp_item_review_id])
break
def train(**kwargs):
if 'dataset' not in kwargs:
opt = getattr(config, 'AmazonDigitalMusic_Config')()
else:
opt = getattr(config, kwargs['dataset'] + '_Config')()
opt.parse(kwargs)
random.seed(opt.seed)
np.random.seed(opt.seed)
torch.manual_seed(opt.seed)
if opt.use_gpu:
torch.cuda.manual_seed_all(opt.seed)
if len(opt.gpu_ids) == 0 and opt.use_gpu:
torch.cuda.set_device(opt.gpu_id)
model = Model(opt, getattr(models, opt.model))
if opt.use_gpu:
model.cuda()
if len(opt.gpu_ids) > 0:
model = nn.DataParallel(model, device_ids=opt.gpu_ids)
if model.net.num_fea != opt.num_fea:
raise ValueError(f"the num_fea of {opt.model} is error, please specific --num_fea={model.net.num_fea}")
# 3 data
train_data = ReviewData(opt.data_root, mode="Train")
train_data_loader = DataLoader(train_data, batch_size=opt.batch_size, shuffle=True, collate_fn=collate_fn)
val_data = ReviewData(opt.data_root, mode="Val")
val_data_loader = DataLoader(val_data, batch_size=opt.batch_size, shuffle=False, collate_fn=collate_fn)
print(f'train data: {len(train_data)}; test data: {len(val_data)}')
optimizer = optim.Adam(model.parameters(), lr=opt.lr, weight_decay=opt.weight_decay)
scheduler = optim.lr_scheduler.StepLR(optimizer, step_size=5, gamma=0.8)
# training
print("start training....")
min_loss = 1e+10
best_res = 1e+10
mse_func = nn.MSELoss()
mae_func = nn.L1Loss()
smooth_mae_func = nn.SmoothL1Loss()
train_mse_list = []
val_mse_list = []
val_mae_list = []
for epoch in range(opt.num_epochs):
total_loss = 0.0
total_maeloss = 0.0
model.train()
print(f"{now()} Epoch {epoch}...")
for idx, (train_datas, scores) in enumerate(train_data_loader):
if opt.use_gpu:
scores = torch.FloatTensor(scores).cuda()
else:
scores = torch.FloatTensor(scores)
train_datas = unpack_input(opt, train_datas)
optimizer.zero_grad()
output = model(train_datas)
mse_loss = mse_func(output, scores)
total_loss += mse_loss.item() * len(scores)
mae_loss = mae_func(output, scores)
total_maeloss += mae_loss.item()
smooth_mae_loss = smooth_mae_func(output, scores)
if opt.loss_method == 'mse':
loss = mse_loss
if opt.loss_method == 'rmse':
loss = torch.sqrt(mse_loss) / 2.0
if opt.loss_method == 'mae':
loss = mae_loss
if opt.loss_method == 'smooth_mae':
loss = smooth_mae_loss
loss.backward()
optimizer.step()
if opt.fine_step:
if idx % opt.print_step == 0 and idx > 0:
print("\t{}, {} step finised;".format(now(), idx))
val_loss, val_mse, val_mae = predict(model, val_data_loader, opt)
if val_loss < min_loss:
model.save(name=opt.dataset, opt=opt.print_opt)
min_loss = val_loss
print("\tmodel save")
if val_loss > min_loss:
best_res = min_loss
scheduler.step()
mse = total_loss * 1.0 / len(train_data)
print(f"\ttrain data: loss:{total_loss:.4f}, mse: {mse:.4f};")
val_loss, val_mse, val_mae = predict(model, val_data_loader, opt)
train_mse_list.append(mse)
val_mse_list.append(val_mse)
val_mae_list.append(val_mae)
if val_loss < min_loss:
model.save(name=opt.dataset, opt=opt.print_opt)
min_loss = val_loss
print("model save")
if val_mse < best_res:
best_res = val_mse
print("*"*30)
print("----"*20)
print(f"{now()} {opt.dataset} {opt.print_opt} best_res: {best_res}")
print("----"*20)
print("Train MSE:", train_mse_list)
print("Val MSE:", val_mse_list)
print("Val MAE:", val_mae_list)
def train(**kwargs):
if 'dataset' not in kwargs:
opt = getattr(config, 'Digital_Music_data_Config')()
else:
opt = getattr(config, kwargs['dataset'] + '_Config')()
opt.parse(kwargs)
random.seed(opt.seed)
np.random.seed(opt.seed)
torch.manual_seed(opt.seed)
if opt.use_gpu:
torch.cuda.manual_seed_all(opt.seed)
if len(opt.gpu_ids) == 0 and opt.use_gpu:
torch.cuda.set_device(opt.gpu_id)
model = Model(opt, getattr(models, opt.model))
if opt.use_gpu:
model.cuda()
if len(opt.gpu_ids) > 0:
model = nn.DataParallel(model, device_ids=opt.gpu_ids)
# 3 data
train_data = ReviewData(opt.data_root, train=True)
train_data_loader = DataLoader(train_data, batch_size=opt.batch_size, shuffle=True, num_workers=opt.num_workers, collate_fn=collate_fn)
test_data = ReviewData(opt.data_root, train=False)
test_data_loader = DataLoader(test_data, batch_size=opt.batch_size, shuffle=False, num_workers=opt.num_workers, collate_fn=collate_fn)
print('{}: train data: {}; test data: {}'.format(now(), len(train_data), len(test_data)))
optimizer = optim.Adam(model.parameters(), lr=opt.lr, weight_decay=opt.weight_decay)
scheduler = optim.lr_scheduler.StepLR(optimizer, step_size=5, gamma=0.8)
# training
print("start training....")
min_loss = 1e+10
best_res = 1e+10
mse_func = nn.MSELoss()
mae_func = nn.L1Loss()
smooth_mae_func = nn.SmoothL1Loss()
for epoch in range(opt.num_epochs):
total_loss = 0.0
total_maeloss = 0.0
model.train()
print("{} Epoch {}: start".format(now(), epoch))
for idx, (train_datas, scores) in enumerate(train_data_loader):
if opt.use_gpu:
scores = torch.FloatTensor(scores).cuda()
else:
scores = torch.FloatTensor(scores)
train_datas = unpack_input(opt, train_datas)
optimizer.zero_grad()
output = model(train_datas)
mse_loss = mse_func(output, scores)
total_loss += mse_loss.item() * len(scores)
mae_loss = mae_func(output, scores)
total_maeloss += mae_loss.item()
smooth_mae_loss = smooth_mae_func(output, scores)
if opt.loss_method == 'mse':
loss = mse_loss
if opt.loss_method == 'rmse':
loss = torch.sqrt(mse_loss) / 2.0
if opt.loss_method == 'mae':
loss = mae_loss
if opt.loss_method == 'smooth_mae':
loss = smooth_mae_loss
loss.backward()
optimizer.step()
if opt.fine_step:
if idx % opt.print_step == 0 and idx > 0:
print("\t{}, {} step finised;".format(now(), idx))
predict_loss, test_mse = predict(model, test_data_loader, opt, use_gpu=opt.use_gpu)
if predict_loss < min_loss:
model.save(name=opt.dataset, opt=opt.print_opt)
min_loss = predict_loss
print("\tmodel save")
if predict_loss > min_loss:
best_res = min_loss
scheduler.step(epoch)
print("{}; epoch:{}; total_loss:{}".format(now(), epoch, total_loss))
mse = total_loss * 1.0 / len(train_data)
mae = total_maeloss * 1.0 / len(train_data)
print("{};train reslut: mse: {}; rmse: {}; mae: {}".format(now(), mse, math.sqrt(mse), mae))
predict_loss, test_mse = predict(model, test_data_loader, opt, use_gpu=opt.use_gpu)
if predict_loss < min_loss:
model.save(name=opt.dataset, opt=opt.print_opt)
min_loss = predict_loss
print("model save")
if test_mse < best_res:
best_res = test_mse
print("----"*20)
print(f"{now()} {opt.dataset} {opt.print_opt} best_res: {best_res}")
print("----"*20)
def train(**kwargs):
if 'dataset' not in kwargs:
opt = getattr(config, 'Gourmet_Food_data_Config')()
else:
opt = getattr(config, kwargs['dataset'] + '_Config')()
opt.parse(kwargs)
logging.basicConfig(
filename=f"logs/{opt}.log",
filemode="w",
format="%(asctime)s %(name)s:%(levelname)s:%(message)s",
datefmt="%d-%m-%Y %H:%M:%S",
level=logging.DEBUG)
random.seed(opt.seed)
np.random.seed(opt.seed)
torch.manual_seed(opt.seed)
if opt.use_gpu:
torch.cuda.manual_seed_all(opt.seed)
if len(opt.gpu_ids) == 0 and opt.use_gpu:
torch.cuda.set_device(opt.gpu_id)
model = Model(opt, getattr(models, opt.model))
if opt.use_gpu:
model.cuda()
# 3 data
train_data = ReviewData(opt.data_root, mode="Train")
train_data_loader = DataLoader(train_data,
batch_size=opt.batch_size,
shuffle=True,
collate_fn=collate_fn)
val_data = ReviewData(opt.data_root, mode="Val")
val_data_loader = DataLoader(val_data,
batch_size=opt.batch_size,
shuffle=True,
collate_fn=collate_fn)
logging.info('{}: train data: {}; val data: {}'.format(
now(), len(train_data), len(val_data)))
optimizer = optim.Adam(model.parameters(),
lr=opt.lr,
weight_decay=opt.weight_decay)
scheduler = optim.lr_scheduler.StepLR(optimizer, step_size=2, gamma=0.5)
# training
logging.info("start training....")
min_loss = 1e+20
best_auc = -1.
best_per = -1.
best_epoch = 0
cre_loss = nn.BCEWithLogitsLoss()
for epoch in range(opt.num_epochs):
total_loss = 0.0
model.train()
for idx, datas in enumerate(train_data_loader):
train_datas, is_helpful, helpful_score = unpack_input(opt, datas)
optimizer.zero_grad()
output = model(train_datas)
loss = cre_loss(output, is_helpful.float())
cur_loss = loss.item()
total_loss += cur_loss
loss.backward()
optimizer.step()
scheduler.step(epoch)
logging.info(f"{now()}: epoch {epoch}: total_loss: {total_loss}")
print(f"epoch: {epoch}")
auc, corr, predict_loss = predict(model, val_data_loader, opt, logging)
if predict_loss < min_loss:
min_loss = predict_loss
if auc > best_auc:
model.save(name=opt.dataset, epoch=epoch, opt=f"{opt}")
best_epoch = epoch
best_auc = auc
best_per = corr
logging.info("model save")
logging.info("----" * 20)
logging.info(
f"{now()}:{opt.model}:{opt} \n\t\t best_auc:{best_auc}, best_per:{best_per}"
)
logging.info("----" * 20)
print("----" * 20)
print(
f"{now()}:{opt.model}:{opt} \n\t epoch:{best_epoch}: best_auc:{best_auc}, best_per:{best_per}"
)
print("----" * 20)