-
Notifications
You must be signed in to change notification settings - Fork 62
/
main.py
141 lines (122 loc) · 3.89 KB
/
main.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
import os
import time
import argparse
import numpy as np
import torch
import torch.nn as nn
import torch.optim as optim
import torch.utils.data as data
import torch.backends.cudnn as cudnn
from tensorboardX import SummaryWriter
import model
import config
import evaluate
import data_utils
parser = argparse.ArgumentParser()
parser.add_argument("--lr",
type=float,
default=0.001,
help="learning rate")
parser.add_argument("--dropout",
type=float,
default=0.0,
help="dropout rate")
parser.add_argument("--batch_size",
type=int,
default=256,
help="batch size for training")
parser.add_argument("--epochs",
type=int,
default=20,
help="training epoches")
parser.add_argument("--top_k",
type=int,
default=10,
help="compute metrics@top_k")
parser.add_argument("--factor_num",
type=int,
default=32,
help="predictive factors numbers in the model")
parser.add_argument("--num_layers",
type=int,
default=3,
help="number of layers in MLP model")
parser.add_argument("--num_ng",
type=int,
default=4,
help="sample negative items for training")
parser.add_argument("--test_num_ng",
type=int,
default=99,
help="sample part of negative items for testing")
parser.add_argument("--out",
default=True,
help="save model or not")
parser.add_argument("--gpu",
type=str,
default="0",
help="gpu card ID")
args = parser.parse_args()
os.environ["CUDA_VISIBLE_DEVICES"] = args.gpu
cudnn.benchmark = True
############################## PREPARE DATASET ##########################
train_data, test_data, user_num ,item_num, train_mat = data_utils.load_all()
# construct the train and test datasets
train_dataset = data_utils.NCFData(
train_data, item_num, train_mat, args.num_ng, True)
test_dataset = data_utils.NCFData(
test_data, item_num, train_mat, 0, False)
train_loader = data.DataLoader(train_dataset,
batch_size=args.batch_size, shuffle=True, num_workers=4)
test_loader = data.DataLoader(test_dataset,
batch_size=args.test_num_ng+1, shuffle=False, num_workers=0)
########################### CREATE MODEL #################################
if config.model == 'NeuMF-pre':
assert os.path.exists(config.GMF_model_path), 'lack of GMF model'
assert os.path.exists(config.MLP_model_path), 'lack of MLP model'
GMF_model = torch.load(config.GMF_model_path)
MLP_model = torch.load(config.MLP_model_path)
else:
GMF_model = None
MLP_model = None
model = model.NCF(user_num, item_num, args.factor_num, args.num_layers,
args.dropout, config.model, GMF_model, MLP_model)
model.cuda()
loss_function = nn.BCEWithLogitsLoss()
if config.model == 'NeuMF-pre':
optimizer = optim.SGD(model.parameters(), lr=args.lr)
else:
optimizer = optim.Adam(model.parameters(), lr=args.lr)
# writer = SummaryWriter() # for visualization
########################### TRAINING #####################################
count, best_hr = 0, 0
for epoch in range(args.epochs):
model.train() # Enable dropout (if have).
start_time = time.time()
train_loader.dataset.ng_sample()
for user, item, label in train_loader:
user = user.cuda()
item = item.cuda()
label = label.float().cuda()
model.zero_grad()
prediction = model(user, item)
loss = loss_function(prediction, label)
loss.backward()
optimizer.step()
# writer.add_scalar('data/loss', loss.item(), count)
count += 1
model.eval()
HR, NDCG = evaluate.metrics(model, test_loader, args.top_k)
elapsed_time = time.time() - start_time
print("The time elapse of epoch {:03d}".format(epoch) + " is: " +
time.strftime("%H: %M: %S", time.gmtime(elapsed_time)))
print("HR: {:.3f}\tNDCG: {:.3f}".format(np.mean(HR), np.mean(NDCG)))
if HR > best_hr:
best_hr, best_ndcg, best_epoch = HR, NDCG, epoch
if args.out:
if not os.path.exists(config.model_path):
os.mkdir(config.model_path)
torch.save(model,
'{}{}.pth'.format(config.model_path, config.model))
print("End. Best epoch {:03d}: HR = {:.3f}, NDCG = {:.3f}".format(
best_epoch, best_hr, best_ndcg))