def __init__(self, config_path, gpu, model_path):
# gpu
self.use_gpu = True
if gpu is None:
self.use_gpu = False
else:
self.use_gpu = True
os.environ["CUDA_VISIBLE_DEVICES"] = gpu
# config
self.config = ConfigParser(config_path)
# formatter
useable_list = {
# "AYYC": AYPredictionFormatter
"DeepFM": DeepFMFormatter,
"LRMM": MusicPairFormatter,
"DeepInterest": DeepInterestFormatter,
"NCF": NCFFormatter
}
if self.config.get("data", "formatter") in useable_list.keys():
self.formatter = useable_list[self.config.get(
"data", "formatter")](self.config)
else:
raise NotImplementedError
task_loss_type = self.config.get("train", "type_of_loss")
self.criterion = get_loss(task_loss_type)
#model
model_name = self.config.get("model", "name")
net = get_model(model_name, self.config)
device = []
if torch.cuda.is_available() and self.use_gpu:
net = net.cuda()
net.load_state_dict(torch.load(model_path))
self.net = net
print_info("Net build done")
args = parser.parse_args()
configFilePath = args.config
if configFilePath is None:
print("python *.py\t--config/-c\tconfigfile")
use_gpu = True
if args.gpu is None:
use_gpu = False
else:
use_gpu = True
os.environ["CUDA_VISIBLE_DEVICES"] = args.gpu
config = ConfigParser(configFilePath)
print_info("Start to build Net")
model_name = config.get("model", "name")
net = get_model(model_name, config)
print_info(model_name)
device = []
print_info("CUDA:%s" % str(torch.cuda.is_available()))
if torch.cuda.is_available() and use_gpu:
device_list = args.gpu.split(",")
for a in range(0, len(device_list)):
device.append(int(a))
print_info('begin .cuda()')
net = net.cuda()
print_info('cuda() successfully')
if cnt % output_time == 0:
print('\r', end='', flush=True)
print(
'%.4f % 3d | %.4f % 2.2f | ???? ????? | %s | %d'
% (lr, epoch_num + 1, train_loss / train_cnt, train_acc /
train_cnt * 100, time_to_str((timer() - start)), cnt),
end='',
flush=True)
train_loss /= train_cnt
train_acc /= train_cnt
# writer.add_scalar(config.get("output", "model_name") + " train loss", train_loss, epoch_num + 1)
# writer.add_scalar(config.get("output", "model_name") + " train accuracy", train_acc, epoch_num + 1)
if not os.path.exists(model_path):
os.makedirs(model_path)
torch.save(net.state_dict(),
os.path.join(model_path, "model-%d.pkl" % (epoch_num + 1)))
valid_loss, valid_accu = valid_net(net, valid_dataset, use_gpu, config,
epoch_num + 1, writer)
print('\r', end='', flush=True)
print(
'%.4f % 3d | %.4f %.2f | %.4f % 2.2f | %s |'
% (lr, epoch_num + 1, train_loss, train_acc * 100, valid_loss,
valid_accu * 100, time_to_str((timer() - start))))
print_info("training is finished!")
def __init__(self, path):
print_info("begin to load word embedding")
self.model = fasttext.load_model(path)
print_info("load word embedding succeed")
args = parser.parse_args()
configFilePath = args.config
if configFilePath is None:
print("python *.py\t--config/-c\tconfigfile")
use_gpu = True
if args.gpu is None:
use_gpu = False
else:
use_gpu = True
os.environ["CUDA_VISIBLE_DEVICES"] = args.gpu
config = ConfigParser(configFilePath)
print_info("Start to build Net")
model_name = config.get("model", "name")
net = get_model(model_name, config)
device = []
if torch.cuda.is_available() and use_gpu:
device_list = args.gpu.split(",")
for a in range(0, len(device_list)):
device.append(int(a))
net = net.cuda()
try:
net.init_multi_gpu(device)
except Exception as e: