Here is the part of code
os.environ["KMP_DUPLICATE_LIB_OK"]="TRUE"
parser = argparse.ArgumentParser()
parser.add_argument('-j', '--workers', default=12, type=int, metavar='N', help='number of data loading workers')
parser.add_argument('--epochs', default=1000, type=int, metavar='N', help='number of total epochs to run')
parser.add_argument('--start-epoch', default=0, type=int, metavar='N', help='manual epoch number (useful on restarts)')
parser.add_argument('-b', '--batch-size', default=40, type=int, metavar='N')
parser.add_argument('--lr', '--learning-rate', default=0.001, type=float, metavar='LR', dest='lr')
parser.add_argument('--momentum', default=0.9, type=float, metavar='M')
parser.add_argument('--wd', '--weight-decay', default=1e-1, type=float, metavar='W', dest='weight_decay')
parser.add_argument('-p', '--print-freq', default=10, type=int, metavar='N', help='print frequency')
parser.add_argument('--resume', default=None, type=str, metavar='PATH', help='path to latest checkpoint')
parser.add_argument('--data_set', type=int, default=1)
parser.add_argument('--gpu', type=str, default='0')
args = parser.parse_args()
now = datetime.datetime.now()
time_str = now.strftime("[%m-%d]-[%H:%M]-")
project_path = './'
log_txt_path = project_path + 'log/' + time_str + 'set' + str(args.data_set) + '-log.txt'
log_curve_path = project_path + 'log/' + time_str + 'set' + str(args.data_set) + '-log.png'
checkpoint_path = project_path + 'checkpoint/' + time_str + 'set' + str(args.data_set) + '-model.pth'
best_checkpoint_path = project_path + 'checkpoint/' + time_str + 'set' + str(args.data_set) + '-model_best.pth'
os.environ["CUDA_VISIBLE_DEVICES"] = args.gpu
pretrained_checkpoint_path = './pretrain_DFEW.pth'
def SoftCrossEntropy(inputs, target, reduction='average'):
log_likelihood = -torch.log_softmax(inputs, dim=1)
batch = inputs.shape[0]
if reduction == 'average':
loss = torch.sum(torch.mul(log_likelihood, target)) / batch
else:
loss = torch.sum(torch.mul(log_likelihood, target))
return loss
def main():
best_acc = 0
recorder = RecorderMeter(args.epochs)
print('The training time: ' + now.strftime("%m-%d %H:%M"))
print('The training set: set ' + str(args.data_set))
with open(log_txt_path, 'a') as f:
f.write('The training set: set ' + str(args.data_set) + '\n')
# create model and load pre_trained parameters
model = GenerateModel()
model = torch.nn.DataParallel(model).cuda()
##CE_LOSS, keepdim
criterion = nn.CrossEntropyLoss(reduction='none').cuda()
optimizer = torch.optim.SGD(model.parameters(), args.lr, momentum=args.momentum, weight_decay=args.weight_decay)
#lr_decay
scheduler = torch.optim.lr_scheduler.StepLR(optimizer, step_size=7, gamma=0.5)
#scheduler = torch.optim.lr_scheduler.CosineAnnealingWarmRestarts(optimizer, T_0=10)
can anyone please tell me where is the error?
I also have the updated driver of my cuda
