Pytorch代码段

# from co-teaching train codetxtfile = save_dir + "/" + model_str + "_%s.txt"%str(args.optimizer)  ## good job！
nowTime=datetime.datetime.now().strftime('%Y-%m-%d-%H:%M:%S')
if os.path.exists(txtfile):
  os.system('mv %s %s' % (txtfile, txtfile+".bak-%s" % nowTime)) # bakeup 备份文件

# from co-teaching code but MixMatch_pytorch code also has itdef accuracy(logit, target, topk=(1,)):
  """Computes the precision@k for the specified values of k"""
  output = F.softmax(logit, dim=1) # but actually not need it 
  maxk = max(topk)
  batch_size = target.size(0)

  _, pred = output.topk(maxk, 1, True, True) # _, pred = logit.topk(maxk, 1, True, True)
  pred = pred.t()
  correct = pred.eq(target.view(1, -1).expand_as(pred))

  res = []
  for k in topk:
    correct_k = correct[:k].view(-1).float().sum(0, keepdim=True)
    res.append(correct_k.mul_(100.0 / batch_size)) # it seems this is a bug, when not all batch has same size, the mean of accuracy of each batch is not the mean of accu of all dataset
  return res

prec1, = accuracy(logit, labels, topk=(1,)) # , indicate tuple unpackage
prec1, prec5 = accuracy(logits, labels, topk=(1, 5))

# from Pytorch_MixMatch codeclass Logger(object):
  '''Save training process to log file with simple plot function.'''
  def __init__(self, fpath, title=None, resume=False): 
    self.file = None
    self.resume = resume
    self.title = '' if title == None else title
    if fpath is not None:
      if resume: 
        self.file = open(fpath, 'r') 
        name = self.file.readline()
        self.names = name.rstrip().split('\t')
        self.numbers = {}
        for _, name in enumerate(self.names):
          self.numbers[name] = []

        for numbers in self.file:
          numbers = numbers.rstrip().split('\t')
          for i in range(0, len(numbers)):
            self.numbers[self.names[i]].append(numbers[i])
        self.file.close()
        self.file = open(fpath, 'a') 
      else:
        self.file = open(fpath, 'w')

  def set_names(self, names):
    if self.resume: 
      pass
    # initialize numbers as empty list
    self.numbers = {}
    self.names = names
    for _, name in enumerate(self.names):
      self.file.write(name)
      self.file.write('\t')
      self.numbers[name] = []
    self.file.write('\n')
    self.file.flush()


  def append(self, numbers):
    assert len(self.names) == len(numbers), 'Numbers do not match names'
    for index, num in enumerate(numbers):
      self.file.write("{0:.4f}".format(num))
      self.file.write('\t')
      self.numbers[self.names[index]].append(num)
    self.file.write('\n')
    self.file.flush()

  def plot(self, names=None):  
    names = self.names if names == None else names
    numbers = self.numbers
    for _, name in enumerate(names):
      x = np.arange(len(numbers[name]))
      plt.plot(x, np.asarray(numbers[name]))
    plt.legend([self.title + '(' + name + ')' for name in names])
    plt.grid(True)

  def close(self):
    if self.file is not None:
      self.file.close()
# usage
logger = Logger(new_folder+'/log_for_%s_WebVision1M.txt'%data_type, title=title)
logger.set_names(['epoch', 'val_acc', 'val_acc_ImageNet'])
for epoch in range(100):
  logger.append([epoch, val_acc, val_acc_ImageNet])
logger.close()

### run.sh ###
CUDA_VISIBLE_DEVICES=0 /usr/bin/python2.7 script/train.py train DIEN >train_dein2.log 2>&1 &
#############

if __name__ == '__main__':
  if len(sys.argv) == 4:
    SEED = int(sys.argv[3]) # 0,1,2,3
  else:
    SEED = 3
  tf.set_random_seed(SEED)
  numpy.random.seed(SEED)
  random.seed(SEED)
  if sys.argv[1] == 'train':
    train(model_type=sys.argv[2], seed=SEED)
  elif sys.argv[1] == 'test':
    test(model_type=sys.argv[2], seed=SEED)
  else:
    print('do nothing...')

#适用于输出变量的个数不同的情况
if time_point：
　　A, B, C = f1(x, y, time_point=True)
else:
　　A, B = f1(x, y, time_point=False)
# 适用于输出变量个数和类型相同的情况
C, D = f2(x, y, time_point=time_point)

mkdir cora
for num in $(seq 0 99) do
　　python train_grand.py --hidden 32 --lr 0.01 --patience 200 --seed $num --dropnode_rate 0.5 > cora/"$num".txt
done