Pytorch: TypeError: 'str' object 不能解释为 integer

Question

#无论我做什么，我都会遇到这个错误，我该怎么办？

class SearchCell(nn.Module):

  def __init__(self, steps, multiplier, prev_prev_C, prev_C, curr_C, reduction, prev_reduction):
    super(SearchCell, self).__init__()
    self.steps = steps
    self.multiplier = multiplier
    self.reduction = reduction
  
    if prev_reduction:
      self.prep0 = FactorizedReduce(prev_prev_C,curr_C, affine=False)
    else:
      self.prep0 = ReLUConvBN(prev_prev_C, curr_C, 1, 1, 0, affine=False)
    self.prep1 = ReLUConvBN(prev_C, curr_C, 1, 1, 0, affine=False)

    self.layers = nn.ModuleList()
 -->   for i in range(steps):
        for j in range(2+i):
            stride = 2 if reduction and j < 2 else 1
            op = MixedOp(curr_C, stride)
            self.layers.append(op)

  def forward(self, s0, s1, weights):
    s0 = self.prep0(s0)
    s1 = self.prep1(s1)
    states = [s0, s1]
    offset = 0
    for i in range(self.steps):
      s = sum([self.layers[offset + j](h, weights[offset + j]) for j, h in enumerate(states)])
      offset += len(states)
      states.append(s)

    return torch.cat(states[-self.multiplier:], dim=1)

初始化中的 TypeErrorTraceback （最近一次调用）（self，steps，multiplier，prev_prev_C，prev_C，curr_C，reduction，prev_reduction）36 37 self.layers = nn.ModuleList() 38 for i in range(steps): 39 for j in range(2+i): 40 stride = 2 if reduction and j < 2 else 1 TypeError: 'str' object 不能解释为 integer

Answer 1

根据您的错误，steps 是一个字符串，而 range(steps) 意味着 step 必须是 integer 导致范围迭代 integer n （从 0 到 n-1）。 检查步骤 integer 是否使用print(type(steps))如果它是一个字符串，请尝试使用此steps = int(steps)它将类型转换为 integer。 如果步骤中有一个字符，它将返回另一个错误can convert str to string 。 如果发生这种情况，请跟踪每个步骤的出现并检查使用print(type(steps))将 steps(int) 转换为 str 的位置

class SearchCell(nn.Module):

  def __init__(self, steps, multiplier, prev_prev_C, prev_C, curr_C, reduction, prev_reduction):
    super(SearchCell, self).__init__()
    self.steps = int(steps)    # changed here 
    self.multiplier = multiplier
    self.reduction = reduction
  
    if prev_reduction:
      self.prep0 = FactorizedReduce(prev_prev_C,curr_C, affine=False)
    else:
      self.prep0 = ReLUConvBN(prev_prev_C, curr_C, 1, 1, 0, affine=False)
    self.prep1 = ReLUConvBN(prev_C, curr_C, 1, 1, 0, affine=False)

或者试试这个，希望对你有帮助。