linear(): argument ‘input‘ (position 1) must be Tensor, not str

TypeError: linear(): argument 'input' (position 1) must be Tensor, not str

在使用hugging fice加载预训练bert的时候，出现这个问题，原来是这样写的：

self.bert = BertModel.from_pretrained(pretrained_model_path, output_hidden_states=True, output_attentions=True, return_dict=True)

将 return_dict 设置为 False 即可

self.bert = BertModel.from_pretrained(pretrained_model_path, output_hidden_states=True, output_attentions=True, return_dict=False)

参考：https://blog.csdn.net/qsx123432/article/details/123984811

linear(): argument ‘input‘ (position 1) must be Tensor, not str相关推荐

TypeError系列之：TypeError: conv2d(): argument 'input' (position 1) must be Tensor, not NoneType
这里出现类似错误往往是因为,conv2d()函数的第一个参数,需要时一个tensor行的数据,然而却赋值成了not后给的类型. 我出现问题的原因是,中间有一个函数缺少返回值,因此会造成NoneType ...
argument ‘input‘ (position 1) must be Tensor, not XX
这里:numpy 和 tensor数据相互转换的方法: 1.numpy->tensor data = torch.tensor(data) 2.tensor->numpy 非训练数据(训练 ...
input(position 1) must be Tensor, not NoneType
https://blog.csdn.net/qq_41368074/article/details/105560274?utm_medium=distribute.pc_relevant.none-t ...
pytorch view(): argument 'size' (position 1) must be tuple of ints, not Tensor
view(): argument 'size' (position 1) must be tuple of ints, not Tensor pytorch的view函数参数不能是tensor,解决方 ...
{TypeError}clamp(): argument 'min' must be Number, not Tensor
{TypeError}clamp(): argument 'min' must be Number, not Tensor x1是二维数组, xx1 = x1[order[1:]].clamp(min ...
errors_impl.InvalidArgumentError: Input to reshape is a tensor
errors_impl.InvalidArgumentError: Input to reshape is a tensor InvalidArgumentError (see above for t ...
pytorch torch.norm(input, p=2) → float、torch.norm(input, p, dim, out=None) → Tensor（求范数）
torch.norm 用法1: torch.norm(input, p=2) → float 返回输入张量input 的p 范数. 参数: input (Tensor) – 输入张量 p (float ...
2021.08.25学习内容torch.clamp(input, min, max, out=None) → Tensor，torch.mm（matrix multiply）
学习pytorch时,看到了mm和clamp,不甚理解,其他地方也看到过,所以具体了解一下前向传递:计算预测yh = x.mm(w1)h_relu = h.clamp(min=0) 把 h 张量的最 ...
【tensorflow】Input to reshape is a tensor with xxx values, but the requested shape requires a multipl
今天写了一个简单的3DCNN,结果在跑的时候出现一个问题, tensorflow.python.framework.errors.InvalidArgumentError: Input to resh ...

linear(): argument ‘input‘ (position 1) must be Tensor, not str

linear(): argument ‘input‘ (position 1) must be Tensor, not str相关推荐

最新文章

热门文章