Pytorch报错`RuntimeError: “nll_loss_forward_reduce_cuda_kernel_2d_index“ not implemented for ‘Float‘`

最新推荐文章于 2025-01-18 21:00:44 发布

原创最新推荐文章于 2025-01-18 21:00:44 发布 · 819 阅读 ·

本内容遵循CC 4.0 BY-SA版权协议

樱木之

关注

标签

#pytorch #人工智能 #python

分类数据科学与机器学习开发

文章讲述了在使用BCELoss函数时遇到的RuntimeError，原因是标签Y的类型为Float而非Long。作者提供了解决方案，即强制将Y转换为torch.long格式以确保GPU计算的兼容性。

参考:

https://blog.csdn.net/BetrayFree/article/details/133927378

完整报错如下：

Traceback (most recent call last):
  File "/home/yingmuzhi/SpecML2/test.py", line 150, in <module>
    trainer.fit(model, data)
  File "/home/yingmuzhi/SpecML2/core.py", line 486, in fit
    self.fit_epoch()
  File "/home/yingmuzhi/SpecML2/core.py", line 496, in fit_epoch
    loss = self.model.training_step(self.prepare_batch(batch))
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yingmuzhi/SpecML2/core.py", line 393, in training_step
    l = self.loss(self(*batch[:-1]), batch[-1])
        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/yingmuzhi/SpecML2/core.py", line 762, in loss
    return F.cross_entropy(
           ^^^^^^^^^^^^^^^^
  File "/root/anaconda3/envs/env_cp311_ymz/lib/python3.11/site-packages/torch/nn/functional.py", line 3029, in cross_entropy
    return torch._C._nn.cross_entropy_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index, label_smoothing)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: "nll_loss_forward_reduce_cuda_kernel_2d_index" not implemented for 'Float'

错误代码如下：

在这里插入图片描述