RuntimeError："addmm_impl_cpu_“在”一半“中没有实现
RuntimeError："addmm_impl_cpu_“在”一半“中没有实现
提问于 2022-08-29 14:44:48
当我运行pytorch matmul时，会引发以下错误：
Traceback (most recent call last):
File "/home/omrastogi/Desktop/Side/One-Class-Classification-Customer-Complaints/pattern.py", line 71, in <module>
print(obj.infer(list([df.text[0]]), list([df.reason[0]])))
File "/home/omrastogi/Desktop/Side/One-Class-Classification-Customer-Complaints/pattern.py", line 45, in infer
cos_sm = self.batch_cosine_similarity(enc1, enc2)
File "/home/omrastogi/Desktop/Side/One-Class-Classification-Customer-Complaints/pattern.py", line 51, in batch_cosine_similarity
dot_prd = torch.matmul(inp1, inp2.transpose(0, 1))
RuntimeError: "addmm_impl_cpu_" not implemented for 'Half'inp1 -> 1_256_
_inp2 -> 1_256
回答 1
Stack Overflow用户
发布于 2022-08-29 14:48:07
错误是抛出的，因为操作数的数据类型是float16。将其改为float32解决了这个问题。我想float16只适用于GPU实现。
页面原文内容由Stack Overflow提供。腾讯云小微IT领域专用引擎提供翻译支持
原文链接：
https://stackoverflow.com/questions/73530569
复制相关文章
相似问题
腾讯云开发者
