码上欢乐
相关内容   简体   繁体

TypeError: can't convert CUDA tensor to numpy. Use Tensor.cpu() to copy the tensor to host memory first.

本文转载自  查看原文  2019-04-09 15:46  3398    python

报错原因：numpy不能读取CUDA tensor 需要将它转化为 CPU tensor。

所以如果想把CUDA tensor格式的数据改成numpy时，需要先将其转换成cpu float-tensor随后再转到numpy格式

报错行：

tcls[index, best_n, g_y_center, g_x_center, np.array(target[index, t, 0])] = 1

修改后：

tcls[index, best_n, g_y_center, g_x_center, np.array(target[index, t, 0].cpu())] = 1

 


免责声明！

本站转载的文章为个人学习借鉴使用，本站对版权不负任何法律责任。如果侵犯了您的隐私权益，请联系本站邮箱yoyou2525@163.com删除。



猜您在找 TypeError: can't convert cuda:0 device type tensor to numpy. Use Tensor.cpu() to copy the tensor to host memory first. can't convert CUDA tensor to numpy. Use Tensor.cpu() to copy the tensor to host memory first. TypeError: can't convert CUDA tensor to numpy. Use Tensor.cpu() to copy the tensor to host memory .. TypeError: Can not convert a float32 into a Tensor or Operation. TypeError: Fetch argument 0 has invalid type , must be a string or Tensor. (Can not convert a int into a Tensor or Operation.) python中遇到问题TypeError: Can't convert 'int' object to str implicitly 报错：invalid index of a 0-dim tensor. Use tensor.item() to convert a 0-dim tensor to a Python number IndexError: invalid index of a 0-dim tensor. Use tensor.item() to convert a 0-dim tensor to a Python number tensorflow基础--LeNet-5测试模型遇到TypeError: Failed to convert object of type to Tensor Python求定积分+处理can‘t convert expression to float错误
 
粤ICP备18138465号  © 2018-2025 CODEPRJ.COM