[debug] RuntimeError: “nll_loss_forward_reduce_cuda_kernel_2d

问题描述

在使用nn.CrossEntropyLoss时出现报错：

loss_id = self.IDLoss(id_preds, id_targets)

Traceback (most recent call last):File "/home/hgx/pycharm-2020.1.3/plugins/python/helpers/pydev/_pydevd_bundle/pydevd_exec2.py", line 3, in Execexec(exp, global_vars, local_vars)File "<input>", line 1, in <module>File "/home/hgx/anaconda3/envs/bytetrack/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1102, in _call_implreturn forward_call(*input, **kwargs)File "/home/hgx/anaconda3/envs/bytetrack/lib/python3.7/site-packages/torch/nn/modules/loss.py", line 1152, in forwardlabel_smoothing=self.label_smoothing)File "/home/hgx/anaconda3/envs/bytetrack/lib/python3.7/site-packages/torch/nn/functional.py", line 2846, in cross_entropyreturn 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 'Int'

问题分析

数据类型导致的错误

解决方案

进行数据类型转换

id_targets = id_targets.to(torch.int64)     # TODO: ReID. [matched_anchor], float16 to int

[debug] RuntimeError: “nll_loss_forward_reduce_cuda_kernel_2d_index“ not implemented for ‘Int‘相关推荐

RuntimeError: “unfolded2d_copy“ not implemented for ‘Half‘（实测百分百有效）
报错 RuntimeError: "unfolded2d_copy" not implemented for 'Half' 原因模型传入的参数use_half=true,就是利用 ...
[debug] RuntimeError: CUDA error: no kernel image is available for execution on the device
问题描述运行程序时出现报错: RuntimeError: CUDA error: no kernel image is available for execution on the device ( ...
RuntimeError: “LayerNormKernelImpl“ not implemented for ‘Long‘
将GitHUB上下载的模块用于自己的模型,一定要注意输入数据的数据类型(dtype)是否满足模块的要求第一步:数据类型为张量:train_inputs=torch.tensor(train_inpu ...
YOLOv5+deepsort——报错解决：RuntimeError: “unfolded2d_copy“ not implemented for ‘Half‘
一.报错原因 CPU不支持半精度训练二.解决办法要么采用GPU训练要么将检测模块中的.half()全部改成.float()(计算时请保证数据类型一致)
python个人bug修炼手册
文章目录问题一:python: can't open file 'argparse_learning_1.py': [Errno 2] No such file or directory 问题二:M ...
64位Fedora运行32位C++程序中int精度溢出处理
在64-bit机器中编译32-bit的代码出现int(强制转换而至)精度溢出: Debug==> error: cast from 'void*' to 'int' loses precisio ...
从C＃中的枚举获取int值
我有一堂课,叫做Questions (复数). 在此类中,有一个名为Question (单数)的枚举,它看起来像这样. public enum Question {Role = 2,ProjectFu ...
区分Debug版还是Relase版
// test.cpp : 区分Debug版还是Relase版 // #include "stdafx.h" //提示使用Debug环境会定义宏_DEBUG int _tmain( ...
DEBUG命令的应用
TAG:随笔杂记下面对一些常用指令进行详细剖析: A (Assemble) 汇编指令 1,输入汇编语句被汇编到内存的指定区段,此区段在开始时用A address 指定. 2,所有语句输入完成后,按E ...

[debug] RuntimeError: “nll_loss_forward_reduce_cuda_kernel_2d_index“ not implemented for ‘Int‘

问题描述

问题分析

解决方案

[debug] RuntimeError: “nll_loss_forward_reduce_cuda_kernel_2d_index“ not implemented for ‘Int‘相关推荐

最新文章

热门文章