PyTorch出现RuntimeError: Function AddBackward0 returned an invalid gradient at index 1

感谢下面这篇文章，问题解决了：

https://blog.csdn.net/andyL_05/article/details/107952479

报错是这样的：

RuntimeError: Function AddBackward0 returned an invalid gradient at index 1 - expected type TensorOptions(dtype=float, device=cuda:0, layout=Strided, requires_grad=false) but got TensorOptions(dtype=float, device=cpu, layout=Strided, requires_grad=false) (validate_outputs at /pytorch/torch/csrc/autograd/engine.cpp:484)
frame #0: c10::Error::Error(c10::SourceLocation, std::string const&) + 0x46 (0x7f4228517536 in /usr/local/lib/python3.8/dist-packages/torch/lib/libc10.so)
frame #1: + 0x2d84224 (0x7f418672b224 in /usr/local/lib/python3.8/dist-packages/torch/lib/libtorch_cpu.so)
frame #2: torch::autograd::Engine::evaluate_function(std::shared_ptrtorch::autograd::GraphTask&, torch::autograd::Node*, torch::autograd::InputBuffer&) + 0x548 (0x7f418672cd58 in /usr/local/lib/python3.8/dist-packages/torch/lib/libtorch_cpu.so)
frame #3: torch::autograd::Engine::thread_main(std::shared_ptrtorch::autograd::GraphTask const&, bool) + 0x3d2 (0x7f418672ece2 in /usr/local/lib/python3.8/dist-packages/torch/lib/libtorch_cpu.so)
frame #4: torch::autograd::Engine::thread_init(int) + 0x39 (0x7f4186727359 in /usr/local/lib/python3.8/dist-packages/torch/lib/libtorch_cpu.so)
frame #5: torch::autograd::python::PythonEngine::thread_init(int) + 0x38 (0x7f422f0ad3d8 in /usr/local/lib/python3.8/dist-packages/torch/lib/libtorch_python.so)

说的是反向传播需要数据在GPU上，然而却得到了CPU的数据。但是我明明是都.to(cuda0)了。

原因是在模型中，前向传播函数里面又定义了新的变量，但是这个变量默认是在cpu上定义的。

解决方法就是：

x = torch.tensor([0.]).cuda()

这也就OK啦！

PyTorch出现RuntimeError: Function AddBackward0 returned an invalid gradient at index 1相关推荐

RuntimeError: Function CdistBackward returned an invalid gradient
报错:RuntimeError: Function CdistBackward returned an invalid gradient at index 1 – got [2,7,7] but ex ...
【Pytorch】反向传播为NaN报错的排查解决方法，RuntimeError: Function ‘BmmBackward0‘ returned nan values
最近在训练模型的过程中,反复出现方向传播至为NaN的报错,报错信息如下所示: File "/home/fu/anaconda3/envs/torch/lib/python3.7/site-p ...
PyTorch RuntimeError: Function ‘CudnnBatchNormBackward0‘ returned nan values in its 0th output. 解决方法
1. 查看输入是否含有nan或者全是0 2. 查看最后的loss是否是nan 3. 最难debug的一点是当learning rate过高的时候也会报题目中的错
Function ‘MseLossBackward0‘ returned nan values in its 0th output.
这个比较奇怪的提示来自于Pytorch计算梯度的过程中产生了一个nan值. 如果开启了: torch.autograd.set_detect_anomaly(True) 那么在loss.backwar ...
pytorch测试报错：RuntimeError: cuda runtime error (10) : invalid device ordinal at torch/csrc/cuda/Module
模型在服务器多gpu上训练,测试在自己台式机上进行,只有一块gpu,测试报错: File "/home/fuxueping/sdb/PycharmProjects/face_recognit ...
PyTorch 错误 RuntimeError: invalid argument 5: k not in range for dimension at /pytorch/aten/src/THC/g
PyTorch 错误 RuntimeError: invalid argument 5: k not in range for dimension at /pytorch/aten/src/THC/g ...
RuntimeError: cuda runtime error (11) : invalid argument at /pytorch/aten/src/THC/THCGeneral.cpp
RuntimeError: cuda runtime error (11) : invalid argument at /pytorch/aten/src/THC/THCGeneral.cpp cud ...
小程序Git问题：ERROR: credentials callback returned an invalid cred type解决方法
ERROR: credentials callback returned an invalid cred type 错误:凭据回调返回了无效的凭据类型从最字面上的意思理解是在拉取或者合并时,没有拿到 ...
TypeError: The view function for did not return a valid response. The function either returned None
TypeError: The view function for 'uploadImg' did not return a valid response. The function either re ...

PyTorch出现RuntimeError: Function AddBackward0 returned an invalid gradient at index 1

PyTorch出现RuntimeError: Function AddBackward0 returned an invalid gradient at index 1相关推荐

最新文章

热门文章