RuntimeError: Input and parameter tensors are not at the same device, found input tensor at cpu and

本文解析了PyTorch中常见的RuntimeError: Input and parameter tensors are not at the same device的问题,提供了一个实例并详细介绍了如何通过调整代码确保所有张量位于同一设备上(CPU或GPU),以避免此类错误。

摘要生成于 C知道 ,由 DeepSeek-R1 满血版支持, 前往体验 >

RuntimeError: Input and parameter tensors are not at the same device, found input tensor at cpu and parameter tensor at cuda:0

在学习pytorch的时候遇到的错误,意思是,输入和参数的张量不是在同一个device里,有一部分在CPU有一部分在GPU.

下面是一个例子,参考于 https://github.com/zergtant/pytorch-handbook/blob/master/chapter3/3.3-rnn.ipynb

只需要将下面代码 #x = x.cuda() #y = y.cuda()取消注释就可以运行。
因为下面的x,y这两个tensor放在CPU里,所以只需要把他们放入GPU中

import torch
import torch.nn as nn
from torch.nn import functional as F
from torch import optim
import numpy as np
from matplotlib import pyplot as plt
import matplotlib.animation
import math, random
TIME_STEP = 10  # rnn 时序步长数
INPUT_SIZE = 1  # rnn 的输入维度
DEVICE = torch.device("cuda" if torch.cuda.is_available() else "cpu")
H_SIZE = 64  # of rnn 隐藏单元个数
EPOCHS = 300  # 总共训练次数
h_state = None  # 隐藏层状态

steps = np.linspace(0, np.pi * 2, 256, dtype=np.float32)
x_np = np.sin(steps)
y_np = np.cos(steps)


class RNN(nn.Module):
    def __init__(self):
        super(RNN, self).__init__()
        self.rnn = nn.RNN(
            input_size=INPUT_SIZE,
            hidden_size=H_SIZE,
            num_layers=1,
            batch_first=True,
        )
        self.out = nn.Linear(H_SIZE, 1)

    def forward(self, x, h_state):
        # x (batch, time_step, input_size)
        # h_state (n_layers, batch, hidden_size)
        # r_out (batch, time_step, hidden_size)
        r_out, h_state = self.rnn(x, h_state)
        outs = []  # 保存所有的预测值
        for time_step in range(r_out.size(1)):  # 计算每一步长的预测值
            outs.append(self.out(r_out[:, time_step, :]))
        return torch.stack(outs, dim=1), h_state
        # 也可使用以下这样的返回值
        # r_out = r_out.view(-1, 32)
        # outs = self.out(r_out)
        # return outs, h_state


rnn = RNN().to(DEVICE)
optimizer = torch.optim.Adam(rnn.parameters())  # Adam优化,几乎不用调参
criterion = nn.MSELoss()  # 因为最终的结果是一个数值,所以损失函数用均方误差
rnn.train()

plt.figure(2)
for step in range(EPOCHS):
    start, end = step * np.pi, (step + 1) * np.pi  # 一个时间周期
    steps = np.linspace(start, end, TIME_STEP, dtype=np.float32)
    x_np = np.sin(steps)
    y_np = np.cos(steps)
    x = torch.from_numpy(x_np[np.newaxis, :, np.newaxis]) # shape (batch, time_step, input_size)
    y = torch.from_numpy(y_np[np.newaxis, :, np.newaxis])
    
    #加上这两行就不会报错了
    #x = x.cuda()
    #y = y.cuda()
    
    prediction, h_state = rnn(x, h_state)  # rnn output
    # 这一步非常重要
    h_state = h_state.data  # 重置隐藏层的状态, 切断和前一次迭代的链接
    loss = criterion(prediction, y)
    # 这三行写在一起就可以
    optimizer.zero_grad()
    loss.backward()
    optimizer.step()
    if (step + 1) % 20 == 0:  # 每训练20个批次可视化一下效果,并打印一下loss
        print("EPOCHS: {},Loss:{:4f}".format(step, loss))
        #plt.plot(steps, y_np.flatten(), 'r-')
        #plt.plot(steps, prediction.data.numpy().flatten(), 'b-')
        #plt.draw()
        #plt.pause(0.01)

上面的代码我注释掉画图的部分。
如果不注释,会出现这个错误。
TypeError: can’t convert CUDA tensor to numpy. Use Tensor.cpu() to copy the tensor to host memory first.
这是因为GPU的tensor不能转化为numpy。
如果需要画图的话,可以把所以数据都放在cpu中

DEVICE = torch.device("cuda" if torch.cuda.is_available() else "cpu")

改为

DEVICE = torch.device("CUP")

或者使用tensorboard等可视化工具

Traceback (most recent call last): File "D:\Sogou\yolov12-main\train.py", line 8, in <module> results = model.train( ^^^^^^^^^^^^ File "D:\Sogou\yolov12-main\ultralytics\engine\model.py", line 808, in train self.trainer.train() File "D:\Sogou\yolov12-main\ultralytics\engine\trainer.py", line 207, in train self._do_train(world_size) File "D:\Sogou\yolov12-main\ultralytics\engine\trainer.py", line 381, in _do_train self.loss, self.loss_items = self.model(batch) ^^^^^^^^^^^^^^^^^ File "D:\LBY\envs\yolov12\Lib\site-packages\torch\nn\modules\module.py", line 1553, in _wrapped_call_impl return self._call_impl(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\LBY\envs\yolov12\Lib\site-packages\torch\nn\modules\module.py", line 1562, in _call_impl return forward_call(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Sogou\yolov12-main\ultralytics\nn\tasks.py", line 112, in forward return self.loss(x, *args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Sogou\yolov12-main\ultralytics\nn\tasks.py", line 293, in loss preds = self.forward(batch["img"]) if preds is None else preds ^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Sogou\yolov12-main\ultralytics\nn\tasks.py", line 113, in forward return self.predict(x, *args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Sogou\yolov12-main\ultralytics\nn\tasks.py", line 131, in predict return self._predict_once(x, profile, visualize, embed) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Sogou\yolov12-main\ultralytics\nn\tasks.py", line 152, in _predict_once x = m(x) # run ^^^^ File "D:\LBY\envs\yolov12\Lib\site-packages\torch\nn\modules\module.py", line 1553, in _wrapped_call_impl return self._call_impl(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\LBY\envs\yolov12\Lib\site-packages\torch\nn\modules\module.py", line 1562, in _call_impl return forward_call(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Sogou\yolov12-main\ultralytics\nn\modules\block.py", line 1546, in forward combined = safe_fusion(enhanced_detail, shape_fused) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Sogou\yolov12-main\ultralytics\nn\modules\block.py", line 1544, in safe_fusion return ChannelAttentionFusion()(x1, x2) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\LBY\envs\yolov12\Lib\site-packages\torch\nn\modules\module.py", line 1553, in _wrapped_call_impl return self._call_impl(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\LBY\envs\yolov12\Lib\site-packages\torch\nn\modules\module.py", line 1562, in _call_impl return forward_call(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Sogou\yolov12-main\ultralytics\nn\modules\block.py", line 1453, in forward self.fc2(F.relu(self.fc1(y))) ^^^^^^^^^^^ File "D:\LBY\envs\yolov12\Lib\site-packages\torch\nn\modules\module.py", line 1553, in _wrapped_call_impl return self._call_impl(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\LBY\envs\yolov12\Lib\site-packages\torch\nn\modules\module.py", line 1562, in _call_impl return forward_call(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\LBY\envs\yolov12\Lib\site-packages\torch\nn\modules\linear.py", line 117, in forward return F.linear(input, self.weight, self.bias) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cpu and cuda:0! (when checking argument for argument mat1 in method wrapper_CUDA_addmm)
最新发布
07-19
评论 7
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值