# Running a script on a GPU

**URL:** <https://discuss.pytorch.org/t/running-a-script-on-a-gpu/27887>\
**Category:** Uncategorized\
**Created:** [October 23, 2018, 10:21pm UTC](https://discuss.pytorch.org/t/running-a-script-on-a-gpu/27887 "2018-10-23T22:21:41Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![hosseinshn](https://discuss.pytorch.org/letter_avatar_proxy/v4/letter/h/9e8a1a/32.png) [@hosseinshn](https://discuss.pytorch.org/u/hosseinshn)\
**Post date:** [October 23, 2018, 10:21pm UTC](https://discuss.pytorch.org/t/running-a-script-on-a-gpu/27887/1 "2018-10-23T22:21:41Z")

</div>

Hi, I am trying to run my script on GPU but I am getting an error.  
The data loading part goes like:

```auto
class_sample_count = np.array([len(np.where(y_train==t)[0]) for t in np.unique(y_train)])
weight = 1. / class_sample_count
samples_weight = np.array([weight[t] for t in y_train])
samples_weight = torch.from_numpy(samples_weight)
sampler = WeightedRandomSampler(samples_weight.type('torch.cuda.DoubleTensor'), len(samples_weight), replacement=True)

trainDataset = torch.utils.data.TensorDataset(torch.cuda.FloatTensor(X_train), torch.cuda.FloatTensor(y_train.astype(int)))
trainLoader = torch.utils.data.DataLoader(dataset = trainDataset, batch_size=mb_size, shuffle=False, num_workers=1, sampler = sampler)

```

My model object is like:

```auto

    class AEE(nn.Module):
        def __init__ (self):
            super(AEE, self). __init__ ()
            self.EnE = torch.nn.Sequential(
                nn.Linear(IE_dim, h_dim),
                nn.BatchNorm1d(h_dim),
                nn.ReLU(),
                nn.Dropout(),
                nn.Linear(h_dim, Z_dim),
                nn.Sigmoid(),
                #nn.BatchNorm1d(Z_dim))
            )
        def forward(self, x):
            output = self.EnE(x)
            return output
model= AEE()
model.cuda()

```

I am getting this error in the for loop on my trainloader:

```auto
RuntimeError: CUDA error (3): initialization error

```

Any ideas?