google-cloud-platform - 在已安装 pytorch 和 Cuda10 的 Google Cloud Vm 中没有明显的 GPU 使用情况

Question

我一直在我的机器上使用一个网络，这没什么特别的。我想做得更快，所以我开始使用谷歌云。但我注意到一些奇怪的事情，我的 GTX 1050 ti 机器比 V100 GPU 快。这没有加起来，所以我检查了使用情况，似乎即使我通过在模型和数据：nvidia-smi 命令中没有显示用法，如图所示，您可以在此处查看我的代码：

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
    print("The device is:",device,torch.cuda.get_device_name(0),"and how many are they",torch.cuda.device_count())

    # # We load the training data 
    Samples , Ocupancy, num_samples, Samples_per_slice = common.load_samples(args.samples_filename)
    Samples = Samples * args.scaling_todo

    print(Samples_per_slice)
    # Divide into Slices
    Organize_Positions,Orginezed_Ocupancy, batch_size = common.organize_sample_data(Samples,Ocupancy,num_samples,Samples_per_slice,args.num_batches)

    phi = common.MLP(3, 1).cuda()

    x_test = torch.from_numpy(Organize_Positions.astype(np.float32)).cuda()
    y_test = torch.from_numpy(Orginezed_Ocupancy.astype(np.float32)).cuda()

    all_data = common.CustomDataset(x_test, y_test)


    #Dive into Slices the data
    Slice_data = DataLoader(dataset=all_data, batch_size = batch_size, shuffle=False) # only take batch_size = n/b TODO Don't shuffle

    #Chunky_data = DataLoader(dataset=Slice_data, batch_size =  chunch_size, shuffle=False)


    criterion = torch.nn.BCEWithLogitsLoss()
    optimizer = torch.optim.Adam(phi.parameters(), lr = 0.0001)
    epoch = args.num_epochs

    fit_start_time = time.time()

    phi.train()
    for epoch in range(epoch):
        curr_epoch_loss = 0
        batch = 0
        for x_batch, y_batch in Slice_data:
            optimizer.zero_grad()
            x_train = x_batch
            #print(x_train,batch_size)
            y_train = y_batch

            y_pred = phi(x_train)
            #print(y_pred,x_train)

            loss = criterion(y_pred.squeeze(), y_train.squeeze())

            curr_epoch_loss += loss

            print('Batch {}: train loss: {}'.format(batch, loss.item()))    # Backward pass

            loss.backward()
            optimizer.step() # Optimizes only phi parameters
            batch+=1


        print('Epoch {}: train loss: {}'.format(epoch, loss.item()))


    fit_end_time = time.time()
    print("Total time = %f" % (fit_end_time - fit_start_time))

    # Save Model
    torch.save({'state_dict': phi.state_dict()}, args.model_filename)

和这里的模型：

class MLP(nn.Module):
    def __init__(self, in_dim: int, out_dim: int):
        super().__init__()
        self.in_dim = in_dim
        self.out_dim = out_dim
        self.fc1 = nn.Linear(in_dim, 128)
        self.fc1_bn = nn.BatchNorm1d(128)
        self.fc2 = nn.Linear(128, 256)
        self.fc2_bn = nn.BatchNorm1d(256)
        self.fc3 = nn.Linear(256, 512)
        self.fc3_bn = nn.BatchNorm1d(512)
        self.fc4 = nn.Linear(512, 512)
        self.fc4_bn = nn.BatchNorm1d(512)
        self.fc5 = nn.Linear(512, out_dim,bias=False)

        self.relu = nn.LeakyReLU()


    def forward(self, x):
        x = self.relu(self.fc1_bn(self.fc1(x)))
        x = self.relu(self.fc2_bn(self.fc2(x)))# leaky
        x = self.relu(self.fc3_bn(self.fc3(x)))
        x = self.relu(self.fc4_bn(self.fc4(x)))
        x = self.fc5(x)
        return x

class CustomDataset(Dataset):
    def __init__(self, x_tensor, y_tensor):
        self.x = x_tensor
        self.y = y_tensor

    def __getitem__(self, index):
        return (self.x[index], self.y[index])

    def __len__(self):
        return len(self.x)

标签： google-cloud-platformgpupytorch