lightning $A 使用

1、跳转页面 延迟刷新

var toSobject = $A.get("e.force:navigateToSObject");
toSobject.setParams({
    "recordId": result.recordId,
   "slideDevName" : 'detail'
});
window.setTimeout(function(){        
     $A.get('e.force:refreshView').fire();
},10);
toSobject.fire();

2、弹窗

$A.get("e.force:showToast").setParams({
       message: $A.get("$Label.c.SavedSuccess"),
       type: "success"
   }).fire();

3、页面取消

//取消
handleCancel : function(component, event, helper){
   var recordId = component.get("v.recordId");
   if(!$A.util.isUndefinedOrNull(recordId)){
      $A.get("e.force:navigateToSObject").setParams({
         "recordId" : recordId
      }).fire();
    }else{
       window.history.back();
    }
 },

4、lightning开发–获取当前登录用户


```javascript
$A.get("$SObjectType.CurrentUser.Id")

  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
# As an AI language model, I cannot provide a personal experience with PyTorch Lightning, but I can provide information and examples on how to use it. PyTorch Lightning is a lightweight PyTorch wrapper for high-performance AI research. It allows researchers and practitioners to focus on the core research problem by abstracting the engineering details. PyTorch Lightning provides a high-level interface for building complex deep learning models and training pipelines. It also simplifies the process of scaling models to multiple GPUs or TPUs. Here is an example of how to use PyTorch Lightning to train a simple neural network for image classification: ```python import torch import torch.nn as nn import torch.optim as optim from torch.utils.data import DataLoader from torchvision.datasets import MNIST from torchvision.transforms import ToTensor import pytorch_lightning as pl class Net(nn.Module): def __init__(self): super(Net, self).__init__() self.conv1 = nn.Conv2d(1, 32, 3, 1) self.conv2 = nn.Conv2d(32, 64, 3, 1) self.dropout1 = nn.Dropout2d(0.25) self.dropout2 = nn.Dropout2d(0.5) self.fc1 = nn.Linear(9216, 128) self.fc2 = nn.Linear(128, 10) def forward(self, x): x = self.conv1(x) x = nn.ReLU()(x) x = self.conv2(x) x = nn.ReLU()(x) x = nn.MaxPool2d(2)(x) x = self.dropout1(x) x = torch.flatten(x, 1) x = self.fc1(x) x = nn.ReLU()(x) x = self.dropout2(x) x = self.fc2(x) output = nn.LogSoftmax(dim=1)(x) return output class LitMNIST(pl.LightningModule): def __init__(self): super().__init__() self.net = Net() def forward(self, x): return self.net(x) def training_step(self, batch, batch_idx): x, y = batch y_hat = self(x) loss = nn.NLLLoss()(y_hat, y) self.log('train_loss', loss) return loss def configure_optimizers(self): optimizer = optim.Adam(self.parameters(), lr=1e-3) return optimizer train_data = MNIST('.', train=True, download=True, transform=ToTensor()) train_loader = DataLoader(train_data, batch_size=64) trainer = pl.Trainer(gpus=1, max_epochs=10) model = LitMNIST() trainer.fit(model, train_loader) ``` In this example, we define a simple neural network for image classification using PyTorch. We then wrap the model in a PyTorch Lightning module, which provides hooks for training and validation steps. We define a training step that calculates the loss and logs it to the PyTorch Lightning log, and we configure the optimizer to use the Adam optimizer. Finally, we create a PyTorch DataLoader for the MNIST dataset, create a PyTorch Lightning trainer with one GPU, and fit the model to the training data for 10 epochs. Overall, PyTorch Lightning simplifies the process of training deep learning models while still allowing for flexibility and customization.

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
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