如何解压缩原始形状的张量(反向视图)?

时间:2018-06-22 20:34:23

标签: python neural-network pytorch

我有以下情况

// Context lets us pass a value deep into the component tree
// without explicitly threading it through every component.
// Create a context for the current style (with "{display:none}" as the default).
const SubComponentStyleContext = React.createContext({display:none});

class App extends React.Component {
  render() {
    // Use a Provider to pass the current style to the tree below.
    // Any component can read it, no matter how deep it is.
    // In this example, we're passing "{display:block}" as the current value.
    return (
      <SubComponentStyleContext.Provider value={{display:block}}>
        <MainComponent />
      </SubComponentStyleContext.Provider>
    );
  }
}

// A component in the middle doesn't have to
// pass the style down explicitly anymore.
function MainComponent(props) {
  return (
    <div>
      <SubComponent />
    </div>
  );
}

function SubComponent(props) {
  // Use a Consumer to read the current style context.
  // React will find the closest theme Provider above and use its value.
  // In this example, the current style is "{display:block}".
  return (
    <SubComponentStyleContext.Consumer>
      {style => /*use style here as you want*/}
    </SubComponentStyleContext.Consumer>
  );
}

我需要从[1022,40993]中获取,以保留顺序来获取[2,511,40993]。

0 个答案:

没有答案