METHOD AND SYSTEM WITH DEEP LEARNING MODEL GENERATION

    公开(公告)号:US20240419970A1

    公开(公告)日:2024-12-19

    申请号:US18816769

    申请日:2024-08-27

    Abstract: Provided is a method and system with deep learning model generation. The method includes identifying a plurality of connections in a neural network that is pre-associated with a deep learning model, generating a plurality of pruned neural networks by pruning different sets of one or more of the plurality of connections to respectively generate each of the plurality of pruned neural networks, generating a plurality of intermediate deep learning models by generating a respective intermediate deep learning model corresponding to each of the plurality of pruned neural networks, and selecting one of the plurality of intermediate deep learning models, having a determined greatest accuracy among the plurality of intermediate deep learning models, to be an optimized deep learning model.

    METHOD AND APPARATUS FOR PERFORMING PATH RENDERING
    7.
    发明申请
    METHOD AND APPARATUS FOR PERFORMING PATH RENDERING 有权
    执行路径渲染的方法和装置

    公开(公告)号:US20170039743A1

    公开(公告)日:2017-02-09

    申请号:US15093491

    申请日:2016-04-07

    CPC classification number: G06T11/40 G06T11/203

    Abstract: A method of performing path rendering includes selecting a tile including a path from tiles in a frame based on tile bin data, splitting the selected tile into a plurality of first sub-tiles, selecting a first sub-tile that does not include the path from the plurality of first sub-tiles, and updating an initial winding number of the selected first sub-tile. The tile bin data includes an initial winding number of each of the tiles in the frame.

    Abstract translation: 执行路径渲染的方法包括:基于瓦片块数据选择包括来自帧中的瓦片的路径的瓦片,将所选择的瓦片分割成多个第一子瓦片,选择不包括从所述路径的路径的第一子瓦片 所述多个第一子瓦片,并且更新所选择的第一子瓦片的初始卷绕编号。 瓦片箱数据包括帧中每个瓦片的初始卷绕数。

Patent Agency Ranking