利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

858 条记录 (耗时 0.023 秒)

    MACHINE-LEARNING FOR CAD MODEL RETRIEVAL
    2.
    发明公开
    MACHINE-LEARNING FOR CAD MODEL RETRIEVAL 审中-公开

    公开(公告)号：EP4459496A1

    公开(公告)日：2024-11-06

    申请号：EP23315150.5

    申请日：2023-05-02

    申请人： Dassault Systèmes

    发明人： MAILLARD, Léopold ,  BOUCHER, Julien

    IPC分类号： G06F30/17 ,  G06N20/00 ,  G06F16/00 ,  G06F30/27 ,  G06N3/045

    摘要： The disclosure notably relates to computer-implemented method of machinelearning for CAD model retrieval based on a mating score. The method comprises providing a dataset of pairs of Boundary Representations (B-Reps) representing mechanical parts, each pair being labeled with mating compatibility data, the mating compatibility data representing an extent of mating compatibility between the mechanical parts represented by the pair. The method also comprises training a neural network based on the dataset, the neural network being configured for taking as input a pair of B-reps representing mechanical parts, and outputting a mating score of a pair of single embeddings, each single embedding corresponding to a B-Rep of the pair, the mating score representing a score of mating compatibility between the mechanical parts represented by the pair.

    DEEP LEARNING MODEL INFERENCE FOR DYNAMIC INPUT SHAPES
    7.
    发明公开
    DEEP LEARNING MODEL INFERENCE FOR DYNAMIC INPUT SHAPES 审中-公开

    公开(公告)号：EP4455862A1

    公开(公告)日：2024-10-30

    申请号：EP24164533.2

    申请日：2024-03-19

    申请人： Mediatek Inc.

    发明人： YANG, Meng-Hsuan ,  HUANG, Po-hua ,  CHOU, Hsing-Chang ,  TSAN, Ting-Chen ,  LU, Yu-Lung

    IPC分类号： G06F8/41 ,  G06N3/045

    摘要： A method of compiling a deep learning model includes reading metadata from a compiled result (S620), the metadata indicating a structure of the deep learning model corresponding to a low-level IR, receiving shape information of an input tensor of the deep learning model, determining a shape of an output tensor of a first computation operation of the computation operations based on the shape information of the input tensor of the deep learning model and the structure of the deep learning model (S630), tiling the output tensor of the first computation operation into one or more tiles according to the shape of the output tensor of the first computation operation and hardware limitations of a processor executing the deep learning model (S640), and patching one or more copies of a templated hardware command into executable hardware commands (5660).