利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

265 条记录 (耗时 0.018 秒)

    IMAGE TRANSFORMATION FOR MACHINE LEARNING
    1.
    发明公开
    IMAGE TRANSFORMATION FOR MACHINE LEARNING 审中-公开

    公开(公告)号：EP4254313A3

    公开(公告)日：2023-12-20

    申请号：EP23187356.3

    申请日：2019-01-30

    申请人： Google LLC

    发明人： KILLEBREW, Carrell Daniel ,  NARAYANASWAMI, Ravi ,  WOO, Dong Hyuk

    IPC分类号： G06T1/60

    摘要： Methods, systems, and apparatus, including an apparatus for determining pixel coordinates for image transformation and memory addresses for storing the transformed image data. In some implementations, a system includes a processing unit configured to perform machine learning computations for images using a machine learning model and pixel values for the images, a storage medium configured to store the pixel values, and a memory address computation unit that includes one or more hardware processors. The processors are configured to receive image data for an image and determine that the dimensions of the image do not match the dimensions of the machine learning model. In response, the processors determine pixel coordinates for a transformed version of the image and, for each of the pixel coordinates, memory address(es), in the storage medium, for storing pixel value(s) that will be used to generate an input to the machine learning model.

    IMAGE TRANSFORMATION FOR MACHINE LEARNING
    5.
    发明公开
    IMAGE TRANSFORMATION FOR MACHINE LEARNING 审中-公开

    公开(公告)号：EP4254313A2

    公开(公告)日：2023-10-04

    申请号：EP23187356.3

    申请日：2019-01-30

    申请人： Google LLC

    发明人： The designation of the inventor has not yet been filed

    IPC分类号： G06T1/60

    摘要： Methods, systems, and apparatus, including an apparatus for determining pixel coordinates for image transformation and memory addresses for storing the transformed image data. In some implementations, a system includes a processing unit configured to perform machine learning computations for images using a machine learning model and pixel values for the images, a storage medium configured to store the pixel values, and a memory address computation unit that includes one or more hardware processors. The processors are configured to receive image data for an image and determine that the dimensions of the image do not match the dimensions of the machine learning model. In response, the processors determine pixel coordinates for a transformed version of the image and, for each of the pixel coordinates, memory address(es), in the storage medium, for storing pixel value(s) that will be used to generate an input to the machine learning model.