Skip to content
This repository was archived by the owner on Jun 10, 2024. It is now read-only.
This repository was archived by the owner on Jun 10, 2024. It is now read-only.

pytorch tensor and inference #389

Closed
Closed
pytorch tensor and inference#389
Assignees
contentis
Labels
questionFurther information is requestedwipWork in Progress

Description

@swkms
swkms
opened on Nov 11, 2022

Hello, I use VPF decoding and yolo model, nv12 ->yuv420 ->rgb24 ->rgb24Planar ->python tensor ->"run_inference" in the example. Can I use rgb24Planar to give self. bindings [0] without converting to python tensor

Activity

  1. gedoensmax
    assigned
    contentis
    on Nov 21, 2022
  2. gedoensmax
    added
    wipWork in Progress
    questionFurther information is requested
    on Nov 21, 2022

  3. contentis commented on Nov 21, 2022

    @contentis
    contentis
    on Nov 21, 2022
    Collaborator

    If you want to use the python interface, you need to use the tensor conversion as the binding is a raw byte stream that needs to be interpreted. This should not add any overhead and therefore is not an issue.

  4. gedoensmax
    closed this as completedon Dec 6, 2022
  5. NVIDIA
    locked and limited conversation to collaborators on Dec 6, 2022
  6. gedoensmax
    converted this issue into a discussion #398 on Dec 6, 2022
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

Labels

questionFurther information is requestedwipWork in Progress

Type

No type

Projects

No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions