Skip to content

  • Projects
  • Groups
  • Snippets
  • Help
  • This project
    • Loading...
  • Sign in / Register
D
DASTM
  • Project
    • Project
    • Details
    • Activity
    • Cycle Analytics
  • Repository
    • Repository
    • Files
    • Commits
    • Branches
    • Tags
    • Contributors
    • Graph
    • Compare
    • Charts
  • Issues 3
    • Issues 3
    • List
    • Board
    • Labels
    • Milestones
  • Merge Requests 0
    • Merge Requests 0
  • CI / CD
    • CI / CD
    • Pipelines
    • Jobs
    • Schedules
    • Charts
  • Wiki
    • Wiki
  • Snippets
    • Snippets
  • Members
    • Members
  • Collapse sidebar
  • Activity
  • Graph
  • Charts
  • Create a new issue
  • Jobs
  • Commits
  • Issue Boards
  • 马宁(18博)
  • DASTM
  • Issues
  • #7

Closed
Open
Opened Jun 12, 2023 by 马宁(18博)@maning 
  • Report abuse
  • New issue
Report abuse New issue

What do I have to do if I want to train "5-way-5-shot"

Created by: Lululu100

Your work is excellent! If I want to train "5-way-5-shot", what should I do? I refer to the parameter setting of "5-way-1-shot" and set parameter backbones use STGCN, data use NTU-T, SA=1, reg=0.1, num_support_tr=5, num_support_val=5. The accuracy(test acc: 0.8649239775717259) is very different from the accuracy reported in the paper. May I ask if you have encountered similar situations in the training process. Looking forward to your reply.

Assignee
Assign to
None
Milestone
None
Assign milestone
Time tracking
None
Due date
No due date
0
Labels
None
Assign labels
  • View project labels
Reference: maning/DASTM#7