Skip to content

RelTR: Relation Transformer for Scene Graph Generation: https://arxiv.org/abs/2201.11460v2

active 2023-08-202025-12-31 (UTC)

Complete coverage26,687 / 26,687 hourly files (100%) · 2 absent upstream2023-08-152026-08-30 (UTC)
Events
346
Pushes
0
Pull requests
3
Issues
57
Stars
160
Forks
31

Activity over time

Daily event counts in the loaded window

Line chart, 865 days from 2023-08-20 to 2025-12-31. Pushes: 0 total, peak 0 in a day. Pull requests: 3 total, peak 2 in a day. Issues: 57 total, peak 5 in a day. Comments: 95 total, peak 6 in a day. Stars: 160 total, peak 3 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

Recent activity

Latest issues, pull requests and releases

  • Issue comment#41hadespiration2025-11-12 07:55
    name 'train_stats' is not defined
  • Issue comment#41hadespiration2025-11-12 07:49
    name 'train_stats' is not defined
  • Issue#71filizipek2025-08-22 11:27
    The Checkpoint URL Not Found
  • Issue#70xfufu07242025-08-12 03:07
    关于oi数据集的处理问题
  • Issue#69IceIce1ce2025-08-09 09:29
    Cannot run with pytorch 1.13.1 and cuda 11.7
  • Issue comment#50IceIce1ce2025-08-09 09:21
    When I was training data, I encountered an error
  • Issue comment#39Syh0029252025-07-21 14:32
    RuntimeError: CUDA error: device-side assert triggered CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1. Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.
  • Issue#68zhuhl09132025-04-25 06:42
    Inference Speed
  • Issue comment#67carloscaetano2025-02-26 17:39
    adding CPU device when loading the model
  • Pull request#67carloscaetano2025-02-26 17:39
  • Pull request#67carloscaetano2025-02-26 17:25
  • Issue#66cloudpetticoats2025-02-19 01:13
    Image restoration
  • Issue#65cloudpetticoats2025-02-19 00:43
    demo problem
  • Issue comment#65cloudpetticoats2025-02-19 00:43
    demo problem
  • Issue comment#65yrcong2025-02-18 16:45
    demo problem
  • Issue comment#39AlphaGoooo2025-02-14 11:41
    RuntimeError: CUDA error: device-side assert triggered CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1. Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.
  • Issue comment#39ZHUXUHAN2025-01-20 15:57
    RuntimeError: CUDA error: device-side assert triggered CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1. Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.
  • Issue comment#14trangiahuy84442025-01-09 16:12
    Train and Test for custom images
  • Issue comment#32iamagoodboyyeyeye2024-10-21 08:12
    Model not getting trained on single GPU
  • Issue comment#32A11en4z2024-10-21 08:03
    Model not getting trained on single GPU
  • Issue comment#32A11en4z2024-10-21 08:02
    Model not getting trained on single GPU
  • Issue comment#32iamagoodboyyeyeye2024-10-21 08:01
    Model not getting trained on single GPU
  • Issue comment#32iamagoodboyyeyeye2024-10-21 07:55
    Model not getting trained on single GPU
  • Issue comment#44iamagoodboyyeyeye2024-10-21 07:16
    Evaluation
  • Issue#64wuzhiwei20012024-09-16 14:01
    PredCLS and SGCLS

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 160 stars here means stars gained during the window, not the repo's star count.