Skip to content

A copy from Sparse4D official

active 2025-02-092026-06-27 (UTC)

Partial coverage11,806 / 13,156 hourly files (90%) · 2 absent upstream · 1,346 failed, retryable2025-02-082026-08-10 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
159
Pushes
0
Pull requests
1
Issues
8
Stars
115
Forks
19

Activity over time

Daily event counts in the loaded window

Line chart, 504 days from 2025-02-09 to 2026-06-27. Pushes: 0 total, peak 0 in a day. Pull requests: 1 total, peak 1 in a day. Issues: 8 total, peak 1 in a day. Comments: 16 total, peak 2 in a day. Stars: 115 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#86gliangMT2025-11-26 09:31
    尝试复现训练和评测的时候报错
  • Issue comment#975040585682025-11-18 02:58
    转ONNX
  • Issue comment#115hangzheng-yu2025-09-02 09:02
    分布式训练时sequences_split_num的设置问题
  • Issue comment#124CrawlingD2025-08-07 05:34
    How are future frames used?
  • Issue comment#126SophieZhou2025-07-29 07:02
    时序anchor变化问题
  • Issue comment#132nschi002025-07-24 20:04
    是否训练数据需要LIDAR数据辅助深度监督?
  • Issue comment#131dof-pikes2025-07-23 09:46
    [BUG] Quality的loss写反了?还是有什么特别的考虑?
  • Issue#132zhaoyiming2025-07-09 15:15
    是否训练数据需要LIDAR数据辅助深度监督?
  • Issue#131tianws2025-07-03 02:52
    [BUG] Quality的loss写反了?还是有什么特别的考虑?
  • Pull request#130binding70122025-06-27 09:42
  • Issue#129fengguibinyn2025-06-25 04:04
    关于temp_instance_feature更新问题
  • Issue comment#125SunKaiQing-utky2025-06-03 14:35
    Reproducibility of the ResNet101 Model
  • Issue#127shihaimingtian2025-05-30 01:32
    why set feat_grad=False?时序模型的intance feature为啥设置为不可学习的,feat_grad=False, 设置为true好像id分配得不太对,这是为什么?
  • Issue comment#18sihuaiwei2025-05-28 08:32
    Res101 nuImage config ,please ?
  • Issue#120liao1fan2025-05-03 07:09
    About Instance Bank Cache
  • Issue comment#75APiaoBoDeYu2025-04-30 03:34
    Training baseline model doesn't converge
  • Issue#86WuYiYiYi2025-04-21 03:26
    尝试复现训练和评测的时候报错
  • Issue comment#73zy-Chen992025-04-19 04:43
    run local_test.sh "slow_conv2d_cpu" not implemented for 'Half'
  • Issue comment#119yushengjiexy2025-03-28 02:09
    hi,我是否可以用它车想对自车的运动速度来训练模型,效果怎么样
  • Issue#119yushengjiexy2025-03-11 02:13
    hi,我是否可以用它车想对自车的运动速度来训练模型,效果怎么样
  • Issue comment#90yushengjiexy2025-02-22 12:26
    这是个bug嘛?
  • Issue#115dlwsds2025-02-16 12:26
    分布式训练时sequences_split_num的设置问题
  • Issue comment#109dlwsds2025-02-15 11:58
    Training with smaller batch size or lesser gpus
  • Issue comment#109Eashwar932025-02-15 05:59
    Training with smaller batch size or lesser gpus
  • Issue comment#109ChiShao2025-02-14 22:34
    Training with smaller batch size or lesser gpus

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 115 stars here means stars gained during the window, not the repo's star count.