Skip to content

[CVPR 2024] Official implementation of "DiffCast: A Unified Framework via Residual Diffusion for Precipitation Nowcasting"

active 2024-07-092026-06-16 (UTC)

Partial coverage14,976 / 18,325 hourly files (82%) · 2 absent upstream · 3,348 failed, retryable2024-07-092026-08-11 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
92
Pushes
2
Pull requests
0
Issues
11
Stars
50
Forks
7

Activity over time

Daily event counts in the loaded window

Line chart, 708 days from 2024-07-09 to 2026-06-16. Pushes: 2 total, peak 1 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 11 total, peak 1 in a day. Comments: 22 total, peak 4 in a day. Stars: 50 total, peak 2 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

ContributorContributionsPushesPRsComments
DeminYu9811209
chufall4003
ShileiCao4001
jichongxing20233003
Pipilong-coder2001
earthpimp2001
BlackRab1000
hiuaaa1001
w2obin1001
plaovem1000
qwerttyuiopaz1000
zhangmy1141000
yan16172629651001
ruibing-jin1001
yuanyouke4281000

Recent activity

Latest issues, pull requests and releases

  • Issue#20qwerttyuiopaz2026-01-24 11:41
    您好想问下,上海雷达数据集的h5文件中,每个img的像素点的含义是什么呢,是dBZ吗,还是mm/h啊
  • Issue#19BlackRab2025-12-31 07:34
    How to train the DiffCast?
  • Issue#18yuanyouke4282025-11-15 04:28
    上海雷达验证集是测试集的问题
  • Issue comment#15DeminYu982025-09-18 05:03
    您好,请教一下meteonet中无效值255该如何处理的呢?
  • Issue comment#16DeminYu982025-09-18 05:00
    我想问一下meteonet数据划分中,Tpixel取的是多少,你论文提到的是a mean pixel threshold T pixel,可以告诉一下大概吗
  • Issue comment#17DeminYu982025-09-18 04:52
    Visualisation results on the Shanghai dataset
  • Issue#17Pipilong-coder2025-07-10 02:36
    Visualisation results on the Shanghai dataset
  • Issue comment#16Pipilong-coder2025-07-10 02:13
    我想问一下meteonet数据划分中,Tpixel取的是多少,你论文提到的是a mean pixel threshold T pixel,可以告诉一下大概吗
  • Issue comment#10w2obin2025-01-30 06:31
    Hello, could you please ask how to convert the downloaded cikm, meteonet, and Shanghai datasets into. H5 files? Where can I directly download the. H5 file?
  • Issue comment#13chufall2025-01-09 03:59
    Did the training result correct?
  • Issue comment#13chufall2025-01-08 07:59
    Did the training result correct?
  • Issue#14ShileiCao2025-01-08 06:16
    s
  • Issue comment#13ShileiCao2025-01-07 06:45
    Did the training result correct?
  • Issue#12ShileiCao2025-01-07 06:37
    How to train with multiple Gpus
  • Issue#13chufall2025-01-06 06:40
    Did the training result correct?
  • Issue#12ShileiCao2025-01-01 07:34
    How to train with multiple Gpus
  • Issue comment#4jichongxing20232024-12-29 11:39
    About the loss of image quality after adding diffusion
  • Issue comment#4chufall2024-12-29 03:11
    About the loss of image quality after adding diffusion
  • Issue comment#4jichongxing20232024-11-16 10:29
    About the loss of image quality after adding diffusion
  • Issue comment#11jichongxing20232024-11-16 09:38
    1
  • Issue comment#4yan16172629652024-10-14 04:16
    About the loss of image quality after adding diffusion
  • Issue comment#11hiuaaa2024-09-26 02:29
    1
  • Issue#11zhangmy1142024-09-26 02:18
    1
  • Issue comment#10DeminYu982024-09-08 02:45
    Hello, could you please ask how to convert the downloaded cikm, meteonet, and Shanghai datasets into. H5 files? Where can I directly download the. H5 file?
  • Issue comment#8DeminYu982024-08-24 13:35
    several questions on diffcast code

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 50 stars here means stars gained during the window, not the repo's star count.