Skip to content

[CVPR 2024] Deformable Convolution v4

Python · active 2024-09-112026-05-16 (UTC)

Partial coverage13,996 / 16,789 hourly files (83%) · 2 absent upstream · 2,792 failed, retryable2024-09-102026-08-11 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
186
Pushes
0
Pull requests
0
Issues
23
Stars
124
Forks
8

Activity over time

Daily event counts in the loaded window

Line chart, 613 days from 2024-09-11 to 2026-05-16. Pushes: 0 total, peak 0 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 23 total, peak 2 in a day. Comments: 31 total, peak 3 in a day. Stars: 124 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#105LeoAkun2026-05-16 05:41
    DCNV4+YOLO loss中出现了nan
  • Issue comment#87zhihuizhege2025-11-05 10:31
    after aligned d_stride :::get error ::::RuntimeError: CUDA error: an illegal memory access was encountered
  • Issue#105gxy33662025-10-27 00:56
    DCNV4+YOLO loss中出现了nan
  • Issue comment#25Oxygen-ops2025-10-15 08:24
    dcnv4替换普通卷积报错
  • Issue comment#100gtebbutt2025-08-11 20:50
    dcnv4 can't run on cuda1!!!!!!
  • Issue comment#101xinjia-chen2025-08-11 06:24
    No module named 'DCNv4'
  • Issue#103liuyun2025-netizen2025-08-03 14:38
    DCNv4.forward() takes 2 to 3 arguments, the function of self.dcn' argment count is 4
  • Issue comment#6614241831952025-07-02 09:23
    Error
  • Issue comment#90xiyunqiao2025-07-01 12:29
    报错output = ext.dcnv4_forward(*args) ValueError: invalid kernel shape
  • Issue#102GunpowderGuy2025-06-29 23:26
    DCNv4 installation fails
  • Issue comment#85achel-x2025-05-17 13:25
    Question about usage
  • Issue#85achel-x2025-05-17 13:25
    Question about usage
  • Issue comment#58wenhaoli-xmu2025-05-17 13:12
    能否出一个3d的?
  • Issue comment#85wenhaoli-xmu2025-05-17 12:20
    Question about usage
  • Issue comment#35Byte2472025-03-30 20:18
    Encountered with Nan loss when training classification task
  • Issue#100alioth-k2025-03-20 03:05
    can't run your code on cuda1!!!!!!
  • Issue#992463450186Q2025-03-01 16:14
    RuntimeError: channels == (group * group_channels) INTERNAL ASSERT FAILED at "/tmp/pip-req-build-yx744y8g/src/cuda/dcnv3_cuda.cu":50, please report a bug to PyTorch. Input channels and group times group channels wont match: (%d vs %d).6081
  • Issue#992463450186Q2025-02-28 06:15
    RuntimeError: channels == (group * group_channels) INTERNAL ASSERT FAILED at "/tmp/pip-req-build-yx744y8g/src/cuda/dcnv3_cuda.cu":50, please report a bug to PyTorch. Input channels and group times group channels wont match: (%d vs %d).6081
  • Issue comment#96xianbeisukisu2025-01-19 15:38
    Compilation failure? fatal error: cuda/dcnv4_cuda.h: 没有那个文件或目录
  • Issue#98BroenLin2025-01-16 07:46
    DCNv4 参数含义
  • Issue#97123456com12025-01-16 03:04
    error AssertionErrorHow can I solve it?
  • Issue#96beiwei-chen2025-01-14 03:04
    Compilation failure? fatal error: cuda/dcnv4_cuda.h: 没有那个文件或目录
  • Issue comment#58destoryD2025-01-06 07:22
    能否出一个3d的?
  • Issue comment#88xiaotong11182024-12-24 09:19
    RuntimeError: Unrecognized tensor type ID: AutocastCUDA
  • Issue#94yellowaug2024-12-21 07:37
    CNv4-1.0.0.post2-py3.10-linux-x86_64.egg/DCNv4/ext.cpython-310-x86_64-linux-gnu.so: undefined symbol: _ZNSt15__exception_ptr13exception_ptr10_M_releaseEv

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 124 stars here means stars gained during the window, not the repo's star count.