Skip to content

mit-han-lab/temporal-shift-module

View on GitHub ↗Related repositories →

[ICCV 2019] TSM: Temporal Shift Module for Efficient Video Understanding

active 2023-08-152026-05-22 (UTC)

Complete coverage26,519 / 26,519 hourly files (100%) · 2 absent upstream2023-08-152026-08-23 (UTC)
Events
318
Pushes
3
Pull requests
0
Issues
5
Stars
274
Forks
23

Activity over time

Daily event counts in the loaded window

Line chart, 1012 days from 2023-08-15 to 2026-05-22. Pushes: 3 total, peak 2 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 5 total, peak 1 in a day. Comments: 13 total, peak 2 in a day. Stars: 274 total, peak 4 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#211mohsin-672025-02-25 12:22
    the pretrained of TSM MobileNetV2
  • Issue comment#11anuj0182024-10-15 13:23
    Training script for online TSM
  • Issue comment#66anuj0182024-10-14 16:45
    I trained a model myself. How do I test it online in real time
  • Issue#235anuj0182024-10-14 08:10
    view size is not compatible with input tensor's size and stride (at least one dimension spans across two contiguous subspaces).
  • Issue comment#34shukurullo20042024-08-28 01:37
    Question about finetune on UCF101
  • Issue comment#136shukurullo20042024-08-28 00:56
    where can I find the 'kinetics_val.csv', 'kinetics_train.csv'
  • Issue comment#66kevio332024-06-05 13:09
    I trained a model myself. How do I test it online in real time
  • Issue#234SlowMonk2024-05-14 02:32
    TypeError: 'IntImm' object cannot be interpreted as an integer
  • Issue#233Eurususu2024-02-06 10:05
    How to train pretrain model with Kinetics dataset? About choosing parameters
  • Issue comment#103Maxwell2016LeChouchou2024-01-26 09:44
    Convert TSM pytorch model to onnx
  • Issue comment#168abdulhai12342023-12-28 04:57
    how to train on ucf101 from scratch?
  • Issue comment#77WANGCHAO19962023-12-13 06:45
    Does this pytorch model support TensorRT acceleration?
  • Issue comment#103WANGCHAO19962023-12-13 06:39
    Convert TSM pytorch model to onnx
  • Issue#232Changwei-Ouyang2023-11-18 17:41
    Which parameter in the code corresponds to the channel shift ratio? Is it 'shift_div'?
  • Issue comment#137ahamid1232023-10-30 12:55
    Temporal shifts at multiple blocks / video object detection
  • Issue#231tonylins2023-10-03 15:15
    TSM model checkpoint download links not working
  • Issue comment#231jokingww2023-10-03 08:25
    TSM model checkpoint download links not working
  • Issue comment#192momohuangsha2023-08-17 02:43
    how to train the online model

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 274 stars here means stars gained during the window, not the repo's star count.