This is the official PyTorch implementation of the paper "TransFG: A Transformer Architecture for Fine-grained Recognition" (Ju He, Jie-Neng Chen, Shuai Liu, Adam Kortylewski, Cheng Yang, Yutong Bai, Changhu Wang, Alan Yuille).
active 2023-08-15 → 2026-04-06 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 966 days from 2023-08-15 to 2026-04-06. Pushes: 0 total, peak 0 in a day. Pull requests: 1 total, peak 1 in a day. Issues: 5 total, peak 1 in a day. Comments: 8 total, peak 1 in a day. Stars: 57 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
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| ylshxi | 4 | 0 | 0 | 4 |
| CharlesChen24 | 2 | 0 | 0 | 1 |
| Jing--Li | 1 | 0 | 0 | 1 |
| Yhc-777 | 1 | 0 | 0 | 1 |
| SylU0 | 1 | 0 | 0 | 0 |
| DaGuangDaGuang | 1 | 0 | 0 | 0 |
| zerooooone | 1 | 0 | 0 | 0 |
| ngthanhtin | 1 | 0 | 0 | 1 |
| Lishxiian1003 | 1 | 0 | 0 | 0 |
| SatoshiYamazaki | 1 | 0 | 1 | 0 |
Recent activity
Latest issues, pull requests and releases
- Pull request#38SatoshiYamazaki2026-01-19 10:50
- Issue#37SylU02024-06-18 02:02About PSM module
- Issue#36DaGuangDaGuang2024-05-26 14:18dataset help
- Issue#35Lishxiian10032024-05-14 02:41About valid accuracy
- Issue comment#10ylshxi2024-05-05 07:58About running on one GPU
- Issue comment#10Yhc-7772024-04-24 01:37About running on one GPU
- Issue comment#10ylshxi2024-04-23 04:25About running on one GPU
- Issue comment#10ylshxi2024-04-20 04:22About running on one GPU
- Issue comment#32ylshxi2024-04-09 01:26How to pretrain TransFG on my own dataset
- Issue#33zerooooone2024-01-23 04:04about Part Selection Module
- Issue comment#29CharlesChen242023-11-25 04:28Would you like to open source the implementation based on [DeiT] pretrained on ImageNet-1K with distillation fine-tuning.
- Issue#32CharlesChen242023-11-25 04:00How to pretrain
- Issue comment#28Jing--Li2023-10-11 05:07About trainint details
- Issue comment#20ngthanhtin2023-08-15 19:00Normalization parameters
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 57 stars here means stars gained during the window, not the repo's star count.