Code for Finetune like you pretrain: Improved finetuning of zero-shot vision models
active 2023-08-15 → 2026-03-22 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 951 days from 2023-08-15 to 2026-03-22. Pushes: 0 total, peak 0 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 23 total, peak 4 in a day. Comments: 26 total, peak 3 in a day. Stars: 52 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 |
|---|---|---|---|---|
| SachinG007 | 20 | 0 | 0 | 13 |
| ugsup | 4 | 0 | 0 | 2 |
| tjddus9597 | 4 | 0 | 0 | 3 |
| ChChCh8 | 3 | 0 | 0 | 1 |
| ChoiDae1 | 3 | 0 | 0 | 1 |
| Bala93 | 3 | 0 | 0 | 2 |
| sanyalsunny111 | 2 | 0 | 0 | 1 |
| VLadImirluren | 2 | 0 | 0 | 1 |
| LixDemon | 1 | 0 | 0 | 0 |
| ma-kjh | 1 | 0 | 0 | 0 |
| sinahmr | 1 | 0 | 0 | 0 |
| doubleplusplus | 1 | 0 | 0 | 0 |
| wendioooo | 1 | 0 | 0 | 1 |
| ShuangjunLi | 1 | 0 | 0 | 0 |
| anhquancao | 1 | 0 | 0 | 1 |
| linhuibin | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue#25linhuibin2025-03-03 14:14--model=ViT-B/16 instead of ViT-B-16?
- Issue comment#24sanyalsunny1112025-02-28 06:54Trying to reproduce Table 4
- Issue comment#24SachinG0072025-01-23 04:48Trying to reproduce Table 4
- Issue#24sanyalsunny1112024-12-22 17:14Trying to reproduce Table 4
- Issue#23ShuangjunLi2024-07-16 09:29Checkpoints
- Issue comment#15tjddus95972024-05-03 11:56Bad performance on ImageNet variants
- Issue comment#15SachinG0072024-04-03 17:36Bad performance on ImageNet variants
- Issue#18SachinG0072024-03-25 22:45ValueError in fmow_csv_creator.py
- Issue#22SachinG0072024-03-25 22:44How can split ImageNet dataset into train and validation set ?
- Issue comment#1anhquancao2024-03-12 16:19How to implement cross entropy loss and class collisions removal?
- Issue comment#22SachinG0072024-03-11 18:29How can split ImageNet dataset into train and validation set ?
- Issue#22ma-kjh2024-03-11 07:34How can split ImageNet dataset into train and validation set ?
- Issue comment#16ugsup2024-02-01 20:41How to load created checkpoints?
- Issue comment#16ugsup2024-02-01 20:33How to load created checkpoints?
- Issue comment#16wendioooo2024-02-01 20:10How to load created checkpoints?
- Issue#19SachinG0072023-11-02 12:16How to apply FLYP on custom dataset?
- Issue#20SachinG0072023-11-02 12:16ImageNet few-shot experiments
- Issue comment#21ChChCh82023-11-02 05:03ImageNet few shot experiment
- Issue#21ChChCh82023-11-02 05:03ImageNet few shot experiment
- Issue comment#21SachinG0072023-11-02 04:47ImageNet few shot experiment
- Issue#21ChChCh82023-11-02 00:41ImageNet few shot experiment
- Issue comment#19SachinG0072023-10-30 02:28How to apply FLYP on custom dataset?
- Issue comment#20SachinG0072023-10-27 22:06ImageNet few-shot experiments
- Issue comment#15tjddus95972023-10-27 14:47Bad performance on ImageNet variants
- Issue#20sinahmr2023-10-27 05:23ImageNet few-shot experiments
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 52 stars here means stars gained during the window, not the repo's star count.