pytorch实现对比学习
active 2023-08-15 → 2026-06-28 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 1049 days from 2023-08-15 to 2026-06-28. Pushes: 3 total, peak 1 in a day. Pull requests: 8 total, peak 2 in a day. Issues: 19 total, peak 3 in a day. Comments: 34 total, peak 4 in a day. Stars: 902 total, peak 7 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 |
|---|---|---|---|---|
| HobbitLong | 13 | 3 | 1 | 9 |
| adv010 | 7 | 0 | 0 | 5 |
| NinaLong2077 | 5 | 0 | 4 | 1 |
| srsawant34 | 5 | 0 | 1 | 2 |
| LightingMc | 4 | 0 | 0 | 1 |
| yaoerqin | 3 | 0 | 0 | 3 |
| limengting-evelyn | 2 | 0 | 0 | 0 |
| dvdsosa | 2 | 0 | 0 | 2 |
| dave4422 | 2 | 0 | 0 | 2 |
| NickyTan8899 | 2 | 0 | 0 | 1 |
| tanushreebanerjee | 1 | 0 | 0 | 0 |
| tomer-erez | 1 | 0 | 0 | 0 |
| DruncBread | 1 | 0 | 0 | 1 |
| Wolongchicken | 1 | 0 | 0 | 0 |
| strollingorange | 1 | 0 | 0 | 0 |
| wjj20000619 | 1 | 0 | 0 | 1 |
| Aristo23333 | 1 | 0 | 0 | 1 |
| hweejuni | 1 | 0 | 0 | 0 |
| seanswyi | 1 | 0 | 1 | 0 |
| HYC01 | 1 | 0 | 0 | 1 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#150NickyTan88992025-09-01 11:28Solving Loss Saturation
- Issue#156NickyTan88992025-08-31 07:31is there a version for imbalance dataset?
- Pull request#155hein-nkhh2025-06-11 11:56
- Issue comment#151tian13272025-04-14 06:05Training using Supcon loss is slower than cross_entropy loss
- Issue comment#127lxbstar2025-03-03 14:39Loss function is not convergent when batch-sizes smaller？
- Issue#153tomer-erez2025-01-27 20:13is there an implementation for continuos targets?
- Issue#152Wolongchicken2024-10-08 07:21Is there a method that does not require pre training.
- Issue comment#149HobbitLong2024-09-27 17:06about loss_in and loss_out in paper
- Issue#151yinbing6682024-09-12 06:56Training using Supcon loss is slower than cross_entropy loss
- Issue#150avernal18192024-09-06 04:33Solving Loss Saturation
- Issue comment#146HobbitLong2024-08-23 23:33Code for using the ImageNet pretrained model
- Issue comment#146LightingMc2024-08-23 21:13Code for using the ImageNet pretrained model
- Issue comment#146HobbitLong2024-08-23 20:48Code for using the ImageNet pretrained model
- Issue comment#146DruncBread2024-08-23 16:26Code for using the ImageNet pretrained model
- Issue comment#146Aikoin2024-08-09 11:05Code for using the ImageNet pretrained model
- Issue#149hweejuni2024-04-30 08:32about loss_in and loss_out in paper
- Issue comment#148Aristo233332024-04-30 06:39How to change backbone
- Issue comment#111yaoerqin2024-03-24 06:43fix a bug, which has the little probability of producing nan in the loss
- Issue comment#120yaoerqin2024-03-18 02:36Hyperparameters for ImageNet training?
- Issue comment#117yaoerqin2024-03-04 03:02MoCo code
- Issue#148lucasPV2024-02-23 02:03How to change backbone
- Issue comment#72dvdsosa2024-02-15 13:31batch=32
- Issue#147limengting-evelyn2024-01-23 19:54Why images = torch.cat([images[0], images[1]], dim=0) in the training process?
- Issue#147limengting-evelyn2024-01-23 19:44Why images = torch.cat([images[0], images[1]], dim=0) in the training process?
- Issue#146LightingMc2024-01-23 07:33Code for using the ImageNet pretrained model
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 902 stars here means stars gained during the window, not the repo's star count.