Transformer Unet Learning Repo
active 2023-08-15 → 2026-08-13 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 1095 days from 2023-08-15 to 2026-08-13. Pushes: 11 total, peak 4 in a day. Pull requests: 7 total, peak 2 in a day. Issues: 39 total, peak 4 in a day. Comments: 99 total, peak 6 in a day. Stars: 1,325 total, peak 17 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 |
|---|---|---|---|---|
| Beckschen | 10 | 10 | 0 | 0 |
| Karmush21 | 6 | 0 | 0 | 3 |
| onismera | 6 | 0 | 0 | 6 |
| Yanweijians | 4 | 0 | 0 | 4 |
| smallbirdjjz | 4 | 0 | 0 | 0 |
| ylj183 | 4 | 0 | 0 | 4 |
| hdnminh | 4 | 0 | 0 | 4 |
| alqurri77 | 3 | 0 | 0 | 1 |
| congcongWY | 3 | 0 | 0 | 1 |
| zhaoyang23333 | 3 | 0 | 0 | 2 |
| sanctuary-sun | 3 | 0 | 0 | 3 |
| zhangxuan-thecastle | 3 | 0 | 0 | 3 |
| Kyochilian | 3 | 0 | 0 | 3 |
| xinnvY | 3 | 0 | 0 | 3 |
| congcongwy51 | 3 | 0 | 0 | 2 |
| Bigearth6 | 2 | 0 | 0 | 2 |
| tesla2678LLM | 2 | 0 | 2 | 0 |
| Wang-YaoJie | 2 | 0 | 2 | 0 |
| liuyi0316 | 2 | 0 | 0 | 2 |
| janet-rgb | 2 | 0 | 0 | 1 |
Recent activity
Latest issues, pull requests and releases
- Issue#177Worldseer2025-11-12 09:46install pip requirements.txt error
- Issue#176zhaoyang233332025-09-20 03:45test with final epoch.th or best model.pth?,No Best model.pth.
- Issue comment#167zhaoyang233332025-09-20 02:56No best model. pth
- Issue comment#167zhaoyang233332025-09-20 02:55No best model. pth
- Issue#175ssxfc2025-08-07 09:20这网络架构代码看着很费劲，为什么不直截了当的给出一个显式的网络代码，而是通过config去配置呢？
- Issue comment#72wscc1232025-07-04 05:47Regarding position embeddings
- Issue comment#72Bigearth62025-07-04 05:47Regarding position embeddings
- Issue comment#58Pleasurecruise2025-06-26 13:51run python test.py --dataset Synapse --vit_name R50-ViT-B_16 error
- Issue comment#63Bigearth62025-06-24 01:47Training error
- Pull request#173tesla2678LLM2025-06-07 14:35
- Pull request#173tesla2678LLM2025-06-07 14:35
- Issue comment#21Louaq2025-04-30 03:26AttributeError: "'skip_channels'"
- Pull request#172chisngooo2025-04-09 02:56
- Pull request#172chisngooo2025-04-09 02:50
- Issue comment#167chenxulin2025-03-27 06:29No best model. pth
- Issue comment#141yeqian19612025-03-25 04:32Data preprocessing
- Issue comment#96adamnipabupa2025-03-20 13:34The model has how many parameters?
- Issue comment#169YuKaixinn2025-03-15 09:36Hello, I would like to ask what does the 16 in the Embeddings class mean? Is it the patch_size or the multiple of the downsampling performed by resnet?
- Issue comment#115qiukukkk2025-03-12 12:18The mean dice is very low after testing
- Issue comment#22LiuChengAkina2025-02-22 00:36cannot find the 'R50-ViT-L_16' pretrained model
- Issue comment#141Adam44444442025-02-10 01:22Data preprocessing
- Issue comment#134sjttsts8542025-01-30 14:04当我在运行TransUNet-main的train.py时出现错误：KeyError: 'Transformer/encoderblock_0/Multi5HeadDotProductAttention_1/query/kernel is not a file in the archive' 这是在我进行KeyError: 'Transformer/encoderblock_0/MultiHeadDotProductAttention_1/query\\kernel is not a file in the archive'后的更改出现的错误，csdn说这是os.path.join 合并路径的时候出现的问题，更改后仍然出现以上错误
- Issue comment#162reolllllllllll2025-01-24 04:28FileNotFoundError: [Errno 2] No such file or directory: './lists/lists_Synapse\\train.txt'
- Issue#170ceciliadiana002025-01-13 18:29Pretrained weights
- Issue#169yesulove2025-01-02 10:57Hello, I would like to ask what does the 16 in the Embeddings class mean? Is it the patch_size or the multiple of the downsampling performed by resnet?
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 1,325 stars here means stars gained during the window, not the repo's star count.