模型:
Soulaimen/swin-tiny-patch4-window7-224-shortSleeveCleanedData
该模型是在图像文件夹数据集上对 microsoft/swin-tiny-patch4-window7-224 模型进行微调得到的。在评估集上取得了以下结果:
需要更多信息
需要更多信息
需要更多信息
训练时使用了以下超参数:
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.1819 | 1.0 | 147 | 0.0471 | 0.9880 |
0.1431 | 2.0 | 294 | 0.0457 | 0.9891 |
0.1001 | 3.0 | 441 | 0.0392 | 0.9891 |
0.116 | 4.0 | 588 | 0.0451 | 0.9880 |
0.1144 | 5.0 | 735 | 0.0398 | 0.9902 |
0.0787 | 6.0 | 882 | 0.0441 | 0.9902 |
0.0998 | 7.0 | 1029 | 0.0320 | 0.9902 |
0.124 | 8.0 | 1176 | 0.0364 | 0.9902 |
0.103 | 9.0 | 1323 | 0.0395 | 0.9880 |
0.0591 | 10.0 | 1470 | 0.0299 | 0.9913 |
0.0445 | 11.0 | 1617 | 0.0302 | 0.9913 |
0.0684 | 12.0 | 1764 | 0.0350 | 0.9880 |
0.0358 | 13.0 | 1911 | 0.0408 | 0.9891 |
0.0548 | 14.0 | 2058 | 0.0382 | 0.9902 |
0.0611 | 15.0 | 2205 | 0.0331 | 0.9923 |
0.0231 | 16.0 | 2352 | 0.0355 | 0.9945 |
0.046 | 17.0 | 2499 | 0.0321 | 0.9934 |
0.0648 | 18.0 | 2646 | 0.0327 | 0.9923 |
0.0565 | 19.0 | 2793 | 0.0320 | 0.9923 |
0.0413 | 20.0 | 2940 | 0.0327 | 0.9923 |