归零巡礼亡谍镇魂曲万花筒成就如何做
2026-08-08 3445240
2026-08-08 0
sayakpaul/glpn-nyu-finetuned-diode-221116-110652-glpn-nyu-finetuned-diode-22...的重点在于把前置条件、操作顺序和容易误判的地方分清楚。
glpn-nyu-finetuned-diode-221116-110652
This model is a fine-tuned version of vinvino02/glpn-nyu on the diode-subset dataset.
It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss | Mae | Rmse | Abs Rel | Log Mae | Log Rmse | Delta1 | Delta2 | Delta3 |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1.3984 | 1.0 | 72 | 1.1606 | 3.2154 | 3.2710 | 4.6927 | 0.6627 | 0.7082 | 0.0 | 0.0053 | 0.0893 |
| 0.8305 | 2.0 | 144 | 0.5445 | 0.6035 | 0.8404 | 0.8013 | 0.2102 | 0.2726 | 0.2747 | 0.5358 | 0.7609 |
| 0.4601 | 3.0 | 216 | 0.4484 | 0.4041 | 0.5376 | 0.5417 | 0.1617 | 0.2188 | 0.3771 | 0.6932 | 0.8692 |
| 0.4211 | 4.0 | 288 | 0.4251 | 0.3634 | 0.4914 | 0.4800 | 0.1499 | 0.2069 | 0.4136 | 0.7270 | 0.8931 |
| 0.4162 | 5.0 | 360 | 0.4170 | 0.3537 | 0.4833 | 0.4483 | 0.1455 | 0.2005 | 0.4303 | 0.7444 | 0.8992 |
| 0.3776 | 6.0 | 432 | 0.4115 | 0.3491 | 0.4692 | 0.4558 | 0.1449 | 0.1999 | 0.4281 | 0.7471 | 0.9018 |
| 0.3729 | 7.0 | 504 | 0.4058 | 0.3337 | 0.4590 | 0.4135 | 0.1396 | 0.1935 | 0.4517 | 0.7652 | 0.9072 |
| 0.3235 | 8.0 | 576 | 0.4035 | 0.3304 | 0.4602 | 0.4043 | 0.1383 | 0.1929 | 0.4613 | 0.7679 | 0.9073 |
| 0.3382 | 9.0 | 648 | 0.3990 | 0.3254 | 0.4546 | 0.3937 | 0.1365 | 0.1900 | 0.4671 | 0.7717 | 0.9102 |
| 0.3265 | 10.0 | 720 | 0.4018 | 0.3272 | 0.4546 | 0.3934 | 0.1380 | 0.1907 | 0.4598 | 0.7659 | 0.9082 |
sayakpaul/glpn-nyu-finetuned-diode-221116-110652官网入口：https://huggingface.co/sayakpaul/glpn-nyu-finetuned-diode-221116-110652