🚀 mobilevit-small-10k-steps
這個模型是 apple/deeplabv3-mobilevit-small 在 Efferbach/lane_master2 數據集上的微調版本。它在評估集上取得了以下結果：
- 損失值：0.0821
- 平均交併比（Mean Iou）：0.0
- 平均準確率：0.0
- 總體準確率：0.0
- 背景準確率：nan
- 左側準確率：0.0
- 右側準確率：0.0
- 背景交併比：0.0
- 左側交併比：0.0
- 右側交併比：0.0
📚 詳細文檔
訓練過程
訓練超參數
訓練過程中使用了以下超參數：
- 學習率：6e-05
- 訓練批次大小：8
- 評估批次大小：8
- 隨機種子：1337
- 優化器：Adam（β1=0.9，β2=0.999，ε=1e-08）
- 學習率調度器類型：多項式
- 訓練步數：10000
訓練結果
| 訓練損失 |
輪數 |
步數 |
驗證損失 |
平均交併比 |
平均準確率 |
總體準確率 |
背景準確率 |
左側準確率 |
右側準確率 |
背景交併比 |
左側交併比 |
右側交併比 |
| 0.5041 |
1.0 |
385 |
0.3382 |
0.0 |
0.0 |
0.0 |
nan |
0.0 |
0.0 |
0.0 |
0.0 |
0.0 |
| 0.1553 |
2.0 |
770 |
0.1387 |
0.0 |
0.0 |
0.0 |
nan |
0.0 |
0.0 |
0.0 |
0.0 |
0.0 |
| 0.1019 |
3.0 |
1155 |
0.1037 |
0.0 |
0.0 |
0.0 |
nan |
0.0 |
0.0 |
0.0 |
0.0 |
0.0 |
| 0.0882 |
4.0 |
1540 |
0.0883 |
0.0 |
0.0 |
0.0 |
nan |
0.0 |
0.0 |
0.0 |
0.0 |
0.0 |
| 0.0828 |
5.0 |
1925 |
0.0823 |
0.0 |
0.0 |
0.0 |
nan |
0.0 |
0.0 |
0.0 |
0.0 |
0.0 |
| 0.0807 |
6.0 |
2310 |
0.0820 |
0.0 |
0.0 |
0.0 |
nan |
0.0 |
0.0 |
0.0 |
0.0 |
0.0 |
| 0.0795 |
7.0 |
2695 |
0.0804 |
0.0 |
0.0 |
0.0 |
nan |
0.0 |
0.0 |
0.0 |
0.0 |
0.0 |
| 0.0786 |
8.0 |
3080 |
0.0784 |
0.0 |
0.0 |
0.0 |
nan |
0.0 |
0.0 |
0.0 |
0.0 |
0.0 |
| 0.0777 |
9.0 |
3465 |
0.0786 |
0.0 |
0.0 |
0.0 |
nan |
0.0 |
0.0 |
0.0 |
0.0 |
0.0 |
| 0.0771 |
10.0 |
3850 |
0.0774 |
0.0 |
0.0 |
0.0 |
nan |
0.0 |
0.0 |
0.0 |
0.0 |
0.0 |
| 0.0773 |
11.0 |
4235 |
0.0775 |
0.0 |
0.0 |
0.0 |
nan |
0.0 |
0.0 |
0.0 |
0.0 |
0.0 |
| 0.0765 |
12.0 |
4620 |
0.0782 |
0.0 |
0.0 |
0.0 |
nan |
0.0 |
0.0 |
0.0 |
0.0 |
0.0 |
| 0.0757 |
13.0 |
5005 |
0.0775 |
0.0 |
0.0 |
0.0 |
nan |
0.0 |
0.0 |
0.0 |
0.0 |
0.0 |
| 0.0756 |
14.0 |
5390 |
0.0774 |
0.0 |
0.0 |
0.0 |
nan |
0.0 |
0.0 |
0.0 |
0.0 |
0.0 |
| 0.0754 |
15.0 |
5775 |
0.0775 |
0.0 |
0.0 |
0.0 |
nan |
0.0 |
0.0 |
0.0 |
0.0 |
0.0 |
| 0.0746 |
16.0 |
6160 |
0.0775 |
0.0 |
0.0 |
0.0 |
nan |
0.0 |
0.0 |
0.0 |
0.0 |
0.0 |
| 0.074 |
17.0 |
6545 |
0.0779 |
0.0 |
0.0 |
0.0 |
nan |
0.0 |
0.0 |
0.0 |
0.0 |
0.0 |
| 0.0736 |
18.0 |
6930 |
0.0792 |
0.0 |
0.0 |
0.0 |
nan |
0.0 |
0.0 |
0.0 |
0.0 |
0.0 |
| 0.0737 |
19.0 |
7315 |
0.0801 |
0.0 |
0.0 |
0.0 |
nan |
0.0 |
0.0 |
0.0 |
0.0 |
0.0 |
| 0.073 |
20.0 |
7700 |
0.0804 |
0.0 |
0.0 |
0.0 |
nan |
0.0 |
0.0 |
0.0 |
0.0 |
0.0 |
| 0.0729 |
21.0 |
8085 |
0.0805 |
0.0 |
0.0 |
0.0 |
nan |
0.0 |
0.0 |
0.0 |
0.0 |
0.0 |
| 0.0734 |
22.0 |
8470 |
0.0804 |
0.0 |
0.0 |
0.0 |
nan |
0.0 |
0.0 |
0.0 |
0.0 |
0.0 |
| 0.0726 |
23.0 |
8855 |
0.0811 |
0.0 |
0.0 |
0.0 |
nan |
0.0 |
0.0 |
0.0 |
0.0 |
0.0 |
| 0.0726 |
24.0 |
9240 |
0.0816 |
0.0 |
0.0 |
0.0 |
nan |
0.0 |
0.0 |
0.0 |
0.0 |
0.0 |
| 0.0721 |
25.0 |
9625 |
0.0822 |
0.0 |
0.0 |
0.0 |
nan |
0.0 |
0.0 |
0.0 |
0.0 |
0.0 |
| 0.0727 |
25.97 |
10000 |
0.0821 |
0.0 |
0.0 |
0.0 |
nan |
0.0 |
0.0 |
0.0 |
0.0 |
0.0 |
框架版本
- Transformers 4.28.0.dev0
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3
📄 許可證
其他許可證
%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
Transformers 支持多種語言