Hugging Face's logo

sam1120
/
safety-utcustom-train-SF-RGBD-b0

Image Segmentation
Transformers
PyTorch
TensorBoard
segformer
vision
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
sam1120 commited on
Commit
526c3a2
•
1 Parent(s): 953decc

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +52 -34
README.md CHANGED
@@ -1,8 +1,6 @@
1
  ---
2
  license: other
3
  tags:
4
- - vision
5
- - image-segmentation
6
  - generated_from_trainer
7
  model-index:
8
  - name: safety-utcustom-train-SF-RGBD-b0
@@ -14,18 +12,18 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  # safety-utcustom-train-SF-RGBD-b0
16
 
17
- This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on the sam1120/safety-utcustom-TRAIN dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.1668
20
- - Mean Iou: 0.6868
21
- - Mean Accuracy: 0.7168
22
- - Overall Accuracy: 0.9801
23
  - Accuracy Unlabeled: nan
24
- - Accuracy Safe: 0.4368
25
- - Accuracy Unsafe: 0.9967
26
  - Iou Unlabeled: nan
27
- - Iou Safe: 0.3938
28
- - Iou Unsafe: 0.9799
29
 
30
  ## Model description
31
 
@@ -51,7 +49,7 @@ The following hyperparameters were used during training:
51
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
  - lr_scheduler_type: linear
53
  - lr_scheduler_warmup_ratio: 0.05
54
- - num_epochs: 50
55
 
56
  ### Training results
57
 
@@ -85,28 +83,48 @@ The following hyperparameters were used during training:
85
  | 0.2547 | 26.0 | 260 | 0.2737 | nan | 0.9978 | 0.2555 | nan | 0.9763 | 0.2281 | 0.6357 | 0.6159 | 0.9764 |
86
  | 0.2266 | 27.0 | 270 | 0.2391 | nan | 0.9981 | 0.2252 | nan | 0.9755 | 0.2191 | 0.6186 | 0.6004 | 0.9757 |
87
  | 0.2357 | 28.0 | 280 | 0.2227 | nan | 0.9985 | 0.2122 | nan | 0.9754 | 0.2218 | 0.6106 | 0.5938 | 0.9756 |
88
- | 0.2563 | 29.0 | 290 | 0.2096 | 0.5764 | 0.5920 | 0.9748 | nan | 0.1852 | 0.9988 | nan | 0.1782 | 0.9746 |
89
- | 0.226 | 30.0 | 300 | 0.2121 | 0.6203 | 0.6410 | 0.9766 | nan | 0.2844 | 0.9977 | nan | 0.2643 | 0.9764 |
90
- | 0.2221 | 31.0 | 310 | 0.2016 | 0.6147 | 0.6348 | 0.9763 | nan | 0.2718 | 0.9978 | nan | 0.2533 | 0.9761 |
91
- | 0.2317 | 32.0 | 320 | 0.2008 | 0.6131 | 0.6315 | 0.9765 | nan | 0.2649 | 0.9982 | nan | 0.2499 | 0.9763 |
92
- | 0.2643 | 33.0 | 330 | 0.1989 | 0.6394 | 0.6615 | 0.9777 | nan | 0.3254 | 0.9976 | nan | 0.3014 | 0.9775 |
93
- | 0.2118 | 34.0 | 340 | 0.1901 | 0.6448 | 0.6662 | 0.9782 | nan | 0.3347 | 0.9977 | nan | 0.3117 | 0.9779 |
94
- | 0.2133 | 35.0 | 350 | 0.1917 | 0.6568 | 0.6797 | 0.9788 | nan | 0.3619 | 0.9976 | nan | 0.3350 | 0.9785 |
95
- | 0.2064 | 36.0 | 360 | 0.1860 | 0.6478 | 0.6690 | 0.9784 | nan | 0.3401 | 0.9978 | nan | 0.3174 | 0.9782 |
96
- | 0.2341 | 37.0 | 370 | 0.1775 | 0.6162 | 0.6343 | 0.9768 | nan | 0.2704 | 0.9983 | nan | 0.2557 | 0.9766 |
97
- | 0.2093 | 38.0 | 380 | 0.1934 | 0.6306 | 0.6740 | 0.9740 | nan | 0.3552 | 0.9928 | nan | 0.2874 | 0.9737 |
98
- | 0.1958 | 39.0 | 390 | 0.1755 | 0.6295 | 0.6491 | 0.9774 | nan | 0.3001 | 0.9980 | nan | 0.2818 | 0.9772 |
99
- | 0.1886 | 40.0 | 400 | 0.1768 | 0.6654 | 0.6925 | 0.9789 | nan | 0.3881 | 0.9969 | nan | 0.3522 | 0.9787 |
100
- | 0.1734 | 41.0 | 410 | 0.1745 | 0.6709 | 0.6960 | 0.9795 | nan | 0.3948 | 0.9973 | nan | 0.3626 | 0.9793 |
101
- | 0.1795 | 42.0 | 420 | 0.1710 | 0.6793 | 0.7069 | 0.9798 | nan | 0.4168 | 0.9970 | nan | 0.3789 | 0.9796 |
102
- | 0.222 | 43.0 | 430 | 0.1706 | 0.6747 | 0.7007 | 0.9797 | nan | 0.4041 | 0.9972 | nan | 0.3700 | 0.9794 |
103
- | 0.1831 | 44.0 | 440 | 0.1687 | 0.6752 | 0.7008 | 0.9797 | nan | 0.4044 | 0.9972 | nan | 0.3708 | 0.9795 |
104
- | 0.1935 | 45.0 | 450 | 0.1711 | 0.6842 | 0.7155 | 0.9798 | nan | 0.4347 | 0.9964 | nan | 0.3889 | 0.9796 |
105
- | 0.1728 | 46.0 | 460 | 0.1714 | 0.6808 | 0.7088 | 0.9799 | nan | 0.4208 | 0.9969 | nan | 0.3819 | 0.9796 |
106
- | 0.1742 | 47.0 | 470 | 0.1670 | 0.6691 | 0.6936 | 0.9794 | nan | 0.3898 | 0.9974 | nan | 0.3590 | 0.9792 |
107
- | 0.2064 | 48.0 | 480 | 0.1683 | 0.6812 | 0.7089 | 0.9799 | nan | 0.4209 | 0.9970 | nan | 0.3827 | 0.9797 |
108
- | 0.1746 | 49.0 | 490 | 0.1682 | 0.6822 | 0.7108 | 0.9799 | nan | 0.4249 | 0.9968 | nan | 0.3847 | 0.9797 |
109
- | 0.1966 | 50.0 | 500 | 0.1668 | 0.6868 | 0.7168 | 0.9801 | nan | 0.4368 | 0.9967 | nan | 0.3938 | 0.9799 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
110
 
111
 
112
  ### Framework versions
 
1
  ---
2
  license: other
3
  tags:
 
 
4
  - generated_from_trainer
5
  model-index:
6
  - name: safety-utcustom-train-SF-RGBD-b0
 
12
 
13
  # safety-utcustom-train-SF-RGBD-b0
14
 
15
+ This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 0.1393
18
+ - Mean Iou: 0.7018
19
+ - Mean Accuracy: 0.7359
20
+ - Overall Accuracy: 0.9808
21
  - Accuracy Unlabeled: nan
22
+ - Accuracy Safe: 0.4756
23
+ - Accuracy Unsafe: 0.9962
24
  - Iou Unlabeled: nan
25
+ - Iou Safe: 0.4230
26
+ - Iou Unsafe: 0.9806
27
 
28
  ## Model description
29
 
 
49
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
  - lr_scheduler_type: linear
51
  - lr_scheduler_warmup_ratio: 0.05
52
+ - num_epochs: 70
53
 
54
  ### Training results
55
 
 
83
  | 0.2547 | 26.0 | 260 | 0.2737 | nan | 0.9978 | 0.2555 | nan | 0.9763 | 0.2281 | 0.6357 | 0.6159 | 0.9764 |
84
  | 0.2266 | 27.0 | 270 | 0.2391 | nan | 0.9981 | 0.2252 | nan | 0.9755 | 0.2191 | 0.6186 | 0.6004 | 0.9757 |
85
  | 0.2357 | 28.0 | 280 | 0.2227 | nan | 0.9985 | 0.2122 | nan | 0.9754 | 0.2218 | 0.6106 | 0.5938 | 0.9756 |
86
+ | 0.2563 | 29.0 | 290 | 0.1852 | nan | 0.9988 | 0.1782 | nan | 0.9746 | 0.2096 | 0.5920 | 0.5764 | 0.9748 |
87
+ | 0.226 | 30.0 | 300 | 0.2844 | nan | 0.9977 | 0.2643 | nan | 0.9764 | 0.2121 | 0.6410 | 0.6203 | 0.9766 |
88
+ | 0.2221 | 31.0 | 310 | 0.2718 | nan | 0.9978 | 0.2533 | nan | 0.9761 | 0.2016 | 0.6348 | 0.6147 | 0.9763 |
89
+ | 0.2317 | 32.0 | 320 | 0.2649 | nan | 0.9982 | 0.2499 | nan | 0.9763 | 0.2008 | 0.6315 | 0.6131 | 0.9765 |
90
+ | 0.2643 | 33.0 | 330 | 0.3254 | nan | 0.9976 | 0.3014 | nan | 0.9775 | 0.1989 | 0.6615 | 0.6394 | 0.9777 |
91
+ | 0.2118 | 34.0 | 340 | 0.3347 | nan | 0.9977 | 0.3117 | nan | 0.9779 | 0.1901 | 0.6662 | 0.6448 | 0.9782 |
92
+ | 0.2133 | 35.0 | 350 | 0.3619 | nan | 0.9976 | 0.3350 | nan | 0.9785 | 0.1917 | 0.6797 | 0.6568 | 0.9788 |
93
+ | 0.2064 | 36.0 | 360 | 0.3401 | nan | 0.9978 | 0.3174 | nan | 0.9782 | 0.1860 | 0.6690 | 0.6478 | 0.9784 |
94
+ | 0.2341 | 37.0 | 370 | 0.2704 | nan | 0.9983 | 0.2557 | nan | 0.9766 | 0.1775 | 0.6343 | 0.6162 | 0.9768 |
95
+ | 0.2093 | 38.0 | 380 | 0.3552 | nan | 0.9928 | 0.2874 | nan | 0.9737 | 0.1934 | 0.6740 | 0.6306 | 0.9740 |
96
+ | 0.1958 | 39.0 | 390 | 0.3001 | nan | 0.9980 | 0.2818 | nan | 0.9772 | 0.1755 | 0.6491 | 0.6295 | 0.9774 |
97
+ | 0.1886 | 40.0 | 400 | 0.3881 | nan | 0.9969 | 0.3522 | nan | 0.9787 | 0.1768 | 0.6925 | 0.6654 | 0.9789 |
98
+ | 0.1734 | 41.0 | 410 | 0.3948 | nan | 0.9973 | 0.3626 | nan | 0.9793 | 0.1745 | 0.6960 | 0.6709 | 0.9795 |
99
+ | 0.1795 | 42.0 | 420 | 0.4168 | nan | 0.9970 | 0.3789 | nan | 0.9796 | 0.1710 | 0.7069 | 0.6793 | 0.9798 |
100
+ | 0.222 | 43.0 | 430 | 0.4041 | nan | 0.9972 | 0.3700 | nan | 0.9794 | 0.1706 | 0.7007 | 0.6747 | 0.9797 |
101
+ | 0.1831 | 44.0 | 440 | 0.4044 | nan | 0.9972 | 0.3708 | nan | 0.9795 | 0.1687 | 0.7008 | 0.6752 | 0.9797 |
102
+ | 0.1935 | 45.0 | 450 | 0.4347 | nan | 0.9964 | 0.3889 | nan | 0.9796 | 0.1711 | 0.7155 | 0.6842 | 0.9798 |
103
+ | 0.1728 | 46.0 | 460 | 0.4208 | nan | 0.9969 | 0.3819 | nan | 0.9796 | 0.1714 | 0.7088 | 0.6808 | 0.9799 |
104
+ | 0.1742 | 47.0 | 470 | 0.3898 | nan | 0.9974 | 0.3590 | nan | 0.9792 | 0.1670 | 0.6936 | 0.6691 | 0.9794 |
105
+ | 0.2064 | 48.0 | 480 | 0.4209 | nan | 0.9970 | 0.3827 | nan | 0.9797 | 0.1683 | 0.7089 | 0.6812 | 0.9799 |
106
+ | 0.1946 | 49.0 | 490 | 0.1659 | 0.6630 | 0.6861 | 0.9792 | nan | 0.3746 | 0.9976 | nan | 0.3471 | 0.9790 |
107
+ | 0.1836 | 50.0 | 500 | 0.1618 | 0.6910 | 0.7226 | 0.9803 | nan | 0.4487 | 0.9965 | nan | 0.4020 | 0.9800 |
108
+ | 0.1786 | 51.0 | 510 | 0.1595 | 0.6846 | 0.7147 | 0.9800 | nan | 0.4327 | 0.9966 | nan | 0.3896 | 0.9797 |
109
+ | 0.1867 | 52.0 | 520 | 0.1555 | 0.6943 | 0.7253 | 0.9806 | nan | 0.4540 | 0.9966 | nan | 0.4083 | 0.9803 |
110
+ | 0.1824 | 53.0 | 530 | 0.1564 | 0.6870 | 0.7176 | 0.9801 | nan | 0.4386 | 0.9966 | nan | 0.3942 | 0.9798 |
111
+ | 0.1494 | 54.0 | 540 | 0.1540 | 0.7052 | 0.7438 | 0.9807 | nan | 0.4920 | 0.9956 | nan | 0.4299 | 0.9804 |
112
+ | 0.1583 | 55.0 | 550 | 0.1502 | 0.6939 | 0.7261 | 0.9804 | nan | 0.4558 | 0.9964 | nan | 0.4075 | 0.9802 |
113
+ | 0.1648 | 56.0 | 560 | 0.1523 | 0.7005 | 0.7374 | 0.9805 | nan | 0.4791 | 0.9958 | nan | 0.4208 | 0.9802 |
114
+ | 0.1993 | 57.0 | 570 | 0.1502 | 0.6953 | 0.7275 | 0.9805 | nan | 0.4586 | 0.9964 | nan | 0.4103 | 0.9803 |
115
+ | 0.2243 | 58.0 | 580 | 0.1474 | 0.6695 | 0.6946 | 0.9794 | nan | 0.3920 | 0.9973 | nan | 0.3599 | 0.9792 |
116
+ | 0.1551 | 59.0 | 590 | 0.1445 | 0.6980 | 0.7324 | 0.9805 | nan | 0.4687 | 0.9961 | nan | 0.4157 | 0.9803 |
117
+ | 0.1666 | 60.0 | 600 | 0.1444 | 0.6892 | 0.7212 | 0.9801 | nan | 0.4460 | 0.9964 | nan | 0.3986 | 0.9799 |
118
+ | 0.1632 | 61.0 | 610 | 0.1504 | 0.7108 | 0.7535 | 0.9808 | nan | 0.5120 | 0.9951 | nan | 0.4411 | 0.9805 |
119
+ | 0.1589 | 62.0 | 620 | 0.1430 | 0.6749 | 0.7015 | 0.9796 | nan | 0.4059 | 0.9971 | nan | 0.3704 | 0.9794 |
120
+ | 0.1454 | 63.0 | 630 | 0.1423 | 0.7032 | 0.7397 | 0.9808 | nan | 0.4835 | 0.9959 | nan | 0.4260 | 0.9805 |
121
+ | 0.1635 | 64.0 | 640 | 0.1424 | 0.7052 | 0.7430 | 0.9808 | nan | 0.4902 | 0.9957 | nan | 0.4299 | 0.9805 |
122
+ | 0.1515 | 65.0 | 650 | 0.1422 | 0.7022 | 0.7368 | 0.9808 | nan | 0.4775 | 0.9962 | nan | 0.4239 | 0.9806 |
123
+ | 0.151 | 66.0 | 660 | 0.1423 | 0.7000 | 0.7340 | 0.9807 | nan | 0.4718 | 0.9962 | nan | 0.4195 | 0.9804 |
124
+ | 0.166 | 67.0 | 670 | 0.1427 | 0.7007 | 0.7342 | 0.9808 | nan | 0.4721 | 0.9963 | nan | 0.4208 | 0.9805 |
125
+ | 0.1561 | 68.0 | 680 | 0.1420 | 0.7070 | 0.7437 | 0.9810 | nan | 0.4916 | 0.9959 | nan | 0.4332 | 0.9807 |
126
+ | 0.1596 | 69.0 | 690 | 0.1414 | 0.7029 | 0.7375 | 0.9809 | nan | 0.4787 | 0.9962 | nan | 0.4253 | 0.9806 |
127
+ | 0.1395 | 70.0 | 700 | 0.1393 | 0.7018 | 0.7359 | 0.9808 | nan | 0.4756 | 0.9962 | nan | 0.4230 | 0.9806 |
128
 
129
 
130
  ### Framework versions