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
0689742
•
1 Parent(s): 21e5fc7

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +47 -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: 0.1393
20
- - Mean Iou: 0.7018
21
- - Mean Accuracy: 0.7359
22
- - Overall Accuracy: 0.9808
23
  - Accuracy Unlabeled: nan
24
- - Accuracy Safe: 0.4756
25
- - Accuracy Unsafe: 0.9962
26
  - Iou Unlabeled: nan
27
- - Iou Safe: 0.4230
28
- - Iou Unsafe: 0.9806
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: 70
55
 
56
  ### Training results
57
 
@@ -105,28 +103,43 @@ The following hyperparameters were used during training:
105
  | 0.1728 | 46.0 | 460 | 0.4208 | nan | 0.9969 | 0.3819 | nan | 0.9796 | 0.1714 | 0.7088 | 0.6808 | 0.9799 |
106
  | 0.1742 | 47.0 | 470 | 0.3898 | nan | 0.9974 | 0.3590 | nan | 0.9792 | 0.1670 | 0.6936 | 0.6691 | 0.9794 |
107
  | 0.2064 | 48.0 | 480 | 0.4209 | nan | 0.9970 | 0.3827 | nan | 0.9797 | 0.1683 | 0.7089 | 0.6812 | 0.9799 |
108
- | 0.1946 | 49.0 | 490 | 0.1659 | 0.6630 | 0.6861 | 0.9792 | nan | 0.3746 | 0.9976 | nan | 0.3471 | 0.9790 |
109
- | 0.1836 | 50.0 | 500 | 0.1618 | 0.6910 | 0.7226 | 0.9803 | nan | 0.4487 | 0.9965 | nan | 0.4020 | 0.9800 |
110
- | 0.1786 | 51.0 | 510 | 0.1595 | 0.6846 | 0.7147 | 0.9800 | nan | 0.4327 | 0.9966 | nan | 0.3896 | 0.9797 |
111
- | 0.1867 | 52.0 | 520 | 0.1555 | 0.6943 | 0.7253 | 0.9806 | nan | 0.4540 | 0.9966 | nan | 0.4083 | 0.9803 |
112
- | 0.1824 | 53.0 | 530 | 0.1564 | 0.6870 | 0.7176 | 0.9801 | nan | 0.4386 | 0.9966 | nan | 0.3942 | 0.9798 |
113
- | 0.1494 | 54.0 | 540 | 0.1540 | 0.7052 | 0.7438 | 0.9807 | nan | 0.4920 | 0.9956 | nan | 0.4299 | 0.9804 |
114
- | 0.1583 | 55.0 | 550 | 0.1502 | 0.6939 | 0.7261 | 0.9804 | nan | 0.4558 | 0.9964 | nan | 0.4075 | 0.9802 |
115
- | 0.1648 | 56.0 | 560 | 0.1523 | 0.7005 | 0.7374 | 0.9805 | nan | 0.4791 | 0.9958 | nan | 0.4208 | 0.9802 |
116
- | 0.1993 | 57.0 | 570 | 0.1502 | 0.6953 | 0.7275 | 0.9805 | nan | 0.4586 | 0.9964 | nan | 0.4103 | 0.9803 |
117
- | 0.2243 | 58.0 | 580 | 0.1474 | 0.6695 | 0.6946 | 0.9794 | nan | 0.3920 | 0.9973 | nan | 0.3599 | 0.9792 |
118
- | 0.1551 | 59.0 | 590 | 0.1445 | 0.6980 | 0.7324 | 0.9805 | nan | 0.4687 | 0.9961 | nan | 0.4157 | 0.9803 |
119
- | 0.1666 | 60.0 | 600 | 0.1444 | 0.6892 | 0.7212 | 0.9801 | nan | 0.4460 | 0.9964 | nan | 0.3986 | 0.9799 |
120
- | 0.1632 | 61.0 | 610 | 0.1504 | 0.7108 | 0.7535 | 0.9808 | nan | 0.5120 | 0.9951 | nan | 0.4411 | 0.9805 |
121
- | 0.1589 | 62.0 | 620 | 0.1430 | 0.6749 | 0.7015 | 0.9796 | nan | 0.4059 | 0.9971 | nan | 0.3704 | 0.9794 |
122
- | 0.1454 | 63.0 | 630 | 0.1423 | 0.7032 | 0.7397 | 0.9808 | nan | 0.4835 | 0.9959 | nan | 0.4260 | 0.9805 |
123
- | 0.1635 | 64.0 | 640 | 0.1424 | 0.7052 | 0.7430 | 0.9808 | nan | 0.4902 | 0.9957 | nan | 0.4299 | 0.9805 |
124
- | 0.1515 | 65.0 | 650 | 0.1422 | 0.7022 | 0.7368 | 0.9808 | nan | 0.4775 | 0.9962 | nan | 0.4239 | 0.9806 |
125
- | 0.151 | 66.0 | 660 | 0.1423 | 0.7000 | 0.7340 | 0.9807 | nan | 0.4718 | 0.9962 | nan | 0.4195 | 0.9804 |
126
- | 0.166 | 67.0 | 670 | 0.1427 | 0.7007 | 0.7342 | 0.9808 | nan | 0.4721 | 0.9963 | nan | 0.4208 | 0.9805 |
127
- | 0.1561 | 68.0 | 680 | 0.1420 | 0.7070 | 0.7437 | 0.9810 | nan | 0.4916 | 0.9959 | nan | 0.4332 | 0.9807 |
128
- | 0.1596 | 69.0 | 690 | 0.1414 | 0.7029 | 0.7375 | 0.9809 | nan | 0.4787 | 0.9962 | nan | 0.4253 | 0.9806 |
129
- | 0.1395 | 70.0 | 700 | 0.1393 | 0.7018 | 0.7359 | 0.9808 | nan | 0.4756 | 0.9962 | nan | 0.4230 | 0.9806 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
130
 
131
 
132
  ### 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: 0.1291
18
+ - Mean Iou: 0.7126
19
+ - Mean Accuracy: 0.7516
20
+ - Overall Accuracy: 0.9812
21
  - Accuracy Unlabeled: nan
22
+ - Accuracy Safe: 0.5074
23
+ - Accuracy Unsafe: 0.9957
24
  - Iou Unlabeled: nan
25
+ - Iou Safe: 0.4442
26
+ - Iou Unsafe: 0.9810
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: 85
53
 
54
  ### Training results
55
 
 
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 | 0.3746 | nan | 0.9976 | 0.3471 | nan | 0.9790 | 0.1659 | 0.6861 | 0.6630 | 0.9792 |
107
+ | 0.1836 | 50.0 | 500 | 0.4487 | nan | 0.9965 | 0.4020 | nan | 0.9800 | 0.1618 | 0.7226 | 0.6910 | 0.9803 |
108
+ | 0.1786 | 51.0 | 510 | 0.4327 | nan | 0.9966 | 0.3896 | nan | 0.9797 | 0.1595 | 0.7147 | 0.6846 | 0.9800 |
109
+ | 0.1867 | 52.0 | 520 | 0.4540 | nan | 0.9966 | 0.4083 | nan | 0.9803 | 0.1555 | 0.7253 | 0.6943 | 0.9806 |
110
+ | 0.1824 | 53.0 | 530 | 0.4386 | nan | 0.9966 | 0.3942 | nan | 0.9798 | 0.1564 | 0.7176 | 0.6870 | 0.9801 |
111
+ | 0.1494 | 54.0 | 540 | 0.4920 | nan | 0.9956 | 0.4299 | nan | 0.9804 | 0.1540 | 0.7438 | 0.7052 | 0.9807 |
112
+ | 0.1583 | 55.0 | 550 | 0.4558 | nan | 0.9964 | 0.4075 | nan | 0.9802 | 0.1502 | 0.7261 | 0.6939 | 0.9804 |
113
+ | 0.1648 | 56.0 | 560 | 0.4791 | nan | 0.9958 | 0.4208 | nan | 0.9802 | 0.1523 | 0.7374 | 0.7005 | 0.9805 |
114
+ | 0.1993 | 57.0 | 570 | 0.4586 | nan | 0.9964 | 0.4103 | nan | 0.9803 | 0.1502 | 0.7275 | 0.6953 | 0.9805 |
115
+ | 0.2243 | 58.0 | 580 | 0.3920 | nan | 0.9973 | 0.3599 | nan | 0.9792 | 0.1474 | 0.6946 | 0.6695 | 0.9794 |
116
+ | 0.1551 | 59.0 | 590 | 0.4687 | nan | 0.9961 | 0.4157 | nan | 0.9803 | 0.1445 | 0.7324 | 0.6980 | 0.9805 |
117
+ | 0.1666 | 60.0 | 600 | 0.4460 | nan | 0.9964 | 0.3986 | nan | 0.9799 | 0.1444 | 0.7212 | 0.6892 | 0.9801 |
118
+ | 0.1632 | 61.0 | 610 | 0.5120 | nan | 0.9951 | 0.4411 | nan | 0.9805 | 0.1504 | 0.7535 | 0.7108 | 0.9808 |
119
+ | 0.1589 | 62.0 | 620 | 0.4059 | nan | 0.9971 | 0.3704 | nan | 0.9794 | 0.1430 | 0.7015 | 0.6749 | 0.9796 |
120
+ | 0.1454 | 63.0 | 630 | 0.4835 | nan | 0.9959 | 0.4260 | nan | 0.9805 | 0.1423 | 0.7397 | 0.7032 | 0.9808 |
121
+ | 0.1635 | 64.0 | 640 | 0.4902 | nan | 0.9957 | 0.4299 | nan | 0.9805 | 0.1424 | 0.7430 | 0.7052 | 0.9808 |
122
+ | 0.1515 | 65.0 | 650 | 0.4775 | nan | 0.9962 | 0.4239 | nan | 0.9806 | 0.1422 | 0.7368 | 0.7022 | 0.9808 |
123
+ | 0.151 | 66.0 | 660 | 0.4718 | nan | 0.9962 | 0.4195 | nan | 0.9804 | 0.1423 | 0.7340 | 0.7000 | 0.9807 |
124
+ | 0.166 | 67.0 | 670 | 0.4721 | nan | 0.9963 | 0.4208 | nan | 0.9805 | 0.1427 | 0.7342 | 0.7007 | 0.9808 |
125
+ | 0.1561 | 68.0 | 680 | 0.4916 | nan | 0.9959 | 0.4332 | nan | 0.9807 | 0.1420 | 0.7437 | 0.7070 | 0.9810 |
126
+ | 0.1501 | 69.0 | 690 | 0.1437 | 0.7058 | 0.7432 | 0.9809 | nan | 0.4906 | 0.9958 | nan | 0.4311 | 0.9806 |
127
+ | 0.1598 | 70.0 | 700 | 0.1379 | 0.6493 | 0.6711 | 0.9784 | nan | 0.3445 | 0.9977 | nan | 0.3204 | 0.9782 |
128
+ | 0.1431 | 71.0 | 710 | 0.1400 | 0.7066 | 0.7429 | 0.9810 | nan | 0.4898 | 0.9960 | nan | 0.4325 | 0.9807 |
129
+ | 0.164 | 72.0 | 720 | 0.1347 | 0.7001 | 0.7331 | 0.9808 | nan | 0.4698 | 0.9964 | nan | 0.4196 | 0.9805 |
130
+ | 0.1555 | 73.0 | 730 | 0.1368 | 0.7080 | 0.7604 | 0.9799 | nan | 0.5271 | 0.9937 | nan | 0.4364 | 0.9796 |
131
+ | 0.1924 | 74.0 | 740 | 0.1312 | 0.6982 | 0.7301 | 0.9808 | nan | 0.4638 | 0.9965 | nan | 0.4159 | 0.9805 |
132
+ | 0.1612 | 75.0 | 750 | 0.1340 | 0.7108 | 0.7504 | 0.9811 | nan | 0.5052 | 0.9956 | nan | 0.4409 | 0.9808 |
133
+ | 0.1234 | 76.0 | 760 | 0.1354 | 0.7153 | 0.7624 | 0.9809 | nan | 0.5301 | 0.9946 | nan | 0.4501 | 0.9806 |
134
+ | 0.1679 | 77.0 | 770 | 0.1323 | 0.6980 | 0.7304 | 0.9807 | nan | 0.4644 | 0.9964 | nan | 0.4156 | 0.9804 |
135
+ | 0.1375 | 78.0 | 780 | 0.1355 | 0.7035 | 0.7383 | 0.9809 | nan | 0.4804 | 0.9961 | nan | 0.4263 | 0.9806 |
136
+ | 0.1839 | 79.0 | 790 | 0.1319 | 0.7115 | 0.7512 | 0.9811 | nan | 0.5070 | 0.9955 | nan | 0.4422 | 0.9808 |
137
+ | 0.155 | 80.0 | 800 | 0.1298 | 0.7051 | 0.7403 | 0.9810 | nan | 0.4846 | 0.9961 | nan | 0.4295 | 0.9807 |
138
+ | 0.1219 | 81.0 | 810 | 0.1302 | 0.6986 | 0.7317 | 0.9807 | nan | 0.4671 | 0.9963 | nan | 0.4167 | 0.9804 |
139
+ | 0.1218 | 82.0 | 820 | 0.1313 | 0.7054 | 0.7412 | 0.9810 | nan | 0.4864 | 0.9960 | nan | 0.4300 | 0.9807 |
140
+ | 0.138 | 83.0 | 830 | 0.1318 | 0.7127 | 0.7526 | 0.9812 | nan | 0.5097 | 0.9955 | nan | 0.4445 | 0.9809 |
141
+ | 0.1399 | 84.0 | 840 | 0.1290 | 0.7126 | 0.7512 | 0.9813 | nan | 0.5067 | 0.9957 | nan | 0.4441 | 0.9810 |
142
+ | 0.163 | 85.0 | 850 | 0.1291 | 0.7126 | 0.7516 | 0.9812 | nan | 0.5074 | 0.9957 | nan | 0.4442 | 0.9810 |
143
 
144
 
145
  ### Framework versions