Hugging Face's logo

varcoder
/
segformer-DeepCrack

Transformers
PyTorch
TensorBoard
segformer
Generated from Trainer
Model card Files
xet
Metrics Community
1
varcoder commited on
Commit
d1a977d
·
1 Parent(s): f67cd93

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +59 -9
README.md CHANGED
@@ -14,12 +14,14 @@ should probably proofread and complete it, then remove this comment. -->
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: nan
18
- - Mean Iou: nan
19
  - Mean Accuracy: nan
20
  - Overall Accuracy: nan
21
- - Per Category Iou: [nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan]
22
- - Per Category Accuracy: [nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan]
 
 
23
 
24
  ## Model description
25
 
@@ -44,14 +46,62 @@ The following hyperparameters were used during training:
44
  - seed: 42
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
- - num_epochs: 4
48
 
49
  ### Training results
50
 
51
- | Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Per Category Iou | Per Category Accuracy |
52
- |:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|
53
- | 0.0 | 2.0 | 20 | nan | nan | nan | nan | [nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan] | [nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan] |
54
- | 0.0 | 4.0 | 40 | nan | nan | nan | nan | [nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan] | [nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan] |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55
 
56
 
57
  ### Framework versions
 
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: 0.0527
18
+ - Mean Iou: 0.0
19
  - Mean Accuracy: nan
20
  - Overall Accuracy: nan
21
+ - Accuracy Non-cracked: nan
22
+ - Accuracy Cracked: nan
23
+ - Iou Non-cracked: 0.0
24
+ - Iou Cracked: 0.0
25
 
26
  ## Model description
27
 
 
46
  - seed: 42
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
+ - num_epochs: 50
50
 
51
  ### Training results
52
 
53
+ | Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Non-cracked | Accuracy Cracked | Iou Non-cracked | Iou Cracked |
54
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:--------------------:|:----------------:|:---------------:|:-----------:|
55
+ | 0.6178 | 1.0 | 20 | 0.6186 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
56
+ | 0.4909 | 2.0 | 40 | 0.4784 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
57
+ | 0.3845 | 3.0 | 60 | 0.4290 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
58
+ | 0.3352 | 4.0 | 80 | 0.2482 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
59
+ | 0.2033 | 5.0 | 100 | 0.3220 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
60
+ | 0.1557 | 6.0 | 120 | 0.4012 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
61
+ | 0.1851 | 7.0 | 140 | 0.0773 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
62
+ | 0.1049 | 8.0 | 160 | 0.2010 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
63
+ | 0.0884 | 9.0 | 180 | 0.1838 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
64
+ | 0.0887 | 10.0 | 200 | 0.1343 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
65
+ | 0.065 | 11.0 | 220 | 0.1933 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
66
+ | 0.0618 | 12.0 | 240 | 0.1084 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
67
+ | 0.0546 | 13.0 | 260 | 0.0515 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
68
+ | 0.039 | 14.0 | 280 | 0.1159 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
69
+ | 0.04 | 15.0 | 300 | 0.1041 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
70
+ | 0.047 | 16.0 | 320 | 0.1836 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
71
+ | 0.0308 | 17.0 | 340 | 0.1068 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
72
+ | 0.0291 | 18.0 | 360 | 0.0980 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
73
+ | 0.026 | 19.0 | 380 | 0.1805 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
74
+ | 0.0272 | 20.0 | 400 | 0.1208 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
75
+ | 0.0245 | 21.0 | 420 | 0.0758 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
76
+ | 0.0191 | 22.0 | 440 | 0.1378 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
77
+ | 0.0208 | 23.0 | 460 | 0.1485 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
78
+ | 0.0195 | 24.0 | 480 | 0.1166 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
79
+ | 0.0182 | 25.0 | 500 | 0.0893 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
80
+ | 0.0172 | 26.0 | 520 | 0.1040 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
81
+ | 0.0175 | 27.0 | 540 | 0.1170 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
82
+ | 0.0129 | 28.0 | 560 | 0.0813 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
83
+ | 0.0134 | 29.0 | 580 | 0.0805 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
84
+ | 0.0155 | 30.0 | 600 | 0.0633 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
85
+ | 0.013 | 31.0 | 620 | 0.0952 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
86
+ | 0.0116 | 32.0 | 640 | 0.0551 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
87
+ | 0.0121 | 33.0 | 660 | 0.0733 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
88
+ | 0.013 | 34.0 | 680 | 0.0758 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
89
+ | 0.0114 | 35.0 | 700 | 0.0509 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
90
+ | 0.0297 | 36.0 | 720 | 0.0418 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
91
+ | 0.0108 | 37.0 | 740 | 0.0823 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
92
+ | 0.0104 | 38.0 | 760 | 0.0864 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
93
+ | 0.0111 | 39.0 | 780 | 0.1240 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
94
+ | 0.0104 | 40.0 | 800 | 0.1074 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
95
+ | 0.0093 | 41.0 | 820 | 0.0531 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
96
+ | 0.0159 | 42.0 | 840 | 0.0412 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
97
+ | 0.0194 | 43.0 | 860 | 0.0689 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
98
+ | 0.0266 | 44.0 | 880 | 0.0688 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
99
+ | 0.0107 | 45.0 | 900 | 0.0767 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
100
+ | 0.0087 | 46.0 | 920 | 0.1006 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
101
+ | 0.0092 | 47.0 | 940 | 0.0759 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
102
+ | 0.0087 | 48.0 | 960 | 0.0724 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
103
+ | 0.0086 | 49.0 | 980 | 0.0694 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
104
+ | 0.0116 | 50.0 | 1000 | 0.0527 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
105
 
106
 
107
  ### Framework versions