Hugging Face's logo

yijisuk
/
segformer-b1-miic-tl

Image Segmentation
Transformers
TensorBoard
Safetensors
segformer
vision
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
yijisuk commited on
Commit
f81a850
·
verified ·
1 Parent(s): 51adfcf

End of training

Browse files
Files changed (4) hide show
  1. README.md +23 -47
  2. model.safetensors +1 -1
  3. runs/Jun25_16-36-27_Centauri/events.out.tfevents.1719304916.Centauri.23712.2 +3 -0
  4. training_args.bin +1 -1
README.md CHANGED
@@ -17,15 +17,15 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [nvidia/mit-b1](https://huggingface.co/nvidia/mit-b1) on the yijisuk/ic-chip-sample dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.2325
21
- - Mean Iou: 0.4242
22
- - Mean Accuracy: 0.8484
23
- - Overall Accuracy: 0.8484
24
  - Accuracy Unlabeled: nan
25
- - Accuracy Circuit: 0.8484
26
  - Iou Unlabeled: 0.0
27
- - Iou Circuit: 0.8484
28
- - Dice Coefficient: 0.8124
29
 
30
  ## Model description
31
 
@@ -56,46 +56,22 @@ The following hyperparameters were used during training:
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Unlabeled | Accuracy Circuit | Iou Unlabeled | Iou Circuit | Dice Coefficient |
58
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:------------------:|:----------------:|:-------------:|:-----------:|:----------------:|
59
- | 0.6204 | 1.25 | 100 | 0.4305 | 0.2780 | 0.5561 | 0.5561 | nan | 0.5561 | 0.0 | 0.5561 | 0.4505 |
60
- | 0.5362 | 2.5 | 200 | 0.3695 | 0.3415 | 0.6830 | 0.6830 | nan | 0.6830 | 0.0 | 0.6830 | 0.6151 |
61
- | 0.5427 | 3.75 | 300 | 0.3586 | 0.2156 | 0.4312 | 0.4312 | nan | 0.4312 | 0.0 | 0.4312 | 0.3380 |
62
- | 0.5232 | 5.0 | 400 | 0.3678 | 0.3097 | 0.6193 | 0.6193 | nan | 0.6193 | 0.0 | 0.6193 | 0.6195 |
63
- | 0.5173 | 6.25 | 500 | 0.3283 | 0.3075 | 0.6151 | 0.6151 | nan | 0.6151 | 0.0 | 0.6151 | 0.5814 |
64
- | 0.4834 | 7.5 | 600 | 0.2894 | 0.2849 | 0.5698 | 0.5698 | nan | 0.5698 | 0.0 | 0.5698 | 0.5510 |
65
- | 0.4761 | 8.75 | 700 | 0.2636 | 0.4560 | 0.9120 | 0.9120 | nan | 0.9120 | 0.0 | 0.9120 | 0.8203 |
66
- | 0.4556 | 10.0 | 800 | 0.2597 | 0.4140 | 0.8279 | 0.8279 | nan | 0.8279 | 0.0 | 0.8279 | 0.7991 |
67
- | 0.46 | 11.25 | 900 | 0.2564 | 0.3546 | 0.7093 | 0.7093 | nan | 0.7093 | 0.0 | 0.7093 | 0.7022 |
68
- | 0.4607 | 12.5 | 1000 | 0.2497 | 0.3432 | 0.6865 | 0.6865 | nan | 0.6865 | 0.0 | 0.6865 | 0.6894 |
69
- | 0.437 | 13.75 | 1100 | 0.2284 | 0.4269 | 0.8539 | 0.8539 | nan | 0.8539 | 0.0 | 0.8539 | 0.8058 |
70
- | 0.4405 | 15.0 | 1200 | 0.2368 | 0.3750 | 0.7500 | 0.7500 | nan | 0.7500 | 0.0 | 0.7500 | 0.7423 |
71
- | 0.4203 | 16.25 | 1300 | 0.2590 | 0.3002 | 0.6004 | 0.6004 | nan | 0.6004 | 0.0 | 0.6004 | 0.6110 |
72
- | 0.4292 | 17.5 | 1400 | 0.2272 | 0.4050 | 0.8100 | 0.8100 | nan | 0.8100 | 0.0 | 0.8100 | 0.7895 |
73
- | 0.4222 | 18.75 | 1500 | 0.2373 | 0.3702 | 0.7403 | 0.7403 | nan | 0.7403 | 0.0 | 0.7403 | 0.7421 |
74
- | 0.396 | 20.0 | 1600 | 0.2266 | 0.4013 | 0.8025 | 0.8025 | nan | 0.8025 | 0.0 | 0.8025 | 0.7815 |
75
- | 0.406 | 21.25 | 1700 | 0.2344 | 0.4000 | 0.8000 | 0.8000 | nan | 0.8000 | 0.0 | 0.8000 | 0.7823 |
76
- | 0.3998 | 22.5 | 1800 | 0.2204 | 0.4185 | 0.8369 | 0.8369 | nan | 0.8369 | 0.0 | 0.8369 | 0.8059 |
77
- | 0.3915 | 23.75 | 1900 | 0.2418 | 0.3367 | 0.6734 | 0.6734 | nan | 0.6734 | 0.0 | 0.6734 | 0.6917 |
78
- | 0.3836 | 25.0 | 2000 | 0.2231 | 0.3937 | 0.7874 | 0.7874 | nan | 0.7874 | 0.0 | 0.7874 | 0.7747 |
79
- | 0.3824 | 26.25 | 2100 | 0.2249 | 0.4043 | 0.8086 | 0.8086 | nan | 0.8086 | 0.0 | 0.8086 | 0.7848 |
80
- | 0.3869 | 27.5 | 2200 | 0.2233 | 0.3705 | 0.7411 | 0.7411 | nan | 0.7411 | 0.0 | 0.7411 | 0.7408 |
81
- | 0.3707 | 28.75 | 2300 | 0.2259 | 0.4543 | 0.9086 | 0.9086 | nan | 0.9086 | 0.0 | 0.9086 | 0.8453 |
82
- | 0.3671 | 30.0 | 2400 | 0.2335 | 0.4435 | 0.8870 | 0.8870 | nan | 0.8870 | 0.0 | 0.8870 | 0.8331 |
83
- | 0.3758 | 31.25 | 2500 | 0.2324 | 0.4316 | 0.8631 | 0.8631 | nan | 0.8631 | 0.0 | 0.8631 | 0.8205 |
84
- | 0.3768 | 32.5 | 2600 | 0.2324 | 0.3643 | 0.7286 | 0.7286 | nan | 0.7286 | 0.0 | 0.7286 | 0.7372 |
85
- | 0.3657 | 33.75 | 2700 | 0.2357 | 0.3689 | 0.7378 | 0.7378 | nan | 0.7378 | 0.0 | 0.7378 | 0.7381 |
86
- | 0.3558 | 35.0 | 2800 | 0.2264 | 0.3836 | 0.7673 | 0.7673 | nan | 0.7673 | 0.0 | 0.7673 | 0.7593 |
87
- | 0.3586 | 36.25 | 2900 | 0.2265 | 0.4049 | 0.8098 | 0.8098 | nan | 0.8098 | 0.0 | 0.8098 | 0.7887 |
88
- | 0.3435 | 37.5 | 3000 | 0.2269 | 0.4124 | 0.8248 | 0.8248 | nan | 0.8248 | 0.0 | 0.8248 | 0.7985 |
89
- | 0.3659 | 38.75 | 3100 | 0.2282 | 0.3803 | 0.7606 | 0.7606 | nan | 0.7606 | 0.0 | 0.7606 | 0.7571 |
90
- | 0.3482 | 40.0 | 3200 | 0.2233 | 0.4160 | 0.8320 | 0.8320 | nan | 0.8320 | 0.0 | 0.8320 | 0.8040 |
91
- | 0.3452 | 41.25 | 3300 | 0.2208 | 0.4222 | 0.8445 | 0.8445 | nan | 0.8445 | 0.0 | 0.8445 | 0.8151 |
92
- | 0.3582 | 42.5 | 3400 | 0.2332 | 0.4016 | 0.8032 | 0.8032 | nan | 0.8032 | 0.0 | 0.8032 | 0.7845 |
93
- | 0.3254 | 43.75 | 3500 | 0.2171 | 0.4157 | 0.8314 | 0.8314 | nan | 0.8314 | 0.0 | 0.8314 | 0.8053 |
94
- | 0.3485 | 45.0 | 3600 | 0.2422 | 0.4345 | 0.8690 | 0.8690 | nan | 0.8690 | 0.0 | 0.8690 | 0.8163 |
95
- | 0.3401 | 46.25 | 3700 | 0.2263 | 0.4178 | 0.8356 | 0.8356 | nan | 0.8356 | 0.0 | 0.8356 | 0.8032 |
96
- | 0.3276 | 47.5 | 3800 | 0.2226 | 0.4347 | 0.8694 | 0.8694 | nan | 0.8694 | 0.0 | 0.8694 | 0.8254 |
97
- | 0.3637 | 48.75 | 3900 | 0.2284 | 0.4164 | 0.8329 | 0.8329 | nan | 0.8329 | 0.0 | 0.8329 | 0.8036 |
98
- | 0.3181 | 50.0 | 4000 | 0.2325 | 0.4242 | 0.8484 | 0.8484 | nan | 0.8484 | 0.0 | 0.8484 | 0.8124 |
99
 
100
 
101
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [nvidia/mit-b1](https://huggingface.co/nvidia/mit-b1) on the yijisuk/ic-chip-sample dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.2720
21
+ - Mean Iou: 0.4437
22
+ - Mean Accuracy: 0.8874
23
+ - Overall Accuracy: 0.8874
24
  - Accuracy Unlabeled: nan
25
+ - Accuracy Circuit: 0.8874
26
  - Iou Unlabeled: 0.0
27
+ - Iou Circuit: 0.8874
28
+ - Dice Coefficient: 0.8076
29
 
30
  ## Model description
31
 
 
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Unlabeled | Accuracy Circuit | Iou Unlabeled | Iou Circuit | Dice Coefficient |
58
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:------------------:|:----------------:|:-------------:|:-----------:|:----------------:|
59
+ | 0.6147 | 3.12 | 250 | 0.5121 | 0.4257 | 0.8515 | 0.8515 | nan | 0.8515 | 0.0 | 0.8515 | 0.7260 |
60
+ | 0.5757 | 6.25 | 500 | 0.3833 | 0.2639 | 0.5277 | 0.5277 | nan | 0.5277 | 0.0 | 0.5277 | 0.4226 |
61
+ | 0.5378 | 9.38 | 750 | 0.2758 | 0.4087 | 0.8174 | 0.8174 | nan | 0.8174 | 0.0 | 0.8174 | 0.7551 |
62
+ | 0.5127 | 12.5 | 1000 | 0.2915 | 0.2967 | 0.5933 | 0.5933 | nan | 0.5933 | 0.0 | 0.5933 | 0.5977 |
63
+ | 0.4838 | 15.62 | 1250 | 0.3783 | 0.4100 | 0.8200 | 0.8200 | nan | 0.8200 | 0.0 | 0.8200 | 0.7433 |
64
+ | 0.4763 | 18.75 | 1500 | 0.3150 | 0.4422 | 0.8844 | 0.8844 | nan | 0.8844 | 0.0 | 0.8844 | 0.7948 |
65
+ | 0.4509 | 21.88 | 1750 | 0.3324 | 0.4464 | 0.8928 | 0.8928 | nan | 0.8928 | 0.0 | 0.8928 | 0.7829 |
66
+ | 0.4367 | 25.0 | 2000 | 0.2373 | 0.4440 | 0.8880 | 0.8880 | nan | 0.8880 | 0.0 | 0.8880 | 0.8142 |
67
+ | 0.4236 | 28.12 | 2250 | 0.2457 | 0.4023 | 0.8046 | 0.8046 | nan | 0.8046 | 0.0 | 0.8046 | 0.7656 |
68
+ | 0.42 | 31.25 | 2500 | 0.2622 | 0.3672 | 0.7343 | 0.7343 | nan | 0.7343 | 0.0 | 0.7343 | 0.7106 |
69
+ | 0.403 | 34.38 | 2750 | 0.2472 | 0.4470 | 0.8941 | 0.8941 | nan | 0.8941 | 0.0 | 0.8941 | 0.8200 |
70
+ | 0.3946 | 37.5 | 3000 | 0.3254 | 0.4648 | 0.9295 | 0.9295 | nan | 0.9295 | 0.0 | 0.9295 | 0.8138 |
71
+ | 0.3848 | 40.62 | 3250 | 0.2792 | 0.4209 | 0.8418 | 0.8418 | nan | 0.8418 | 0.0 | 0.8418 | 0.7813 |
72
+ | 0.3821 | 43.75 | 3500 | 0.2849 | 0.4217 | 0.8434 | 0.8434 | nan | 0.8434 | 0.0 | 0.8434 | 0.7804 |
73
+ | 0.3756 | 46.88 | 3750 | 0.2722 | 0.4401 | 0.8801 | 0.8801 | nan | 0.8801 | 0.0 | 0.8801 | 0.8058 |
74
+ | 0.3727 | 50.0 | 4000 | 0.2720 | 0.4437 | 0.8874 | 0.8874 | nan | 0.8874 | 0.0 | 0.8874 | 0.8076 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
75
 
76
 
77
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d9016abe384a16713528f0645f9be02699d1ffb8d52e56d69591e7d13f4c0338
3
  size 54737376
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b4a77f455bdc4b54c760c626fc71c25271fd533cce16f43dc6236ab2a859f84
3
  size 54737376
runs/Jun25_16-36-27_Centauri/events.out.tfevents.1719304916.Centauri.23712.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85fd6dca0e15d7b8e9bddcab6a936ed94919d2cce86356d0031e1805a45e4fb4
3
+ size 19487
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:276c0a026ad750f95df60b3b61b685754307c26342ca6a184015f2e8827ab7d6
3
  size 4271
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cd6722b409bc9a601db66af8f7cad4a79325657397987a6692a59f395b3eca0
3
  size 4271