Hugging Face's logo

yijisuk
/
segformer-b0-miic-tl

Image Segmentation
Transformers
TensorBoard
Safetensors
segformer
vision
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
yijisuk commited on
Commit
eee4578
•
1 Parent(s): 63da55c

End of training

Browse files
Files changed (4) hide show
  1. README.md +23 -23
  2. model.safetensors +1 -1
  3. runs/Jun25_16-36-27_Centauri/events.out.tfevents.1719300995.Centauri.23712.1 +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-b0](https://huggingface.co/nvidia/mit-b0) on the yijisuk/ic-chip-sample dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.3908
21
- - Mean Iou: 0.4013
22
- - Mean Accuracy: 0.8026
23
- - Overall Accuracy: 0.8026
24
  - Accuracy Unlabeled: nan
25
- - Accuracy Circuit: 0.8026
26
  - Iou Unlabeled: 0.0
27
- - Iou Circuit: 0.8026
28
- - Dice Coefficient: 0.7558
29
 
30
  ## Model description
31
 
@@ -56,22 +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
- | 0.573 | 3.12 | 250 | 0.5056 | 0.4304 | 0.8608 | 0.8608 | nan | 0.8608 | 0.0 | 0.8608 | 0.7241 |
60
- | 0.5324 | 6.25 | 500 | 0.4020 | 0.2830 | 0.5660 | 0.5660 | nan | 0.5660 | 0.0 | 0.5660 | 0.5211 |
61
- | 0.488 | 9.38 | 750 | 0.3709 | 0.2965 | 0.5930 | 0.5930 | nan | 0.5930 | 0.0 | 0.5930 | 0.5624 |
62
- | 0.4742 | 12.5 | 1000 | 0.4180 | 0.2224 | 0.4448 | 0.4448 | nan | 0.4448 | 0.0 | 0.4448 | 0.3755 |
63
- | 0.4498 | 15.62 | 1250 | 0.4092 | 0.4008 | 0.8017 | 0.8017 | nan | 0.8017 | 0.0 | 0.8017 | 0.7394 |
64
- | 0.4479 | 18.75 | 1500 | 0.3620 | 0.3439 | 0.6878 | 0.6878 | nan | 0.6878 | 0.0 | 0.6878 | 0.6589 |
65
- | 0.4219 | 21.88 | 1750 | 0.3873 | 0.3648 | 0.7295 | 0.7295 | nan | 0.7295 | 0.0 | 0.7295 | 0.6971 |
66
- | 0.4152 | 25.0 | 2000 | 0.3919 | 0.3301 | 0.6602 | 0.6602 | nan | 0.6602 | 0.0 | 0.6602 | 0.6406 |
67
- | 0.4044 | 28.12 | 2250 | 0.3749 | 0.3820 | 0.7639 | 0.7639 | nan | 0.7639 | 0.0 | 0.7639 | 0.7241 |
68
- | 0.3982 | 31.25 | 2500 | 0.3266 | 0.4177 | 0.8354 | 0.8354 | nan | 0.8354 | 0.0 | 0.8354 | 0.7792 |
69
- | 0.3932 | 34.38 | 2750 | 0.3741 | 0.3803 | 0.7605 | 0.7605 | nan | 0.7605 | 0.0 | 0.7605 | 0.7242 |
70
- | 0.3838 | 37.5 | 3000 | 0.4037 | 0.3764 | 0.7528 | 0.7528 | nan | 0.7528 | 0.0 | 0.7528 | 0.7203 |
71
- | 0.3821 | 40.62 | 3250 | 0.4038 | 0.3534 | 0.7069 | 0.7069 | nan | 0.7069 | 0.0 | 0.7069 | 0.6837 |
72
- | 0.3782 | 43.75 | 3500 | 0.3792 | 0.3678 | 0.7356 | 0.7356 | nan | 0.7356 | 0.0 | 0.7356 | 0.7080 |
73
- | 0.3713 | 46.88 | 3750 | 0.4074 | 0.3762 | 0.7524 | 0.7524 | nan | 0.7524 | 0.0 | 0.7524 | 0.7203 |
74
- | 0.3698 | 50.0 | 4000 | 0.3908 | 0.4013 | 0.8026 | 0.8026 | nan | 0.8026 | 0.0 | 0.8026 | 0.7558 |
75
 
76
 
77
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on the yijisuk/ic-chip-sample dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.3532
21
+ - Mean Iou: 0.4001
22
+ - Mean Accuracy: 0.8002
23
+ - Overall Accuracy: 0.8002
24
  - Accuracy Unlabeled: nan
25
+ - Accuracy Circuit: 0.8002
26
  - Iou Unlabeled: 0.0
27
+ - Iou Circuit: 0.8002
28
+ - Dice Coefficient: 0.7456
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
+ | 0.5722 | 3.12 | 250 | 0.4296 | 0.3809 | 0.7618 | 0.7618 | nan | 0.7618 | 0.0 | 0.7618 | 0.6766 |
60
+ | 0.547 | 6.25 | 500 | 0.3983 | 0.3370 | 0.6739 | 0.6739 | nan | 0.6739 | 0.0 | 0.6739 | 0.6065 |
61
+ | 0.5147 | 9.38 | 750 | 0.3643 | 0.3487 | 0.6974 | 0.6974 | nan | 0.6974 | 0.0 | 0.6974 | 0.6477 |
62
+ | 0.5083 | 12.5 | 1000 | 0.3505 | 0.3006 | 0.6012 | 0.6012 | nan | 0.6012 | 0.0 | 0.6012 | 0.5586 |
63
+ | 0.4818 | 15.62 | 1250 | 0.3184 | 0.4400 | 0.8799 | 0.8799 | nan | 0.8799 | 0.0 | 0.8799 | 0.7758 |
64
+ | 0.4664 | 18.75 | 1500 | 0.3622 | 0.4347 | 0.8693 | 0.8693 | nan | 0.8693 | 0.0 | 0.8693 | 0.7755 |
65
+ | 0.4504 | 21.88 | 1750 | 0.3279 | 0.4327 | 0.8654 | 0.8654 | nan | 0.8654 | 0.0 | 0.8654 | 0.7792 |
66
+ | 0.4427 | 25.0 | 2000 | 0.3168 | 0.4386 | 0.8771 | 0.8771 | nan | 0.8771 | 0.0 | 0.8771 | 0.7840 |
67
+ | 0.4336 | 28.12 | 2250 | 0.2790 | 0.4100 | 0.8200 | 0.8200 | nan | 0.8200 | 0.0 | 0.8200 | 0.7636 |
68
+ | 0.4226 | 31.25 | 2500 | 0.3237 | 0.4148 | 0.8295 | 0.8295 | nan | 0.8295 | 0.0 | 0.8295 | 0.7641 |
69
+ | 0.4155 | 34.38 | 2750 | 0.3336 | 0.4169 | 0.8339 | 0.8339 | nan | 0.8339 | 0.0 | 0.8339 | 0.7664 |
70
+ | 0.4082 | 37.5 | 3000 | 0.3787 | 0.4267 | 0.8533 | 0.8533 | nan | 0.8533 | 0.0 | 0.8533 | 0.7760 |
71
+ | 0.403 | 40.62 | 3250 | 0.3541 | 0.3693 | 0.7387 | 0.7387 | nan | 0.7387 | 0.0 | 0.7387 | 0.6942 |
72
+ | 0.398 | 43.75 | 3500 | 0.3361 | 0.3864 | 0.7728 | 0.7728 | nan | 0.7728 | 0.0 | 0.7728 | 0.7244 |
73
+ | 0.3943 | 46.88 | 3750 | 0.3599 | 0.4053 | 0.8106 | 0.8106 | nan | 0.8106 | 0.0 | 0.8106 | 0.7519 |
74
+ | 0.3951 | 50.0 | 4000 | 0.3532 | 0.4001 | 0.8002 | 0.8002 | nan | 0.8002 | 0.0 | 0.8002 | 0.7456 |
75
 
76
 
77
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:29fc32e116eba10cb3d81f7f0d9ef1f45399342112e3a25b62a833c353f32c3c
3
  size 14884776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:157f52787c69d4de1dec54d751eb054e6d551b6a6a0419cd185aee641a087456
3
  size 14884776
runs/Jun25_16-36-27_Centauri/events.out.tfevents.1719300995.Centauri.23712.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41b6ce1635949f48bb401ea9c0b3041b2f8f722a6e845db4eb009ee3d641bf9a
3
+ size 24274
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1be985e922a502791e0b58f6691f2880af9b6c7ff1ad0d1b76d61ad5dfe4bd5d
3
  size 4271
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ec16696c40e8f122dde572c62bd22a4abfbb953ffc3ba5825c0900b02cfa9b0
3
  size 4271