Hugging Face's logo

yijisuk
/
segformer-b0-finetuned-segments-ic-chip-sample

Image Segmentation
Transformers
TensorBoard
Safetensors
segformer
vision
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
yijisuk commited on
Commit
30664a1
•
1 Parent(s): 1fc395e

End of training

Browse files
Files changed (5) hide show
  1. README.md +115 -0
  2. config.json +78 -0
  3. model.safetensors +3 -0
  4. runs/Dec23_19-02-58_Centauri/events.out.tfevents.1703325781.Centauri.43660.3 +3 -0
  5. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ base_model: nvidia/mit-b0
4
+ tags:
5
+ - vision
6
+ - image-segmentation
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: segformer-b0-finetuned-segments-ic-chip-sample
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # segformer-b0-finetuned-segments-ic-chip-sample
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: 0.0772
21
+ - Mean Iou: 0.4863
22
+ - Mean Accuracy: 0.9725
23
+ - Overall Accuracy: 0.9725
24
+ - Accuracy Unlabeled: nan
25
+ - Accuracy Circuit: 0.9725
26
+ - Iou Unlabeled: 0.0
27
+ - Iou Circuit: 0.9725
28
+
29
+ ## Model description
30
+
31
+ More information needed
32
+
33
+ ## Intended uses & limitations
34
+
35
+ More information needed
36
+
37
+ ## Training and evaluation data
38
+
39
+ More information needed
40
+
41
+ ## Training procedure
42
+
43
+ ### Training hyperparameters
44
+
45
+ The following hyperparameters were used during training:
46
+ - learning_rate: 6e-05
47
+ - train_batch_size: 2
48
+ - eval_batch_size: 2
49
+ - seed: 42
50
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
+ - lr_scheduler_type: linear
52
+ - num_epochs: 50
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Unlabeled | Accuracy Circuit | Iou Unlabeled | Iou Circuit |
57
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:------------------:|:----------------:|:-------------:|:-----------:|
58
+ | 0.0885 | 1.0 | 20 | 0.0858 | 0.4907 | 0.9815 | 0.9815 | nan | 0.9815 | 0.0 | 0.9815 |
59
+ | 0.1764 | 2.0 | 40 | 0.0854 | 0.4734 | 0.9469 | 0.9469 | nan | 0.9469 | 0.0 | 0.9469 |
60
+ | 0.0569 | 3.0 | 60 | 0.0854 | 0.4702 | 0.9404 | 0.9404 | nan | 0.9404 | 0.0 | 0.9404 |
61
+ | 0.0959 | 4.0 | 80 | 0.0851 | 0.4893 | 0.9786 | 0.9786 | nan | 0.9786 | 0.0 | 0.9786 |
62
+ | 0.2969 | 5.0 | 100 | 0.0825 | 0.4863 | 0.9727 | 0.9727 | nan | 0.9727 | 0.0 | 0.9727 |
63
+ | 0.1979 | 6.0 | 120 | 0.0824 | 0.4873 | 0.9746 | 0.9746 | nan | 0.9746 | 0.0 | 0.9746 |
64
+ | 0.0906 | 7.0 | 140 | 0.0824 | 0.4740 | 0.9480 | 0.9480 | nan | 0.9480 | 0.0 | 0.9480 |
65
+ | 0.2879 | 8.0 | 160 | 0.0821 | 0.4882 | 0.9764 | 0.9764 | nan | 0.9764 | 0.0 | 0.9764 |
66
+ | 0.1366 | 9.0 | 180 | 0.0807 | 0.4833 | 0.9666 | 0.9666 | nan | 0.9666 | 0.0 | 0.9666 |
67
+ | 0.1664 | 10.0 | 200 | 0.0813 | 0.4860 | 0.9720 | 0.9720 | nan | 0.9720 | 0.0 | 0.9720 |
68
+ | 0.1521 | 11.0 | 220 | 0.0831 | 0.4830 | 0.9660 | 0.9660 | nan | 0.9660 | 0.0 | 0.9660 |
69
+ | 0.2004 | 12.0 | 240 | 0.0795 | 0.4825 | 0.9651 | 0.9651 | nan | 0.9651 | 0.0 | 0.9651 |
70
+ | 0.1547 | 13.0 | 260 | 0.0793 | 0.4812 | 0.9625 | 0.9625 | nan | 0.9625 | 0.0 | 0.9625 |
71
+ | 0.4191 | 14.0 | 280 | 0.0788 | 0.4830 | 0.9659 | 0.9659 | nan | 0.9659 | 0.0 | 0.9659 |
72
+ | 0.0431 | 15.0 | 300 | 0.0782 | 0.4815 | 0.9630 | 0.9630 | nan | 0.9630 | 0.0 | 0.9630 |
73
+ | 1.3911 | 16.0 | 320 | 0.0793 | 0.4820 | 0.9640 | 0.9640 | nan | 0.9640 | 0.0 | 0.9640 |
74
+ | 0.0217 | 17.0 | 340 | 0.0814 | 0.4836 | 0.9671 | 0.9671 | nan | 0.9671 | 0.0 | 0.9671 |
75
+ | 0.1116 | 18.0 | 360 | 0.0789 | 0.4839 | 0.9678 | 0.9678 | nan | 0.9678 | 0.0 | 0.9678 |
76
+ | 0.3295 | 19.0 | 380 | 0.0791 | 0.4763 | 0.9526 | 0.9526 | nan | 0.9526 | 0.0 | 0.9526 |
77
+ | 0.0327 | 20.0 | 400 | 0.0792 | 0.4829 | 0.9658 | 0.9658 | nan | 0.9658 | 0.0 | 0.9658 |
78
+ | 0.2542 | 21.0 | 420 | 0.0787 | 0.4861 | 0.9722 | 0.9722 | nan | 0.9722 | 0.0 | 0.9722 |
79
+ | 0.1587 | 22.0 | 440 | 0.0783 | 0.4772 | 0.9543 | 0.9543 | nan | 0.9543 | 0.0 | 0.9543 |
80
+ | 0.2721 | 23.0 | 460 | 0.0804 | 0.4913 | 0.9825 | 0.9825 | nan | 0.9825 | 0.0 | 0.9825 |
81
+ | 0.0505 | 24.0 | 480 | 0.0781 | 0.4827 | 0.9655 | 0.9655 | nan | 0.9655 | 0.0 | 0.9655 |
82
+ | 0.1417 | 25.0 | 500 | 0.0801 | 0.4834 | 0.9669 | 0.9669 | nan | 0.9669 | 0.0 | 0.9669 |
83
+ | 0.1371 | 26.0 | 520 | 0.0777 | 0.4838 | 0.9676 | 0.9676 | nan | 0.9676 | 0.0 | 0.9676 |
84
+ | 0.1282 | 27.0 | 540 | 0.0773 | 0.4807 | 0.9613 | 0.9613 | nan | 0.9613 | 0.0 | 0.9613 |
85
+ | 0.057 | 28.0 | 560 | 0.0772 | 0.4829 | 0.9657 | 0.9657 | nan | 0.9657 | 0.0 | 0.9657 |
86
+ | 0.2592 | 29.0 | 580 | 0.0807 | 0.4872 | 0.9744 | 0.9744 | nan | 0.9744 | 0.0 | 0.9744 |
87
+ | 0.1687 | 30.0 | 600 | 0.0794 | 0.4825 | 0.9649 | 0.9649 | nan | 0.9649 | 0.0 | 0.9649 |
88
+ | 0.499 | 31.0 | 620 | 0.0805 | 0.4853 | 0.9706 | 0.9706 | nan | 0.9706 | 0.0 | 0.9706 |
89
+ | 0.1584 | 32.0 | 640 | 0.0790 | 0.4845 | 0.9691 | 0.9691 | nan | 0.9691 | 0.0 | 0.9691 |
90
+ | 0.0689 | 33.0 | 660 | 0.0785 | 0.4845 | 0.9690 | 0.9690 | nan | 0.9690 | 0.0 | 0.9690 |
91
+ | 1.3764 | 34.0 | 680 | 0.0790 | 0.4848 | 0.9696 | 0.9696 | nan | 0.9696 | 0.0 | 0.9696 |
92
+ | 0.2597 | 35.0 | 700 | 0.0808 | 0.4875 | 0.9751 | 0.9751 | nan | 0.9751 | 0.0 | 0.9751 |
93
+ | 1.0757 | 36.0 | 720 | 0.0761 | 0.4841 | 0.9681 | 0.9681 | nan | 0.9681 | 0.0 | 0.9681 |
94
+ | 0.6112 | 37.0 | 740 | 0.0779 | 0.4825 | 0.9650 | 0.9650 | nan | 0.9650 | 0.0 | 0.9650 |
95
+ | 0.2899 | 38.0 | 760 | 0.0787 | 0.4796 | 0.9591 | 0.9591 | nan | 0.9591 | 0.0 | 0.9591 |
96
+ | 0.3402 | 39.0 | 780 | 0.0777 | 0.4838 | 0.9676 | 0.9676 | nan | 0.9676 | 0.0 | 0.9676 |
97
+ | 0.0183 | 40.0 | 800 | 0.0771 | 0.4829 | 0.9657 | 0.9657 | nan | 0.9657 | 0.0 | 0.9657 |
98
+ | 0.1407 | 41.0 | 820 | 0.0774 | 0.4809 | 0.9617 | 0.9617 | nan | 0.9617 | 0.0 | 0.9617 |
99
+ | 0.4045 | 42.0 | 840 | 0.0767 | 0.4819 | 0.9638 | 0.9638 | nan | 0.9638 | 0.0 | 0.9638 |
100
+ | 0.2159 | 43.0 | 860 | 0.0780 | 0.4850 | 0.9699 | 0.9699 | nan | 0.9699 | 0.0 | 0.9699 |
101
+ | 0.0541 | 44.0 | 880 | 0.0768 | 0.4812 | 0.9624 | 0.9624 | nan | 0.9624 | 0.0 | 0.9624 |
102
+ | 0.0638 | 45.0 | 900 | 0.0774 | 0.4863 | 0.9726 | 0.9726 | nan | 0.9726 | 0.0 | 0.9726 |
103
+ | 0.0409 | 46.0 | 920 | 0.0788 | 0.4875 | 0.9749 | 0.9749 | nan | 0.9749 | 0.0 | 0.9749 |
104
+ | 0.1662 | 47.0 | 940 | 0.0774 | 0.4871 | 0.9743 | 0.9743 | nan | 0.9743 | 0.0 | 0.9743 |
105
+ | 0.1636 | 48.0 | 960 | 0.0783 | 0.4860 | 0.9720 | 0.9720 | nan | 0.9720 | 0.0 | 0.9720 |
106
+ | 0.033 | 49.0 | 980 | 0.0791 | 0.4882 | 0.9764 | 0.9764 | nan | 0.9764 | 0.0 | 0.9764 |
107
+ | 0.171 | 50.0 | 1000 | 0.0772 | 0.4863 | 0.9725 | 0.9725 | nan | 0.9725 | 0.0 | 0.9725 |
108
+
109
+
110
+ ### Framework versions
111
+
112
+ - Transformers 4.36.2
113
+ - Pytorch 1.11.0+cu115
114
+ - Datasets 2.15.0
115
+ - Tokenizers 0.15.0
config.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "nvidia/mit-b0",
3
+ "architectures": [
4
+ "SegformerForSemanticSegmentation"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "classifier_dropout_prob": 0.1,
8
+ "decoder_hidden_size": 256,
9
+ "depths": [
10
+ 2,
11
+ 2,
12
+ 2,
13
+ 2
14
+ ],
15
+ "downsampling_rates": [
16
+ 1,
17
+ 4,
18
+ 8,
19
+ 16
20
+ ],
21
+ "drop_path_rate": 0.1,
22
+ "hidden_act": "gelu",
23
+ "hidden_dropout_prob": 0.0,
24
+ "hidden_sizes": [
25
+ 32,
26
+ 64,
27
+ 160,
28
+ 256
29
+ ],
30
+ "id2label": {
31
+ "0": "unlabeled",
32
+ "1": "circuit"
33
+ },
34
+ "image_size": 224,
35
+ "initializer_range": 0.02,
36
+ "label2id": {
37
+ "circuit": 1,
38
+ "unlabeled": 0
39
+ },
40
+ "layer_norm_eps": 1e-06,
41
+ "mlp_ratios": [
42
+ 4,
43
+ 4,
44
+ 4,
45
+ 4
46
+ ],
47
+ "model_type": "segformer",
48
+ "num_attention_heads": [
49
+ 1,
50
+ 2,
51
+ 5,
52
+ 8
53
+ ],
54
+ "num_channels": 3,
55
+ "num_encoder_blocks": 4,
56
+ "patch_sizes": [
57
+ 7,
58
+ 3,
59
+ 3,
60
+ 3
61
+ ],
62
+ "reshape_last_stage": true,
63
+ "semantic_loss_ignore_index": 255,
64
+ "sr_ratios": [
65
+ 8,
66
+ 4,
67
+ 2,
68
+ 1
69
+ ],
70
+ "strides": [
71
+ 4,
72
+ 2,
73
+ 2,
74
+ 2
75
+ ],
76
+ "torch_dtype": "float32",
77
+ "transformers_version": "4.36.2"
78
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c58298256d3f570908e5d6611a81762ec24b4dd2bc3ae2504f8c6cca642ac36
3
+ size 14884776
runs/Dec23_19-02-58_Centauri/events.out.tfevents.1703325781.Centauri.43660.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d617fbcfe48df199488293e333909aca927031f314efd1d12e276357fbd74f5c
3
+ size 195452
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91b7bf23908d9d8f3c1fdb7da49673cb851d9165981ede105d880f7d06652004
3
+ size 4271