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
96506f2
·
verified ·
1 Parent(s): fe18d4e

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/Jun08_23-00-04_Centauri/events.out.tfevents.1717855213.Centauri.42668.0 +3 -0
  5. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ base_model: nvidia/mit-b1
4
+ tags:
5
+ - vision
6
+ - image-segmentation
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: segformer-b1-miic-tl
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-b1-miic-tl
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: 0.1915
21
+ - Mean Iou: 0.4765
22
+ - Mean Accuracy: 0.9531
23
+ - Overall Accuracy: 0.9531
24
+ - Accuracy Unlabeled: nan
25
+ - Accuracy Circuit: 0.9531
26
+ - Iou Unlabeled: 0.0
27
+ - Iou Circuit: 0.9531
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
+ | 0.7961 | 1.0 | 20 | 0.5776 | 0.3160 | 0.6320 | 0.6320 | nan | 0.6320 | 0.0 | 0.6320 |
59
+ | 0.7261 | 2.0 | 40 | 0.4222 | 0.4655 | 0.9310 | 0.9310 | nan | 0.9310 | 0.0 | 0.9310 |
60
+ | 0.3132 | 3.0 | 60 | 0.2869 | 0.4478 | 0.8956 | 0.8956 | nan | 0.8956 | 0.0 | 0.8956 |
61
+ | 0.2224 | 4.0 | 80 | 0.2898 | 0.4817 | 0.9635 | 0.9635 | nan | 0.9635 | 0.0 | 0.9635 |
62
+ | 0.1641 | 5.0 | 100 | 0.2861 | 0.4733 | 0.9466 | 0.9466 | nan | 0.9466 | 0.0 | 0.9466 |
63
+ | 0.9802 | 6.0 | 120 | 0.3005 | 0.4790 | 0.9581 | 0.9581 | nan | 0.9581 | 0.0 | 0.9581 |
64
+ | 0.1633 | 7.0 | 140 | 0.2953 | 0.4397 | 0.8794 | 0.8794 | nan | 0.8794 | 0.0 | 0.8794 |
65
+ | 0.3674 | 8.0 | 160 | 0.2951 | 0.4809 | 0.9619 | 0.9619 | nan | 0.9619 | 0.0 | 0.9619 |
66
+ | 0.1632 | 9.0 | 180 | 0.3007 | 0.4740 | 0.9480 | 0.9480 | nan | 0.9480 | 0.0 | 0.9480 |
67
+ | 0.3719 | 10.0 | 200 | 0.2633 | 0.4687 | 0.9374 | 0.9374 | nan | 0.9374 | 0.0 | 0.9374 |
68
+ | 0.2061 | 11.0 | 220 | 0.2544 | 0.4575 | 0.9150 | 0.9150 | nan | 0.9150 | 0.0 | 0.9150 |
69
+ | 0.1756 | 12.0 | 240 | 0.2587 | 0.4856 | 0.9711 | 0.9711 | nan | 0.9711 | 0.0 | 0.9711 |
70
+ | 0.366 | 13.0 | 260 | 0.2458 | 0.4883 | 0.9765 | 0.9765 | nan | 0.9765 | 0.0 | 0.9765 |
71
+ | 0.2532 | 14.0 | 280 | 0.2742 | 0.4771 | 0.9543 | 0.9543 | nan | 0.9543 | 0.0 | 0.9543 |
72
+ | 0.144 | 15.0 | 300 | 0.2424 | 0.4612 | 0.9223 | 0.9223 | nan | 0.9223 | 0.0 | 0.9223 |
73
+ | 0.1314 | 16.0 | 320 | 0.2130 | 0.4745 | 0.9489 | 0.9489 | nan | 0.9489 | 0.0 | 0.9489 |
74
+ | 1.4391 | 17.0 | 340 | 0.2156 | 0.4813 | 0.9626 | 0.9626 | nan | 0.9626 | 0.0 | 0.9626 |
75
+ | 0.211 | 18.0 | 360 | 0.1995 | 0.4767 | 0.9533 | 0.9533 | nan | 0.9533 | 0.0 | 0.9533 |
76
+ | 0.0792 | 19.0 | 380 | 0.2052 | 0.4855 | 0.9710 | 0.9710 | nan | 0.9710 | 0.0 | 0.9710 |
77
+ | 1.1 | 20.0 | 400 | 0.1972 | 0.4712 | 0.9424 | 0.9424 | nan | 0.9424 | 0.0 | 0.9424 |
78
+ | 0.067 | 21.0 | 420 | 0.2015 | 0.4697 | 0.9394 | 0.9394 | nan | 0.9394 | 0.0 | 0.9394 |
79
+ | 0.1783 | 22.0 | 440 | 0.2100 | 0.4821 | 0.9642 | 0.9642 | nan | 0.9642 | 0.0 | 0.9642 |
80
+ | 0.1594 | 23.0 | 460 | 0.1989 | 0.4746 | 0.9491 | 0.9491 | nan | 0.9491 | 0.0 | 0.9491 |
81
+ | 0.2306 | 24.0 | 480 | 0.1957 | 0.4668 | 0.9337 | 0.9337 | nan | 0.9337 | 0.0 | 0.9337 |
82
+ | 0.9809 | 25.0 | 500 | 0.1971 | 0.4802 | 0.9603 | 0.9603 | nan | 0.9603 | 0.0 | 0.9603 |
83
+ | 0.1154 | 26.0 | 520 | 0.1957 | 0.4792 | 0.9585 | 0.9585 | nan | 0.9585 | 0.0 | 0.9585 |
84
+ | 0.2142 | 27.0 | 540 | 0.1945 | 0.4827 | 0.9655 | 0.9655 | nan | 0.9655 | 0.0 | 0.9655 |
85
+ | 0.177 | 28.0 | 560 | 0.1930 | 0.4725 | 0.9451 | 0.9451 | nan | 0.9451 | 0.0 | 0.9451 |
86
+ | 0.2003 | 29.0 | 580 | 0.1965 | 0.4827 | 0.9654 | 0.9654 | nan | 0.9654 | 0.0 | 0.9654 |
87
+ | 0.1977 | 30.0 | 600 | 0.1995 | 0.4861 | 0.9722 | 0.9722 | nan | 0.9722 | 0.0 | 0.9722 |
88
+ | 0.1671 | 31.0 | 620 | 0.1946 | 0.4760 | 0.9520 | 0.9520 | nan | 0.9520 | 0.0 | 0.9520 |
89
+ | 0.1449 | 32.0 | 640 | 0.1895 | 0.4642 | 0.9285 | 0.9285 | nan | 0.9285 | 0.0 | 0.9285 |
90
+ | 0.2587 | 33.0 | 660 | 0.1920 | 0.4810 | 0.9619 | 0.9619 | nan | 0.9619 | 0.0 | 0.9619 |
91
+ | 1.2053 | 34.0 | 680 | 0.1931 | 0.4790 | 0.9579 | 0.9579 | nan | 0.9579 | 0.0 | 0.9579 |
92
+ | 0.1107 | 35.0 | 700 | 0.1951 | 0.4824 | 0.9647 | 0.9647 | nan | 0.9647 | 0.0 | 0.9647 |
93
+ | 0.0821 | 36.0 | 720 | 0.1926 | 0.4788 | 0.9577 | 0.9577 | nan | 0.9577 | 0.0 | 0.9577 |
94
+ | 0.5034 | 37.0 | 740 | 0.1903 | 0.4656 | 0.9311 | 0.9311 | nan | 0.9311 | 0.0 | 0.9311 |
95
+ | 0.137 | 38.0 | 760 | 0.1892 | 0.4684 | 0.9368 | 0.9368 | nan | 0.9368 | 0.0 | 0.9368 |
96
+ | 0.2861 | 39.0 | 780 | 0.1911 | 0.4762 | 0.9524 | 0.9524 | nan | 0.9524 | 0.0 | 0.9524 |
97
+ | 0.965 | 40.0 | 800 | 0.1928 | 0.4716 | 0.9432 | 0.9432 | nan | 0.9432 | 0.0 | 0.9432 |
98
+ | 0.138 | 41.0 | 820 | 0.1926 | 0.4742 | 0.9483 | 0.9483 | nan | 0.9483 | 0.0 | 0.9483 |
99
+ | 0.0291 | 42.0 | 840 | 0.1888 | 0.4689 | 0.9378 | 0.9378 | nan | 0.9378 | 0.0 | 0.9378 |
100
+ | 0.0624 | 43.0 | 860 | 0.1895 | 0.4684 | 0.9369 | 0.9369 | nan | 0.9369 | 0.0 | 0.9369 |
101
+ | 0.0611 | 44.0 | 880 | 0.1915 | 0.4772 | 0.9545 | 0.9545 | nan | 0.9545 | 0.0 | 0.9545 |
102
+ | 0.0322 | 45.0 | 900 | 0.1893 | 0.4670 | 0.9340 | 0.9340 | nan | 0.9340 | 0.0 | 0.9340 |
103
+ | 0.0927 | 46.0 | 920 | 0.1901 | 0.4714 | 0.9428 | 0.9428 | nan | 0.9428 | 0.0 | 0.9428 |
104
+ | 0.1752 | 47.0 | 940 | 0.1897 | 0.4758 | 0.9516 | 0.9516 | nan | 0.9516 | 0.0 | 0.9516 |
105
+ | 0.1343 | 48.0 | 960 | 0.1906 | 0.4779 | 0.9559 | 0.9559 | nan | 0.9559 | 0.0 | 0.9559 |
106
+ | 0.0765 | 49.0 | 980 | 0.1903 | 0.4732 | 0.9464 | 0.9464 | nan | 0.9464 | 0.0 | 0.9464 |
107
+ | 0.048 | 50.0 | 1000 | 0.1915 | 0.4765 | 0.9531 | 0.9531 | nan | 0.9531 | 0.0 | 0.9531 |
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-b1",
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
+ 64,
26
+ 128,
27
+ 320,
28
+ 512
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:b0000c9158f01fd43a3442ec71a5c9e8b91bedfbd3f904b064d769544158be8a
3
+ size 54737376
runs/Jun08_23-00-04_Centauri/events.out.tfevents.1717855213.Centauri.42668.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92277be13ff76a745ca817c53ca189bb6e7503c9003209f5bf18a654ad43cb17
3
+ size 195480
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7b7038b7b516e3ac795730df2bf7de1cd62210ed1e3b411751a572c49169e28
3
+ size 4271