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
3074525
•
1 Parent(s): 041c776

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_21-07-36_Centauri/events.out.tfevents.1717848467.Centauri.28876.0 +3 -0
  5. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ base_model: nvidia/mit-b0
4
+ tags:
5
+ - vision
6
+ - image-segmentation
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: segformer-b0-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-b0-miic-tl
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: 0.4495
21
+ - Mean Iou: 0.4202
22
+ - Mean Accuracy: 0.8404
23
+ - Overall Accuracy: 0.8404
24
+ - Accuracy Unlabeled: nan
25
+ - Accuracy Circuit: 0.8404
26
+ - Iou Unlabeled: 0.0
27
+ - Iou Circuit: 0.8404
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
+ | 0.465 | 1.0 | 20 | 0.6113 | 0.3296 | 0.6593 | 0.6593 | nan | 0.6593 | 0.0 | 0.6593 |
59
+ | 0.4071 | 2.0 | 40 | 0.4866 | 0.3345 | 0.6689 | 0.6689 | nan | 0.6689 | 0.0 | 0.6689 |
60
+ | 0.4429 | 3.0 | 60 | 0.3963 | 0.3623 | 0.7245 | 0.7245 | nan | 0.7245 | 0.0 | 0.7245 |
61
+ | 0.2408 | 4.0 | 80 | 0.3606 | 0.4257 | 0.8515 | 0.8515 | nan | 0.8515 | 0.0 | 0.8515 |
62
+ | 0.2002 | 5.0 | 100 | 0.3594 | 0.4345 | 0.8690 | 0.8690 | nan | 0.8690 | 0.0 | 0.8690 |
63
+ | 0.1885 | 6.0 | 120 | 0.3702 | 0.4291 | 0.8583 | 0.8583 | nan | 0.8583 | 0.0 | 0.8583 |
64
+ | 0.4626 | 7.0 | 140 | 0.3858 | 0.4128 | 0.8256 | 0.8256 | nan | 0.8256 | 0.0 | 0.8256 |
65
+ | 0.0865 | 8.0 | 160 | 0.3578 | 0.4456 | 0.8912 | 0.8912 | nan | 0.8912 | 0.0 | 0.8912 |
66
+ | 0.0752 | 9.0 | 180 | 0.3595 | 0.4387 | 0.8774 | 0.8774 | nan | 0.8774 | 0.0 | 0.8774 |
67
+ | 0.2567 | 10.0 | 200 | 0.4103 | 0.3981 | 0.7961 | 0.7961 | nan | 0.7961 | 0.0 | 0.7961 |
68
+ | 0.1419 | 11.0 | 220 | 0.4053 | 0.4229 | 0.8458 | 0.8458 | nan | 0.8458 | 0.0 | 0.8458 |
69
+ | 0.0623 | 12.0 | 240 | 0.3798 | 0.4415 | 0.8830 | 0.8830 | nan | 0.8830 | 0.0 | 0.8830 |
70
+ | 0.3336 | 13.0 | 260 | 0.3855 | 0.4374 | 0.8748 | 0.8748 | nan | 0.8748 | 0.0 | 0.8748 |
71
+ | 0.1283 | 14.0 | 280 | 0.3931 | 0.4368 | 0.8736 | 0.8736 | nan | 0.8736 | 0.0 | 0.8736 |
72
+ | 0.5155 | 15.0 | 300 | 0.4108 | 0.4268 | 0.8535 | 0.8535 | nan | 0.8535 | 0.0 | 0.8535 |
73
+ | 1.2662 | 16.0 | 320 | 0.4062 | 0.4328 | 0.8656 | 0.8656 | nan | 0.8656 | 0.0 | 0.8656 |
74
+ | 0.2631 | 17.0 | 340 | 0.3825 | 0.4464 | 0.8929 | 0.8929 | nan | 0.8929 | 0.0 | 0.8929 |
75
+ | 0.1751 | 18.0 | 360 | 0.3981 | 0.4335 | 0.8669 | 0.8669 | nan | 0.8669 | 0.0 | 0.8669 |
76
+ | 0.243 | 19.0 | 380 | 0.3963 | 0.4436 | 0.8872 | 0.8872 | nan | 0.8872 | 0.0 | 0.8872 |
77
+ | 0.1779 | 20.0 | 400 | 0.4413 | 0.4060 | 0.8119 | 0.8119 | nan | 0.8119 | 0.0 | 0.8119 |
78
+ | 0.0682 | 21.0 | 420 | 0.4106 | 0.4363 | 0.8725 | 0.8725 | nan | 0.8725 | 0.0 | 0.8725 |
79
+ | 0.2943 | 22.0 | 440 | 0.4052 | 0.4386 | 0.8771 | 0.8771 | nan | 0.8771 | 0.0 | 0.8771 |
80
+ | 0.118 | 23.0 | 460 | 0.4260 | 0.4197 | 0.8394 | 0.8394 | nan | 0.8394 | 0.0 | 0.8394 |
81
+ | 0.0865 | 24.0 | 480 | 0.4023 | 0.4270 | 0.8540 | 0.8540 | nan | 0.8540 | 0.0 | 0.8540 |
82
+ | 0.1693 | 25.0 | 500 | 0.4276 | 0.4199 | 0.8399 | 0.8399 | nan | 0.8399 | 0.0 | 0.8399 |
83
+ | 0.1778 | 26.0 | 520 | 0.4044 | 0.4409 | 0.8818 | 0.8818 | nan | 0.8818 | 0.0 | 0.8818 |
84
+ | 0.3617 | 27.0 | 540 | 0.4405 | 0.4121 | 0.8242 | 0.8242 | nan | 0.8242 | 0.0 | 0.8242 |
85
+ | 0.1688 | 28.0 | 560 | 0.4333 | 0.4234 | 0.8467 | 0.8467 | nan | 0.8467 | 0.0 | 0.8467 |
86
+ | 0.282 | 29.0 | 580 | 0.4060 | 0.4365 | 0.8730 | 0.8730 | nan | 0.8730 | 0.0 | 0.8730 |
87
+ | 0.0992 | 30.0 | 600 | 0.4297 | 0.4196 | 0.8393 | 0.8393 | nan | 0.8393 | 0.0 | 0.8393 |
88
+ | 1.379 | 31.0 | 620 | 0.4389 | 0.4193 | 0.8386 | 0.8386 | nan | 0.8386 | 0.0 | 0.8386 |
89
+ | 0.1355 | 32.0 | 640 | 0.4438 | 0.4205 | 0.8410 | 0.8410 | nan | 0.8410 | 0.0 | 0.8410 |
90
+ | 0.1067 | 33.0 | 660 | 0.4271 | 0.4299 | 0.8598 | 0.8598 | nan | 0.8598 | 0.0 | 0.8598 |
91
+ | 1.0659 | 34.0 | 680 | 0.4490 | 0.4063 | 0.8125 | 0.8125 | nan | 0.8125 | 0.0 | 0.8125 |
92
+ | 0.1481 | 35.0 | 700 | 0.4317 | 0.4279 | 0.8557 | 0.8557 | nan | 0.8557 | 0.0 | 0.8557 |
93
+ | 1.385 | 36.0 | 720 | 0.4215 | 0.4322 | 0.8644 | 0.8644 | nan | 0.8644 | 0.0 | 0.8644 |
94
+ | 0.3081 | 37.0 | 740 | 0.4564 | 0.4089 | 0.8178 | 0.8178 | nan | 0.8178 | 0.0 | 0.8178 |
95
+ | 0.1989 | 38.0 | 760 | 0.4345 | 0.4241 | 0.8482 | 0.8482 | nan | 0.8482 | 0.0 | 0.8482 |
96
+ | 0.1752 | 39.0 | 780 | 0.4230 | 0.4302 | 0.8605 | 0.8605 | nan | 0.8605 | 0.0 | 0.8605 |
97
+ | 0.1489 | 40.0 | 800 | 0.4253 | 0.4231 | 0.8462 | 0.8462 | nan | 0.8462 | 0.0 | 0.8462 |
98
+ | 0.1769 | 41.0 | 820 | 0.4184 | 0.4275 | 0.8549 | 0.8549 | nan | 0.8549 | 0.0 | 0.8549 |
99
+ | 0.1927 | 42.0 | 840 | 0.4162 | 0.4314 | 0.8629 | 0.8629 | nan | 0.8629 | 0.0 | 0.8629 |
100
+ | 0.2442 | 43.0 | 860 | 0.4321 | 0.4234 | 0.8468 | 0.8468 | nan | 0.8468 | 0.0 | 0.8468 |
101
+ | 0.2513 | 44.0 | 880 | 0.4280 | 0.4258 | 0.8515 | 0.8515 | nan | 0.8515 | 0.0 | 0.8515 |
102
+ | 0.7221 | 45.0 | 900 | 0.4449 | 0.4190 | 0.8380 | 0.8380 | nan | 0.8380 | 0.0 | 0.8380 |
103
+ | 0.0675 | 46.0 | 920 | 0.4369 | 0.4210 | 0.8419 | 0.8419 | nan | 0.8419 | 0.0 | 0.8419 |
104
+ | 0.1256 | 47.0 | 940 | 0.4159 | 0.4313 | 0.8625 | 0.8625 | nan | 0.8625 | 0.0 | 0.8625 |
105
+ | 0.1251 | 48.0 | 960 | 0.4312 | 0.4249 | 0.8498 | 0.8498 | nan | 0.8498 | 0.0 | 0.8498 |
106
+ | 0.2183 | 49.0 | 980 | 0.4340 | 0.4262 | 0.8524 | 0.8524 | nan | 0.8524 | 0.0 | 0.8524 |
107
+ | 0.2148 | 50.0 | 1000 | 0.4495 | 0.4202 | 0.8404 | 0.8404 | nan | 0.8404 | 0.0 | 0.8404 |
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:b82ce65a26c7c35b3e0a4624f474cfb810bc8d9f8aba449bd3ca37b1e6766be9
3
+ size 14884776
runs/Jun08_21-07-36_Centauri/events.out.tfevents.1717848467.Centauri.28876.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0951d2d7dff5f3ae046285487e94e9edc95d47b97e3ce8cc174fcb602b11a393
3
+ size 195434
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e805f92470616cb7d2acbffab0ec5de90b1003c3fcb61b698e0c8efbe49d898
3
+ size 4271