Hugging Face's logo

yiming19
/
segformer-b0-finetuned-segments-construction-1

Image Segmentation
Transformers
PyTorch
segformer
vision
Generated from Trainer
Inference Endpoints
Model card Files Community
2
yiming19 commited on
Commit
3b8ba18
·
1 Parent(s): 05ba053

End of training

Browse files
Files changed (6) hide show
  1. pytorch_model.bin +1 -1
  2. segformer-b0-finetuned-segments-construction-outputs/README.md +0 -117
  3. segformer-b0-finetuned-segments-construction-outputs/config.json +0 -96
  4. segformer-b0-finetuned-segments-construction-outputs/pytorch_model.bin +0 -3
  5. segformer-b0-finetuned-segments-construction-outputs/training_args.bin +0 -3
  6. training_args.bin +1 -1
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:00eeea3a83fecf657a45edfa9b390dda6be1248b48c05aea838d7bb7b4e15444
3
  size 14941005
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1066f9fd80f41bd2a6aee8e5acbe78427ed3362fc5c80015c913bf236f6143e6
3
  size 14941005
segformer-b0-finetuned-segments-construction-outputs/README.md DELETED
@@ -1,117 +0,0 @@
1
- ---
2
- license: other
3
- tags:
4
- - vision
5
- - image-segmentation
6
- - generated_from_trainer
7
- model-index:
8
- - name: segformer-b0-finetuned-segments-construction-1
9
- results: []
10
- ---
11
-
12
- <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
- should probably proofread and complete it, then remove this comment. -->
14
-
15
- # segformer-b0-finetuned-segments-construction-1
16
-
17
- This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on the yiming19/construction_place dataset.
18
- It achieves the following results on the evaluation set:
19
- - Loss: 0.2796
20
- - Mean Iou: 0.3218
21
- - Mean Accuracy: 0.5305
22
- - Overall Accuracy: 0.9276
23
- - Accuracy Unlabeled: nan
24
- - Accuracy Ruler: 0.8954
25
- - Accuracy Socket: 0.0
26
- - Accuracy Wall: 0.9644
27
- - Accuracy Window: nan
28
- - Accuracy Heater: nan
29
- - Accuracy Floor: 0.6710
30
- - Accuracy Ceiling: 0.0
31
- - Accuracy Skirting: nan
32
- - Accuracy Door: 0.6525
33
- - Accuracy Light: nan
34
- - Iou Unlabeled: nan
35
- - Iou Ruler: 0.7222
36
- - Iou Socket: 0.0
37
- - Iou Wall: 0.9553
38
- - Iou Window: 0.0
39
- - Iou Heater: nan
40
- - Iou Floor: 0.2630
41
- - Iou Ceiling: 0.0
42
- - Iou Skirting: 0.0
43
- - Iou Door: 0.6342
44
- - Iou Light: nan
45
-
46
- ## Model description
47
-
48
- More information needed
49
-
50
- ## Intended uses & limitations
51
-
52
- More information needed
53
-
54
- ## Training and evaluation data
55
-
56
- More information needed
57
-
58
- ## Training procedure
59
-
60
- ### Training hyperparameters
61
-
62
- The following hyperparameters were used during training:
63
- - learning_rate: 6e-05
64
- - train_batch_size: 2
65
- - eval_batch_size: 2
66
- - seed: 42
67
- - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
68
- - lr_scheduler_type: linear
69
- - num_epochs: 50
70
-
71
- ### Training results
72
-
73
- | Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Unlabeled | Accuracy Ruler | Accuracy Socket | Accuracy Wall | Accuracy Window | Accuracy Heater | Accuracy Floor | Accuracy Ceiling | Accuracy Skirting | Accuracy Door | Accuracy Light | Iou Unlabeled | Iou Ruler | Iou Socket | Iou Wall | Iou Window | Iou Heater | Iou Floor | Iou Ceiling | Iou Skirting | Iou Door | Iou Light |
74
- |:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:------------------:|:--------------:|:---------------:|:-------------:|:---------------:|:---------------:|:--------------:|:----------------:|:-----------------:|:-------------:|:--------------:|:-------------:|:---------:|:----------:|:--------:|:----------:|:----------:|:---------:|:-----------:|:------------:|:--------:|:---------:|
75
- | 1.8126 | 1.43 | 20 | 2.1233 | 0.1955 | 0.5160 | 0.8448 | nan | 0.8191 | 0.0 | 0.8868 | nan | nan | 0.9618 | 0.0 | nan | 0.4281 | nan | 0.0 | 0.5555 | 0.0 | 0.8845 | 0.0 | 0.0 | 0.2971 | 0.0 | 0.0 | 0.4135 | 0.0 |
76
- | 1.905 | 2.86 | 40 | 1.3611 | 0.1827 | 0.4921 | 0.8505 | nan | 0.9275 | 0.0 | 0.9139 | nan | nan | 0.9627 | 0.0 | nan | 0.1484 | nan | nan | 0.5404 | 0.0 | 0.9095 | 0.0 | 0.0 | 0.2289 | 0.0 | 0.0 | 0.1484 | 0.0 |
77
- | 1.1072 | 4.29 | 60 | 1.0502 | 0.2327 | 0.5517 | 0.8903 | nan | 0.9108 | 0.0 | 0.9266 | nan | nan | 0.9367 | 0.0 | nan | 0.5360 | nan | nan | 0.5301 | 0.0 | 0.9206 | 0.0 | 0.0 | 0.3475 | 0.0 | 0.0 | 0.5284 | 0.0 |
78
- | 1.0076 | 5.71 | 80 | 0.8802 | 0.2744 | 0.5609 | 0.9089 | nan | 0.8208 | 0.0 | 0.9410 | nan | nan | 0.9532 | 0.0 | nan | 0.6505 | nan | nan | 0.5500 | 0.0 | 0.9277 | 0.0 | 0.0 | 0.3688 | 0.0 | 0.0 | 0.6227 | nan |
79
- | 1.5533 | 7.14 | 100 | 0.8991 | 0.2846 | 0.5514 | 0.8878 | nan | 0.8918 | 0.0 | 0.9243 | nan | nan | 0.9591 | 0.0 | nan | 0.5332 | nan | nan | 0.5262 | 0.0 | 0.9169 | 0.0 | nan | 0.3209 | 0.0 | 0.0 | 0.5132 | nan |
80
- | 0.9912 | 8.57 | 120 | 0.9340 | 0.2891 | 0.5652 | 0.8854 | nan | 0.9478 | 0.0 | 0.9151 | nan | nan | 0.9438 | 0.0 | nan | 0.5844 | nan | nan | 0.5059 | 0.0 | 0.9098 | 0.0 | nan | 0.3424 | 0.0 | 0.0 | 0.5544 | nan |
81
- | 0.784 | 10.0 | 140 | 0.7017 | 0.3140 | 0.5984 | 0.9173 | nan | 0.9136 | 0.0 | 0.9305 | nan | nan | 0.8971 | 0.0 | nan | 0.8493 | nan | nan | 0.5324 | 0.0 | 0.9224 | 0.0 | 0.0 | 0.5805 | 0.0 | 0.0 | 0.7909 | nan |
82
- | 0.5636 | 11.43 | 160 | 0.6925 | 0.3573 | 0.5978 | 0.9280 | nan | 0.8714 | 0.0 | 0.9412 | nan | nan | 0.8868 | 0.0 | nan | 0.8876 | nan | nan | 0.5701 | 0.0 | 0.9308 | 0.0 | nan | 0.5638 | 0.0 | 0.0 | 0.7935 | nan |
83
- | 1.0692 | 12.86 | 180 | 0.7313 | 0.2931 | 0.5724 | 0.8981 | nan | 0.9587 | 0.0 | 0.9231 | nan | nan | 0.8880 | 0.0 | nan | 0.6647 | nan | nan | 0.4988 | 0.0 | 0.9182 | 0.0 | nan | 0.3342 | 0.0 | 0.0 | 0.5932 | nan |
84
- | 0.7603 | 14.29 | 200 | 0.6907 | 0.2577 | 0.5744 | 0.9001 | nan | 0.9619 | 0.0 | 0.9251 | nan | nan | 0.8930 | 0.0 | nan | 0.6661 | nan | nan | 0.4939 | 0.0 | 0.9208 | 0.0 | 0.0 | 0.3219 | 0.0 | 0.0 | 0.5824 | nan |
85
- | 0.9509 | 15.71 | 220 | 0.5110 | 0.3682 | 0.6069 | 0.9324 | nan | 0.9355 | 0.0 | 0.9417 | nan | nan | 0.8453 | 0.0 | nan | 0.9191 | nan | nan | 0.5671 | 0.0 | 0.9334 | 0.0 | nan | 0.6050 | 0.0 | 0.0 | 0.8403 | nan |
86
- | 0.4254 | 17.14 | 240 | 0.5925 | 0.2961 | 0.5629 | 0.9023 | nan | 0.9646 | 0.0 | 0.9295 | nan | nan | 0.8261 | 0.0 | nan | 0.6569 | nan | nan | 0.5302 | 0.0 | 0.9243 | 0.0 | nan | 0.3138 | 0.0 | 0.0 | 0.6009 | nan |
87
- | 0.3839 | 18.57 | 260 | 0.4226 | 0.3537 | 0.5479 | 0.9367 | nan | 0.9108 | 0.0 | 0.9540 | nan | nan | 0.5102 | 0.0 | nan | 0.9124 | nan | nan | 0.6643 | 0.0 | 0.9426 | 0.0 | nan | 0.3868 | 0.0 | 0.0 | 0.8361 | nan |
88
- | 0.7441 | 20.0 | 280 | 0.5084 | 0.3533 | 0.5993 | 0.9277 | nan | 0.9691 | 0.0 | 0.9391 | nan | nan | 0.8075 | 0.0 | nan | 0.8801 | nan | nan | 0.5527 | 0.0 | 0.9333 | 0.0 | nan | 0.5197 | 0.0 | 0.0 | 0.8208 | nan |
89
- | 0.4374 | 21.43 | 300 | 0.4683 | 0.3038 | 0.5549 | 0.9173 | nan | 0.9662 | 0.0 | 0.9480 | nan | nan | 0.7594 | 0.0 | nan | 0.6558 | nan | nan | 0.6024 | 0.0 | 0.9419 | 0.0 | nan | 0.2804 | 0.0 | 0.0 | 0.6056 | nan |
90
- | 0.6224 | 22.86 | 320 | 0.4100 | 0.3810 | 0.5960 | 0.9374 | nan | 0.9704 | 0.0 | 0.9460 | nan | nan | 0.7131 | 0.0 | nan | 0.9467 | nan | nan | 0.5986 | 0.0 | 0.9401 | 0.0 | nan | 0.6197 | 0.0 | 0.0 | 0.8898 | nan |
91
- | 0.4473 | 24.29 | 340 | 0.3933 | 0.3368 | 0.5431 | 0.9336 | nan | 0.9212 | 0.0 | 0.9620 | nan | nan | 0.6197 | 0.0 | nan | 0.7556 | nan | nan | 0.7221 | 0.0 | 0.9521 | 0.0 | nan | 0.2958 | 0.0 | 0.0 | 0.7245 | nan |
92
- | 0.3364 | 25.71 | 360 | 0.4336 | 0.2976 | 0.5125 | 0.9134 | nan | 0.9408 | 0.0 | 0.9544 | nan | nan | 0.6075 | 0.0 | nan | 0.5721 | nan | nan | 0.6918 | 0.0 | 0.9481 | 0.0 | nan | 0.1998 | 0.0 | 0.0 | 0.5411 | nan |
93
- | 0.281 | 27.14 | 380 | 0.3795 | 0.3689 | 0.5760 | 0.9420 | nan | 0.9250 | 0.0 | 0.9589 | nan | nan | 0.6859 | 0.0 | nan | 0.8863 | nan | nan | 0.7108 | 0.0 | 0.9518 | 0.0 | nan | 0.4576 | 0.0 | 0.0 | 0.8305 | nan |
94
- | 0.3198 | 28.57 | 400 | 0.4023 | 0.3158 | 0.5143 | 0.9238 | nan | 0.9120 | 0.0 | 0.9610 | nan | nan | 0.5580 | 0.0 | nan | 0.6550 | nan | nan | 0.7210 | 0.0 | 0.9519 | 0.0 | nan | 0.2238 | 0.0 | 0.0 | 0.6293 | nan |
95
- | 0.4624 | 30.0 | 420 | 0.3565 | 0.3770 | 0.5774 | 0.9475 | nan | 0.9408 | 0.0 | 0.9613 | nan | nan | 0.6287 | 0.0 | nan | 0.9337 | nan | nan | 0.6855 | 0.0 | 0.9539 | 0.0 | nan | 0.4943 | 0.0 | 0.0 | 0.8827 | nan |
96
- | 0.2356 | 31.43 | 440 | 0.3940 | 0.3100 | 0.5349 | 0.9221 | nan | 0.9268 | 0.0 | 0.9602 | nan | nan | 0.7187 | 0.0 | nan | 0.6040 | nan | nan | 0.7005 | 0.0 | 0.9536 | 0.0 | nan | 0.2474 | 0.0 | 0.0 | 0.5781 | nan |
97
- | 0.3931 | 32.86 | 460 | 0.3516 | 0.3162 | 0.5570 | 0.9258 | nan | 0.9338 | 0.0 | 0.9598 | nan | nan | 0.8124 | 0.0 | nan | 0.6362 | nan | nan | 0.6824 | 0.0 | 0.9542 | 0.0 | nan | 0.2888 | 0.0 | 0.0 | 0.6040 | nan |
98
- | 0.2431 | 34.29 | 480 | 0.4011 | 0.2955 | 0.5291 | 0.9138 | nan | 0.9242 | 0.0 | 0.9583 | nan | nan | 0.7864 | 0.0 | nan | 0.5058 | nan | nan | 0.6954 | 0.0 | 0.9520 | 0.0 | nan | 0.2331 | 0.0 | 0.0 | 0.4832 | nan |
99
- | 0.2131 | 35.71 | 500 | 0.2847 | 0.3764 | 0.5613 | 0.9487 | nan | 0.8877 | 0.0 | 0.9679 | nan | nan | 0.6103 | 0.0 | nan | 0.9020 | nan | nan | 0.7330 | 0.0 | 0.9571 | 0.0 | nan | 0.4539 | 0.0 | 0.0 | 0.8669 | nan |
100
- | 0.4151 | 37.14 | 520 | 0.3176 | 0.3186 | 0.5239 | 0.9256 | nan | 0.8930 | 0.0 | 0.9640 | nan | nan | 0.6505 | 0.0 | nan | 0.6356 | nan | nan | 0.7251 | 0.0 | 0.9544 | 0.0 | nan | 0.2507 | 0.0 | 0.0 | 0.6187 | nan |
101
- | 0.2408 | 38.57 | 540 | 0.3267 | 0.3071 | 0.5361 | 0.9208 | nan | 0.9264 | 0.0 | 0.9600 | nan | nan | 0.7441 | 0.0 | nan | 0.5859 | nan | nan | 0.6868 | 0.0 | 0.9538 | 0.0 | nan | 0.2526 | 0.0 | 0.0 | 0.5635 | nan |
102
- | 0.2274 | 40.0 | 560 | 0.2875 | 0.3396 | 0.5471 | 0.9349 | nan | 0.9098 | 0.0 | 0.9626 | nan | nan | 0.6456 | 0.0 | nan | 0.7649 | nan | nan | 0.7018 | 0.0 | 0.9547 | 0.0 | nan | 0.3216 | 0.0 | 0.0 | 0.7387 | nan |
103
- | 0.2452 | 41.43 | 580 | 0.2998 | 0.3181 | 0.5357 | 0.9279 | nan | 0.9089 | 0.0 | 0.9642 | nan | nan | 0.6932 | 0.0 | nan | 0.6480 | nan | nan | 0.7057 | 0.0 | 0.9562 | 0.0 | nan | 0.2578 | 0.0 | 0.0 | 0.6252 | nan |
104
- | 0.2922 | 42.86 | 600 | 0.2957 | 0.3131 | 0.5246 | 0.9255 | nan | 0.9056 | 0.0 | 0.9643 | nan | nan | 0.6535 | 0.0 | nan | 0.6242 | nan | nan | 0.7103 | 0.0 | 0.9563 | 0.0 | nan | 0.2347 | 0.0 | 0.0 | 0.6037 | nan |
105
- | 0.3704 | 44.29 | 620 | 0.3290 | 0.3172 | 0.5429 | 0.9247 | nan | 0.9246 | 0.0 | 0.9583 | nan | nan | 0.7123 | 0.0 | nan | 0.6621 | nan | nan | 0.6856 | 0.0 | 0.9527 | 0.0 | nan | 0.2707 | 0.0 | 0.0 | 0.6286 | nan |
106
- | 0.2482 | 45.71 | 640 | 0.2995 | 0.3251 | 0.5368 | 0.9276 | nan | 0.9018 | 0.0 | 0.9617 | nan | nan | 0.6795 | 0.0 | nan | 0.6779 | nan | nan | 0.7154 | 0.0 | 0.9538 | 0.0 | nan | 0.2790 | 0.0 | 0.0 | 0.6528 | nan |
107
- | 0.2798 | 47.14 | 660 | 0.2808 | 0.3323 | 0.5374 | 0.9319 | nan | 0.8938 | 0.0 | 0.9644 | nan | nan | 0.6554 | 0.0 | nan | 0.7110 | nan | nan | 0.7218 | 0.0 | 0.9554 | 0.0 | nan | 0.2919 | 0.0 | 0.0 | 0.6894 | nan |
108
- | 0.2746 | 48.57 | 680 | 0.2695 | 0.3265 | 0.5341 | 0.9299 | nan | 0.8947 | 0.0 | 0.9642 | nan | nan | 0.6597 | 0.0 | nan | 0.6861 | nan | nan | 0.7198 | 0.0 | 0.9554 | 0.0 | nan | 0.2735 | 0.0 | 0.0 | 0.6633 | nan |
109
- | 0.2169 | 50.0 | 700 | 0.2796 | 0.3218 | 0.5305 | 0.9276 | nan | 0.8954 | 0.0 | 0.9644 | nan | nan | 0.6710 | 0.0 | nan | 0.6525 | nan | nan | 0.7222 | 0.0 | 0.9553 | 0.0 | nan | 0.2630 | 0.0 | 0.0 | 0.6342 | nan |
110
-
111
-
112
- ### Framework versions
113
-
114
- - Transformers 4.25.1
115
- - Pytorch 1.13.1
116
- - Datasets 2.10.1
117
- - Tokenizers 0.13.0.dev0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
segformer-b0-finetuned-segments-construction-outputs/config.json DELETED
@@ -1,96 +0,0 @@
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": "ruler",
33
- "2": "socket",
34
- "3": "wall",
35
- "4": "window",
36
- "5": "heater",
37
- "6": "floor",
38
- "7": "ceiling",
39
- "8": "skirting",
40
- "9": "door",
41
- "10": "light"
42
- },
43
- "image_size": 224,
44
- "initializer_range": 0.02,
45
- "label2id": {
46
- "ceiling": 7,
47
- "door": 9,
48
- "floor": 6,
49
- "heater": 5,
50
- "light": 10,
51
- "ruler": 1,
52
- "skirting": 8,
53
- "socket": 2,
54
- "unlabeled": 0,
55
- "wall": 3,
56
- "window": 4
57
- },
58
- "layer_norm_eps": 1e-06,
59
- "mlp_ratios": [
60
- 4,
61
- 4,
62
- 4,
63
- 4
64
- ],
65
- "model_type": "segformer",
66
- "num_attention_heads": [
67
- 1,
68
- 2,
69
- 5,
70
- 8
71
- ],
72
- "num_channels": 3,
73
- "num_encoder_blocks": 4,
74
- "patch_sizes": [
75
- 7,
76
- 3,
77
- 3,
78
- 3
79
- ],
80
- "reshape_last_stage": true,
81
- "semantic_loss_ignore_index": 255,
82
- "sr_ratios": [
83
- 8,
84
- 4,
85
- 2,
86
- 1
87
- ],
88
- "strides": [
89
- 4,
90
- 2,
91
- 2,
92
- 2
93
- ],
94
- "torch_dtype": "float32",
95
- "transformers_version": "4.25.1"
96
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
segformer-b0-finetuned-segments-construction-outputs/pytorch_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:00eeea3a83fecf657a45edfa9b390dda6be1248b48c05aea838d7bb7b4e15444
3
- size 14941005
 
 
 
 
segformer-b0-finetuned-segments-construction-outputs/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d58fbd9bf4946ef25d9761f0566d98188d4ed5637376c7eca5ff8c56dc9e51bd
3
- size 3515
 
 
 
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d58fbd9bf4946ef25d9761f0566d98188d4ed5637376c7eca5ff8c56dc9e51bd
3
  size 3515
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a182fe45e17b5451aa84df459974b73d72344fd3cc5d00030cb09fc7328f1aec
3
  size 3515