Hugging Face's logo

NICOPOI-9
/
segformer-b0-finetuned-morphpadver1-hgo-coord-v2

Image Segmentation
Transformers
Safetensors
segformer
vision
Generated from Trainer
Model card Files Community
NICOPOI-9 commited on
Commit
a3845d0
·
verified ·
1 Parent(s): c6374e5

End of training

Browse files
Files changed (4) hide show
  1. README.md +37 -37
  2. config.json +6 -6
  3. model.safetensors +2 -2
  4. training_args.bin +1 -1
README.md CHANGED
@@ -1,7 +1,7 @@
1
  ---
2
  library_name: transformers
3
  license: other
4
- base_model: nvidia/mit-b2
5
  tags:
6
  - vision
7
  - image-segmentation
@@ -16,20 +16,20 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  # segformer-b0-finetuned-morphpadver1-hgo-coord-v2
18
 
19
- This model is a fine-tuned version of [nvidia/mit-b2](https://huggingface.co/nvidia/mit-b2) on the NICOPOI-9/morphpad_coord_hgo_512_4class dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.2286
22
- - Mean Iou: 0.8128
23
- - Mean Accuracy: 0.8969
24
- - Overall Accuracy: 0.8968
25
- - Accuracy 0-0: 0.9119
26
- - Accuracy 0-90: 0.8833
27
- - Accuracy 90-0: 0.8951
28
- - Accuracy 90-90: 0.8974
29
- - Iou 0-0: 0.8200
30
- - Iou 0-90: 0.8185
31
- - Iou 90-0: 0.8144
32
- - Iou 90-90: 0.7983
33
 
34
  ## Model description
35
 
@@ -60,29 +60,29 @@ The following hyperparameters were used during training:
60
 
61
  | Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy 0-0 | Accuracy 0-90 | Accuracy 90-0 | Accuracy 90-90 | Iou 0-0 | Iou 0-90 | Iou 90-0 | Iou 90-90 |
62
  |:-------------:|:-------:|:-----:|:---------------:|:--------:|:-------------:|:----------------:|:------------:|:-------------:|:-------------:|:--------------:|:-------:|:--------:|:--------:|:---------:|
63
- | 1.1507 | 2.5445 | 4000 | 1.1730 | 0.2502 | 0.4074 | 0.4084 | 0.4143 | 0.2410 | 0.6535 | 0.3208 | 0.2753 | 0.2079 | 0.2790 | 0.2385 |
64
- | 1.0135 | 5.0891 | 8000 | 0.9857 | 0.3270 | 0.4992 | 0.4961 | 0.6108 | 0.4085 | 0.3399 | 0.6378 | 0.3508 | 0.3116 | 0.3093 | 0.3363 |
65
- | 0.8651 | 7.6336 | 12000 | 0.8655 | 0.3997 | 0.5634 | 0.5652 | 0.4675 | 0.8101 | 0.4588 | 0.5172 | 0.4234 | 0.3705 | 0.3925 | 0.4123 |
66
- | 0.7904 | 10.1781 | 16000 | 0.7801 | 0.4485 | 0.6141 | 0.6147 | 0.5644 | 0.4939 | 0.8116 | 0.5863 | 0.4541 | 0.4593 | 0.4161 | 0.4645 |
67
- | 0.9002 | 12.7226 | 20000 | 0.7177 | 0.4769 | 0.6460 | 0.6457 | 0.6775 | 0.6256 | 0.6334 | 0.6475 | 0.4691 | 0.4874 | 0.4857 | 0.4657 |
68
- | 0.6111 | 15.2672 | 24000 | 0.6339 | 0.5288 | 0.6790 | 0.6814 | 0.6149 | 0.9232 | 0.6051 | 0.5727 | 0.5528 | 0.4628 | 0.5587 | 0.5409 |
69
- | 0.5422 | 17.8117 | 28000 | 0.5576 | 0.5788 | 0.7312 | 0.7300 | 0.6673 | 0.7190 | 0.6918 | 0.8469 | 0.6206 | 0.5811 | 0.5793 | 0.5340 |
70
- | 0.5594 | 20.3562 | 32000 | 0.5073 | 0.6016 | 0.7470 | 0.7482 | 0.7632 | 0.7259 | 0.8431 | 0.6558 | 0.5749 | 0.6233 | 0.5720 | 0.6361 |
71
- | 0.6542 | 22.9008 | 36000 | 0.4921 | 0.6137 | 0.7580 | 0.7590 | 0.7073 | 0.8514 | 0.7415 | 0.7320 | 0.6381 | 0.5894 | 0.6460 | 0.5813 |
72
- | 0.4827 | 25.4453 | 40000 | 0.4701 | 0.6321 | 0.7736 | 0.7730 | 0.7499 | 0.7378 | 0.7800 | 0.8268 | 0.6531 | 0.6572 | 0.6355 | 0.5827 |
73
- | 0.3901 | 27.9898 | 44000 | 0.4068 | 0.6747 | 0.8050 | 0.8052 | 0.8030 | 0.7737 | 0.8480 | 0.7955 | 0.6972 | 0.6956 | 0.6582 | 0.6477 |
74
- | 0.4725 | 30.5344 | 48000 | 0.3738 | 0.6928 | 0.8180 | 0.8180 | 0.8152 | 0.7977 | 0.8433 | 0.8158 | 0.7242 | 0.7024 | 0.6954 | 0.6492 |
75
- | 0.3067 | 33.0789 | 52000 | 0.3493 | 0.7223 | 0.8367 | 0.8374 | 0.8139 | 0.8374 | 0.8924 | 0.8029 | 0.7510 | 0.7253 | 0.6839 | 0.7290 |
76
- | 0.4898 | 35.6234 | 56000 | 0.3349 | 0.7197 | 0.8369 | 0.8368 | 0.8726 | 0.8097 | 0.8431 | 0.8221 | 0.7006 | 0.7348 | 0.7254 | 0.7179 |
77
- | 0.2826 | 38.1679 | 60000 | 0.3021 | 0.7503 | 0.8563 | 0.8569 | 0.8839 | 0.8769 | 0.8603 | 0.8041 | 0.7457 | 0.7359 | 0.7530 | 0.7668 |
78
- | 0.3235 | 40.7125 | 64000 | 0.2863 | 0.7561 | 0.8612 | 0.8610 | 0.8758 | 0.8490 | 0.8598 | 0.8601 | 0.7478 | 0.7821 | 0.7630 | 0.7316 |
79
- | 0.3374 | 43.2570 | 68000 | 0.2927 | 0.7689 | 0.8668 | 0.8674 | 0.8621 | 0.8328 | 0.9457 | 0.8266 | 0.7827 | 0.8025 | 0.7194 | 0.7708 |
80
- | 0.2588 | 45.8015 | 72000 | 0.2737 | 0.7743 | 0.8716 | 0.8717 | 0.9129 | 0.8702 | 0.8653 | 0.8380 | 0.7254 | 0.7849 | 0.8016 | 0.7852 |
81
- | 0.5224 | 48.3461 | 76000 | 0.2579 | 0.7905 | 0.8819 | 0.8822 | 0.9212 | 0.8628 | 0.9067 | 0.8367 | 0.7605 | 0.8124 | 0.7815 | 0.8075 |
82
- | 0.2171 | 50.8906 | 80000 | 0.2373 | 0.7971 | 0.8867 | 0.8870 | 0.9187 | 0.8895 | 0.8875 | 0.8512 | 0.7941 | 0.7931 | 0.7986 | 0.8025 |
83
- | 0.2075 | 53.4351 | 84000 | 0.2374 | 0.8051 | 0.8912 | 0.8916 | 0.9032 | 0.9120 | 0.8891 | 0.8608 | 0.8289 | 0.7819 | 0.8033 | 0.8064 |
84
- | 0.3577 | 55.9796 | 88000 | 0.2390 | 0.8081 | 0.8931 | 0.8935 | 0.9098 | 0.9007 | 0.9072 | 0.8545 | 0.8076 | 0.7889 | 0.8134 | 0.8224 |
85
- | 0.2084 | 58.5242 | 92000 | 0.2286 | 0.8128 | 0.8969 | 0.8968 | 0.9119 | 0.8833 | 0.8951 | 0.8974 | 0.8200 | 0.8185 | 0.8144 | 0.7983 |
86
 
87
 
88
  ### Framework versions
 
1
  ---
2
  library_name: transformers
3
  license: other
4
+ base_model: NICOPOI-9/segformer-b0-finetuned-morphpadver1-hgo-coord-v1
5
  tags:
6
  - vision
7
  - image-segmentation
 
16
 
17
  # segformer-b0-finetuned-morphpadver1-hgo-coord-v2
18
 
19
+ This model is a fine-tuned version of [NICOPOI-9/segformer-b0-finetuned-morphpadver1-hgo-coord-v1](https://huggingface.co/NICOPOI-9/segformer-b0-finetuned-morphpadver1-hgo-coord-v1) on the NICOPOI-9/morphpad_coord_hgo_512_4class dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.0408
22
+ - Mean Iou: 0.9952
23
+ - Mean Accuracy: 0.9976
24
+ - Overall Accuracy: 0.9976
25
+ - Accuracy 0-0: 0.9993
26
+ - Accuracy 0-90: 0.9958
27
+ - Accuracy 90-0: 0.9969
28
+ - Accuracy 90-90: 0.9983
29
+ - Iou 0-0: 0.9975
30
+ - Iou 0-90: 0.9929
31
+ - Iou 90-0: 0.9949
32
+ - Iou 90-90: 0.9955
33
 
34
  ## Model description
35
 
 
60
 
61
  | Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy 0-0 | Accuracy 0-90 | Accuracy 90-0 | Accuracy 90-90 | Iou 0-0 | Iou 0-90 | Iou 90-0 | Iou 90-90 |
62
  |:-------------:|:-------:|:-----:|:---------------:|:--------:|:-------------:|:----------------:|:------------:|:-------------:|:-------------:|:--------------:|:-------:|:--------:|:--------:|:---------:|
63
+ | 0.0654 | 2.5445 | 4000 | 0.1134 | 0.9236 | 0.9604 | 0.9602 | 0.9729 | 0.9373 | 0.9642 | 0.9674 | 0.9265 | 0.9144 | 0.9233 | 0.9301 |
64
+ | 0.0552 | 5.0891 | 8000 | 0.1426 | 0.9161 | 0.9562 | 0.9561 | 0.9607 | 0.9538 | 0.9547 | 0.9555 | 0.9166 | 0.9146 | 0.9112 | 0.9218 |
65
+ | 0.0469 | 7.6336 | 12000 | 0.0633 | 0.9556 | 0.9774 | 0.9773 | 0.9811 | 0.9714 | 0.9744 | 0.9826 | 0.9588 | 0.9516 | 0.9545 | 0.9576 |
66
+ | 0.0378 | 10.1781 | 16000 | 0.0506 | 0.9650 | 0.9822 | 0.9822 | 0.9826 | 0.9773 | 0.9844 | 0.9844 | 0.9661 | 0.9601 | 0.9643 | 0.9696 |
67
+ | 0.0582 | 12.7226 | 20000 | 0.0402 | 0.9737 | 0.9867 | 0.9866 | 0.9925 | 0.9891 | 0.9791 | 0.9860 | 0.9774 | 0.9700 | 0.9699 | 0.9774 |
68
+ | 0.0322 | 15.2672 | 24000 | 0.0453 | 0.9707 | 0.9850 | 0.9851 | 0.9809 | 0.9843 | 0.9909 | 0.9840 | 0.9746 | 0.9715 | 0.9637 | 0.9728 |
69
+ | 0.0254 | 17.8117 | 28000 | 0.1030 | 0.9652 | 0.9823 | 0.9822 | 0.9895 | 0.9808 | 0.9748 | 0.9841 | 0.9761 | 0.9599 | 0.9583 | 0.9666 |
70
+ | 2.3028 | 20.3562 | 32000 | 0.0572 | 0.9745 | 0.9871 | 0.9870 | 0.9861 | 0.9839 | 0.9885 | 0.9896 | 0.9789 | 0.9717 | 0.9700 | 0.9773 |
71
+ | 0.0769 | 22.9008 | 36000 | 0.0225 | 0.9866 | 0.9932 | 0.9932 | 0.9960 | 0.9899 | 0.9939 | 0.9932 | 0.9893 | 0.9837 | 0.9849 | 0.9884 |
72
+ | 0.0512 | 25.4453 | 40000 | 0.0329 | 0.9850 | 0.9924 | 0.9924 | 0.9959 | 0.9867 | 0.9954 | 0.9917 | 0.9857 | 0.9820 | 0.9843 | 0.9878 |
73
+ | 0.3281 | 27.9898 | 44000 | 0.0301 | 0.9866 | 0.9933 | 0.9932 | 0.9958 | 0.9913 | 0.9907 | 0.9952 | 0.9899 | 0.9858 | 0.9843 | 0.9863 |
74
+ | 0.1536 | 30.5344 | 48000 | 0.0355 | 0.9889 | 0.9944 | 0.9944 | 0.9981 | 0.9927 | 0.9920 | 0.9949 | 0.9941 | 0.9855 | 0.9880 | 0.9880 |
75
+ | 0.0079 | 33.0789 | 52000 | 0.0256 | 0.9933 | 0.9966 | 0.9966 | 0.9979 | 0.9951 | 0.9961 | 0.9974 | 0.9956 | 0.9917 | 0.9934 | 0.9924 |
76
+ | 0.0074 | 35.6234 | 56000 | 0.0205 | 0.9938 | 0.9969 | 0.9969 | 0.9983 | 0.9970 | 0.9966 | 0.9956 | 0.9963 | 0.9923 | 0.9928 | 0.9939 |
77
+ | 0.0077 | 38.1679 | 60000 | 0.0255 | 0.9933 | 0.9967 | 0.9966 | 0.9985 | 0.9946 | 0.9964 | 0.9971 | 0.9954 | 0.9925 | 0.9919 | 0.9934 |
78
+ | 0.0061 | 40.7125 | 64000 | 0.0282 | 0.9945 | 0.9972 | 0.9972 | 0.9987 | 0.9958 | 0.9974 | 0.9969 | 0.9967 | 0.9916 | 0.9950 | 0.9945 |
79
+ | 0.0051 | 43.2570 | 68000 | 0.0262 | 0.9937 | 0.9969 | 0.9968 | 0.9987 | 0.9949 | 0.9959 | 0.9979 | 0.9968 | 0.9916 | 0.9934 | 0.9930 |
80
+ | 0.0047 | 45.8015 | 72000 | 0.0564 | 0.9912 | 0.9956 | 0.9956 | 0.9991 | 0.9950 | 0.9940 | 0.9943 | 0.9958 | 0.9882 | 0.9897 | 0.9912 |
81
+ | 0.0046 | 48.3461 | 76000 | 0.0492 | 0.9939 | 0.9969 | 0.9969 | 0.9992 | 0.9941 | 0.9974 | 0.9970 | 0.9969 | 0.9903 | 0.9938 | 0.9945 |
82
+ | 0.0552 | 50.8906 | 80000 | 0.0438 | 0.9948 | 0.9974 | 0.9974 | 0.9992 | 0.9966 | 0.9967 | 0.9972 | 0.9980 | 0.9924 | 0.9948 | 0.9941 |
83
+ | 0.0039 | 53.4351 | 84000 | 0.0361 | 0.9953 | 0.9976 | 0.9976 | 0.9991 | 0.9961 | 0.9973 | 0.9981 | 0.9975 | 0.9928 | 0.9952 | 0.9956 |
84
+ | 0.0034 | 55.9796 | 88000 | 0.0317 | 0.9958 | 0.9979 | 0.9979 | 0.9993 | 0.9964 | 0.9974 | 0.9985 | 0.9979 | 0.9937 | 0.9955 | 0.9963 |
85
+ | 0.0149 | 58.5242 | 92000 | 0.0408 | 0.9952 | 0.9976 | 0.9976 | 0.9993 | 0.9958 | 0.9969 | 0.9983 | 0.9975 | 0.9929 | 0.9949 | 0.9955 |
86
 
87
 
88
  ### Framework versions
config.json CHANGED
@@ -1,16 +1,16 @@
1
  {
2
- "_name_or_path": "nvidia/mit-b2",
3
  "architectures": [
4
  "SegformerForSemanticSegmentation"
5
  ],
6
  "attention_probs_dropout_prob": 0.0,
7
  "classifier_dropout_prob": 0.1,
8
- "decoder_hidden_size": 768,
9
  "depths": [
10
- 3,
11
- 4,
12
- 6,
13
- 3
14
  ],
15
  "downsampling_rates": [
16
  1,
 
1
  {
2
+ "_name_or_path": "NICOPOI-9/segformer-b0-finetuned-morphpadver1-hgo-coord-v1",
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,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b64397289bc17483c769ceaf00998d9e238e683091fed7dbcfbb32ab66525a2
3
- size 109450168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ce2e1ce033a7516baa748fec341eb2b63afd03b44530520c5537df8375a4ba2
3
+ size 54739432
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:24411a836223d859e5eef1d3f244d80368a3934e3df7e1450d60112276621708
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a3200b97f67b5424179cc5f253a166b1496abea681e737b17ae870e4caeb596
3
  size 5432