Hugging Face's logo

Transformers123
/
testing_100_epoches

Transformers
PyTorch
segformer
Generated from Trainer
Inference Endpoints
Model card Files Community
Transformers123 commited on
Commit
9c9be8a
•
1 Parent(s): 636f7cb

End of training

Browse files
Files changed (4) hide show
  1. README.md +114 -0
  2. config.json +78 -0
  3. pytorch_model.bin +3 -0
  4. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: nividia/mit-b2
3
+ tags:
4
+ - retouch
5
+ - image-segmentation
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: testing_100_epoches
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
+ # testing_100_epoches
16
+
17
+ This model is a fine-tuned version of [nividia/mit-b2](https://huggingface.co/nividia/mit-b2) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.1400
20
+ - Mean Iou: 0.0066
21
+ - Mean Accuracy: 0.0133
22
+ - Overall Accuracy: 0.0133
23
+ - Accuracy Bkg: nan
24
+ - Accuracy Wht: 0.0133
25
+ - Iou Bkg: 0.0
26
+ - Iou Wht: 0.0133
27
+
28
+ ## Model description
29
+
30
+ More information needed
31
+
32
+ ## Intended uses & limitations
33
+
34
+ More information needed
35
+
36
+ ## Training and evaluation data
37
+
38
+ More information needed
39
+
40
+ ## Training procedure
41
+
42
+ ### Training hyperparameters
43
+
44
+ The following hyperparameters were used during training:
45
+ - learning_rate: 6e-05
46
+ - train_batch_size: 3
47
+ - eval_batch_size: 8
48
+ - seed: 42
49
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
+ - lr_scheduler_type: linear
51
+ - num_epochs: 50
52
+
53
+ ### Training results
54
+
55
+ | Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Bkg | Accuracy Wht | Iou Bkg | Iou Wht |
56
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:------------:|:------------:|:-------:|:-------:|
57
+ | 0.1707 | 1.0 | 180 | 0.0800 | 0.0 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 |
58
+ | 0.0919 | 2.0 | 360 | 0.0798 | 0.0 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 |
59
+ | 0.0874 | 3.0 | 540 | 0.0771 | 0.0 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 |
60
+ | 0.0843 | 4.0 | 720 | 0.0786 | 0.0 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 |
61
+ | 0.0808 | 5.0 | 900 | 0.0805 | 0.0014 | 0.0029 | 0.0029 | nan | 0.0029 | 0.0 | 0.0029 |
62
+ | 0.0775 | 6.0 | 1080 | 0.0796 | 0.0 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 |
63
+ | 0.0712 | 7.0 | 1260 | 0.0906 | 0.0381 | 0.0762 | 0.0762 | nan | 0.0762 | 0.0 | 0.0762 |
64
+ | 0.0629 | 8.0 | 1440 | 0.0830 | 0.0055 | 0.0110 | 0.0110 | nan | 0.0110 | 0.0 | 0.0110 |
65
+ | 0.0547 | 9.0 | 1620 | 0.0911 | 0.0141 | 0.0281 | 0.0281 | nan | 0.0281 | 0.0 | 0.0281 |
66
+ | 0.0483 | 10.0 | 1800 | 0.1032 | 0.0097 | 0.0194 | 0.0194 | nan | 0.0194 | 0.0 | 0.0194 |
67
+ | 0.0443 | 11.0 | 1980 | 0.0924 | 0.0146 | 0.0292 | 0.0292 | nan | 0.0292 | 0.0 | 0.0292 |
68
+ | 0.0406 | 12.0 | 2160 | 0.0979 | 0.0069 | 0.0137 | 0.0137 | nan | 0.0137 | 0.0 | 0.0137 |
69
+ | 0.0369 | 13.0 | 2340 | 0.1030 | 0.0103 | 0.0206 | 0.0206 | nan | 0.0206 | 0.0 | 0.0206 |
70
+ | 0.0352 | 14.0 | 2520 | 0.0993 | 0.0065 | 0.0129 | 0.0129 | nan | 0.0129 | 0.0 | 0.0129 |
71
+ | 0.0341 | 15.0 | 2700 | 0.0978 | 0.0062 | 0.0125 | 0.0125 | nan | 0.0125 | 0.0 | 0.0125 |
72
+ | 0.0324 | 16.0 | 2880 | 0.1044 | 0.0151 | 0.0302 | 0.0302 | nan | 0.0302 | 0.0 | 0.0302 |
73
+ | 0.0307 | 17.0 | 3060 | 0.1014 | 0.0164 | 0.0328 | 0.0328 | nan | 0.0328 | 0.0 | 0.0328 |
74
+ | 0.03 | 18.0 | 3240 | 0.1043 | 0.0128 | 0.0257 | 0.0257 | nan | 0.0257 | 0.0 | 0.0257 |
75
+ | 0.0295 | 19.0 | 3420 | 0.1093 | 0.0083 | 0.0165 | 0.0165 | nan | 0.0165 | 0.0 | 0.0165 |
76
+ | 0.0273 | 20.0 | 3600 | 0.1136 | 0.0100 | 0.0201 | 0.0201 | nan | 0.0201 | 0.0 | 0.0201 |
77
+ | 0.0264 | 21.0 | 3780 | 0.1086 | 0.0154 | 0.0309 | 0.0309 | nan | 0.0309 | 0.0 | 0.0309 |
78
+ | 0.0261 | 22.0 | 3960 | 0.1107 | 0.0165 | 0.0330 | 0.0330 | nan | 0.0330 | 0.0 | 0.0330 |
79
+ | 0.0257 | 23.0 | 4140 | 0.1119 | 0.0137 | 0.0274 | 0.0274 | nan | 0.0274 | 0.0 | 0.0274 |
80
+ | 0.0248 | 24.0 | 4320 | 0.1140 | 0.0101 | 0.0201 | 0.0201 | nan | 0.0201 | 0.0 | 0.0201 |
81
+ | 0.0242 | 25.0 | 4500 | 0.1056 | 0.0168 | 0.0336 | 0.0336 | nan | 0.0336 | 0.0 | 0.0336 |
82
+ | 0.024 | 26.0 | 4680 | 0.1143 | 0.0100 | 0.0200 | 0.0200 | nan | 0.0200 | 0.0 | 0.0200 |
83
+ | 0.0234 | 27.0 | 4860 | 0.1155 | 0.0091 | 0.0181 | 0.0181 | nan | 0.0181 | 0.0 | 0.0181 |
84
+ | 0.0228 | 28.0 | 5040 | 0.1201 | 0.0073 | 0.0146 | 0.0146 | nan | 0.0146 | 0.0 | 0.0146 |
85
+ | 0.0226 | 29.0 | 5220 | 0.1192 | 0.0094 | 0.0188 | 0.0188 | nan | 0.0188 | 0.0 | 0.0188 |
86
+ | 0.0224 | 30.0 | 5400 | 0.1187 | 0.0118 | 0.0237 | 0.0237 | nan | 0.0237 | 0.0 | 0.0237 |
87
+ | 0.0218 | 31.0 | 5580 | 0.1227 | 0.0105 | 0.0209 | 0.0209 | nan | 0.0209 | 0.0 | 0.0209 |
88
+ | 0.0211 | 32.0 | 5760 | 0.1159 | 0.0155 | 0.0310 | 0.0310 | nan | 0.0310 | 0.0 | 0.0310 |
89
+ | 0.0208 | 33.0 | 5940 | 0.1224 | 0.0108 | 0.0215 | 0.0215 | nan | 0.0215 | 0.0 | 0.0215 |
90
+ | 0.0203 | 34.0 | 6120 | 0.1239 | 0.0123 | 0.0246 | 0.0246 | nan | 0.0246 | 0.0 | 0.0246 |
91
+ | 0.0197 | 35.0 | 6300 | 0.1285 | 0.0065 | 0.0130 | 0.0130 | nan | 0.0130 | 0.0 | 0.0130 |
92
+ | 0.02 | 36.0 | 6480 | 0.1293 | 0.0037 | 0.0075 | 0.0075 | nan | 0.0075 | 0.0 | 0.0075 |
93
+ | 0.0192 | 37.0 | 6660 | 0.1258 | 0.0059 | 0.0119 | 0.0119 | nan | 0.0119 | 0.0 | 0.0119 |
94
+ | 0.0193 | 38.0 | 6840 | 0.1234 | 0.0105 | 0.0210 | 0.0210 | nan | 0.0210 | 0.0 | 0.0210 |
95
+ | 0.0189 | 39.0 | 7020 | 0.1267 | 0.0080 | 0.0159 | 0.0159 | nan | 0.0159 | 0.0 | 0.0159 |
96
+ | 0.0181 | 40.0 | 7200 | 0.1308 | 0.0060 | 0.0120 | 0.0120 | nan | 0.0120 | 0.0 | 0.0120 |
97
+ | 0.0183 | 41.0 | 7380 | 0.1337 | 0.0056 | 0.0112 | 0.0112 | nan | 0.0112 | 0.0 | 0.0112 |
98
+ | 0.018 | 42.0 | 7560 | 0.1349 | 0.0071 | 0.0142 | 0.0142 | nan | 0.0142 | 0.0 | 0.0142 |
99
+ | 0.0178 | 43.0 | 7740 | 0.1332 | 0.0069 | 0.0139 | 0.0139 | nan | 0.0139 | 0.0 | 0.0139 |
100
+ | 0.0171 | 44.0 | 7920 | 0.1363 | 0.0066 | 0.0132 | 0.0132 | nan | 0.0132 | 0.0 | 0.0132 |
101
+ | 0.0176 | 45.0 | 8100 | 0.1352 | 0.0065 | 0.0131 | 0.0131 | nan | 0.0131 | 0.0 | 0.0131 |
102
+ | 0.0181 | 46.0 | 8280 | 0.1384 | 0.0064 | 0.0127 | 0.0127 | nan | 0.0127 | 0.0 | 0.0127 |
103
+ | 0.0173 | 47.0 | 8460 | 0.1419 | 0.0065 | 0.0129 | 0.0129 | nan | 0.0129 | 0.0 | 0.0129 |
104
+ | 0.0176 | 48.0 | 8640 | 0.1374 | 0.0081 | 0.0161 | 0.0161 | nan | 0.0161 | 0.0 | 0.0161 |
105
+ | 0.0173 | 49.0 | 8820 | 0.1383 | 0.0065 | 0.0130 | 0.0130 | nan | 0.0130 | 0.0 | 0.0130 |
106
+ | 0.0173 | 50.0 | 9000 | 0.1400 | 0.0066 | 0.0133 | 0.0133 | nan | 0.0133 | 0.0 | 0.0133 |
107
+
108
+
109
+ ### Framework versions
110
+
111
+ - Transformers 4.33.3
112
+ - Pytorch 2.0.1+cu118
113
+ - Datasets 2.14.5
114
+ - Tokenizers 0.13.3
config.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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,
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": "BKG",
32
+ "1": "WHT"
33
+ },
34
+ "image_size": 224,
35
+ "initializer_range": 0.02,
36
+ "label2id": {
37
+ "BKG": 0,
38
+ "WHT": 1
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": "4.33.3"
78
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d611f479503a3cb606f62ba856528d269959bd3fec5d5c251054830f6733c53b
3
+ size 109529789
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0743862b7e940808bc0851597593b9aee6514488cd3b9a1d3b1e18afc4547b18
3
+ size 4091