Transformers123 commited on
Commit
c7b8a61
1 Parent(s): 326a6c6

End of training

Browse files
Files changed (4) hide show
  1. README.md +63 -0
  2. config.json +76 -0
  3. pytorch_model.bin +3 -0
  4. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: mividia/mit-b2
3
+ tags:
4
+ - retouch
5
+ - image-segmentation
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: testing_303
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_303
16
+
17
+ This model is a fine-tuned version of [mividia/mit-b2](https://huggingface.co/mividia/mit-b2) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.0228
20
+ - Mean Iou: 1.0
21
+ - Mean Accuracy: 1.0
22
+ - Overall Accuracy: 1.0
23
+ - Accuracy Wht: 1.0
24
+ - Iou Wht: 1.0
25
+
26
+ ## Model description
27
+
28
+ More information needed
29
+
30
+ ## Intended uses & limitations
31
+
32
+ More information needed
33
+
34
+ ## Training and evaluation data
35
+
36
+ More information needed
37
+
38
+ ## Training procedure
39
+
40
+ ### Training hyperparameters
41
+
42
+ The following hyperparameters were used during training:
43
+ - learning_rate: 6e-05
44
+ - train_batch_size: 2
45
+ - eval_batch_size: 8
46
+ - seed: 42
47
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
+ - lr_scheduler_type: linear
49
+ - num_epochs: 1
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Wht | Iou Wht |
54
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:------------:|:-------:|
55
+ | 0.1064 | 1.0 | 270 | 0.0228 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 |
56
+
57
+
58
+ ### Framework versions
59
+
60
+ - Transformers 4.33.3
61
+ - Pytorch 2.0.1+cu118
62
+ - Datasets 2.14.5
63
+ - Tokenizers 0.13.3
config.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "WHT"
32
+ },
33
+ "image_size": 224,
34
+ "initializer_range": 0.02,
35
+ "label2id": {
36
+ "WHT": 0
37
+ },
38
+ "layer_norm_eps": 1e-06,
39
+ "mlp_ratios": [
40
+ 4,
41
+ 4,
42
+ 4,
43
+ 4
44
+ ],
45
+ "model_type": "segformer",
46
+ "num_attention_heads": [
47
+ 1,
48
+ 2,
49
+ 5,
50
+ 8
51
+ ],
52
+ "num_channels": 3,
53
+ "num_encoder_blocks": 4,
54
+ "patch_sizes": [
55
+ 7,
56
+ 3,
57
+ 3,
58
+ 3
59
+ ],
60
+ "reshape_last_stage": true,
61
+ "semantic_loss_ignore_index": 255,
62
+ "sr_ratios": [
63
+ 8,
64
+ 4,
65
+ 2,
66
+ 1
67
+ ],
68
+ "strides": [
69
+ 4,
70
+ 2,
71
+ 2,
72
+ 2
73
+ ],
74
+ "torch_dtype": "float32",
75
+ "transformers_version": "4.33.3"
76
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d4e855a6f2bf1745890ba20f9c7a383e0537145f40b8d319b6c0e41e6c8172d
3
+ size 109526717
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0c3509426524d730791d5face32ec6a33d3d7bcbb628b9c3d33a7b548c0ce87
3
+ size 4091