Hugging Face's logo

twdent
/
segformer-b1-finetuned-HikingHD

Image Segmentation
Transformers
PyTorch
segformer
vision
Generated from Trainer
Model card Files Community
1
twdent commited on
Commit
c8d086e
·
1 Parent(s): c00a9b4

End of training

Browse files
Files changed (4) hide show
  1. README.md +97 -0
  2. config.json +80 -0
  3. pytorch_model.bin +3 -0
  4. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ base_model: nvidia/mit-b1
4
+ tags:
5
+ - vision
6
+ - image-segmentation
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: segformer-b1-finetuned-HikingHD
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-b1-finetuned-HikingHD
17
+
18
+ This model is a fine-tuned version of [nvidia/mit-b1](https://huggingface.co/nvidia/mit-b1) on the twdent/HikingHD dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.1067
21
+ - Mean Iou: 0.9379
22
+ - Mean Accuracy: 0.9665
23
+ - Overall Accuracy: 0.9684
24
+ - Accuracy Unlabeled: nan
25
+ - Accuracy Traversable: 0.9485
26
+ - Accuracy Non-traversable: 0.9845
27
+ - Iou Unlabeled: nan
28
+ - Iou Traversable: 0.9305
29
+ - Iou Non-traversable: 0.9452
30
+
31
+ ## Model description
32
+
33
+ More information needed
34
+
35
+ ## Intended uses & limitations
36
+
37
+ More information needed
38
+
39
+ ## Training and evaluation data
40
+
41
+ More information needed
42
+
43
+ ## Training procedure
44
+
45
+ ### Training hyperparameters
46
+
47
+ The following hyperparameters were used during training:
48
+ - learning_rate: 6e-05
49
+ - train_batch_size: 2
50
+ - eval_batch_size: 2
51
+ - seed: 42
52
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
53
+ - lr_scheduler_type: linear
54
+ - num_epochs: 50
55
+
56
+ ### Training results
57
+
58
+ | Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Unlabeled | Accuracy Traversable | Accuracy Non-traversable | Iou Unlabeled | Iou Traversable | Iou Non-traversable |
59
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:------------------:|:--------------------:|:------------------------:|:-------------:|:---------------:|:-------------------:|
60
+ | 0.3796 | 1.67 | 20 | 0.5835 | 0.6174 | 0.9605 | 0.9617 | nan | 0.9488 | 0.9721 | 0.0 | 0.9180 | 0.9343 |
61
+ | 0.3086 | 3.33 | 40 | 0.2597 | 0.9230 | 0.9589 | 0.9605 | nan | 0.9439 | 0.9739 | nan | 0.9143 | 0.9318 |
62
+ | 0.2717 | 5.0 | 60 | 0.2202 | 0.9386 | 0.9681 | 0.9687 | nan | 0.9626 | 0.9736 | nan | 0.9321 | 0.9451 |
63
+ | 0.2655 | 6.67 | 80 | 0.2127 | 0.9334 | 0.9658 | 0.9659 | nan | 0.9646 | 0.9670 | nan | 0.9267 | 0.9402 |
64
+ | 0.1603 | 8.33 | 100 | 0.1699 | 0.9383 | 0.9677 | 0.9686 | nan | 0.9601 | 0.9753 | nan | 0.9316 | 0.9450 |
65
+ | 0.2 | 10.0 | 120 | 0.1692 | 0.9289 | 0.9609 | 0.9637 | nan | 0.9342 | 0.9876 | nan | 0.9200 | 0.9378 |
66
+ | 0.1613 | 11.67 | 140 | 0.1389 | 0.9399 | 0.9676 | 0.9695 | nan | 0.9498 | 0.9853 | nan | 0.9328 | 0.9470 |
67
+ | 0.185 | 13.33 | 160 | 0.1612 | 0.9217 | 0.9566 | 0.9600 | nan | 0.9254 | 0.9878 | nan | 0.9116 | 0.9318 |
68
+ | 0.251 | 15.0 | 180 | 0.1461 | 0.9277 | 0.9603 | 0.9631 | nan | 0.9340 | 0.9865 | nan | 0.9187 | 0.9368 |
69
+ | 0.1038 | 16.67 | 200 | 0.1401 | 0.9248 | 0.9581 | 0.9616 | nan | 0.9258 | 0.9904 | nan | 0.9149 | 0.9346 |
70
+ | 0.0628 | 18.33 | 220 | 0.1556 | 0.9195 | 0.9548 | 0.9588 | nan | 0.9171 | 0.9924 | nan | 0.9086 | 0.9303 |
71
+ | 0.077 | 20.0 | 240 | 0.1439 | 0.9213 | 0.9561 | 0.9598 | nan | 0.9220 | 0.9902 | nan | 0.9110 | 0.9317 |
72
+ | 0.0714 | 21.67 | 260 | 0.1267 | 0.9344 | 0.9641 | 0.9666 | nan | 0.9404 | 0.9878 | nan | 0.9263 | 0.9425 |
73
+ | 0.081 | 23.33 | 280 | 0.1097 | 0.9397 | 0.9672 | 0.9694 | nan | 0.9470 | 0.9874 | nan | 0.9324 | 0.9470 |
74
+ | 0.09 | 25.0 | 300 | 0.1063 | 0.9402 | 0.9679 | 0.9696 | nan | 0.9522 | 0.9836 | nan | 0.9332 | 0.9472 |
75
+ | 0.0737 | 26.67 | 320 | 0.1045 | 0.9395 | 0.9674 | 0.9692 | nan | 0.9502 | 0.9845 | nan | 0.9323 | 0.9466 |
76
+ | 0.1173 | 28.33 | 340 | 0.1019 | 0.9427 | 0.9702 | 0.9708 | nan | 0.9644 | 0.9760 | nan | 0.9365 | 0.9488 |
77
+ | 0.0535 | 30.0 | 360 | 0.1132 | 0.9387 | 0.9674 | 0.9688 | nan | 0.9549 | 0.9799 | nan | 0.9317 | 0.9456 |
78
+ | 0.0693 | 31.67 | 380 | 0.1182 | 0.9340 | 0.9637 | 0.9664 | nan | 0.9389 | 0.9886 | nan | 0.9258 | 0.9422 |
79
+ | 0.0649 | 33.33 | 400 | 0.1108 | 0.9374 | 0.9662 | 0.9681 | nan | 0.9483 | 0.9841 | nan | 0.9300 | 0.9448 |
80
+ | 0.1581 | 35.0 | 420 | 0.1107 | 0.9368 | 0.9658 | 0.9678 | nan | 0.9473 | 0.9844 | nan | 0.9293 | 0.9443 |
81
+ | 0.0711 | 36.67 | 440 | 0.1011 | 0.9414 | 0.9690 | 0.9702 | nan | 0.9578 | 0.9801 | nan | 0.9348 | 0.9479 |
82
+ | 0.0743 | 38.33 | 460 | 0.1026 | 0.9400 | 0.9676 | 0.9695 | nan | 0.9500 | 0.9853 | nan | 0.9329 | 0.9471 |
83
+ | 0.0602 | 40.0 | 480 | 0.1029 | 0.9407 | 0.9681 | 0.9699 | nan | 0.9521 | 0.9841 | nan | 0.9337 | 0.9476 |
84
+ | 0.0768 | 41.67 | 500 | 0.1059 | 0.9386 | 0.9670 | 0.9688 | nan | 0.9502 | 0.9837 | nan | 0.9314 | 0.9458 |
85
+ | 0.0494 | 43.33 | 520 | 0.1076 | 0.9375 | 0.9663 | 0.9682 | nan | 0.9484 | 0.9842 | nan | 0.9302 | 0.9449 |
86
+ | 0.0359 | 45.0 | 540 | 0.1097 | 0.9369 | 0.9659 | 0.9679 | nan | 0.9473 | 0.9844 | nan | 0.9294 | 0.9444 |
87
+ | 0.0799 | 46.67 | 560 | 0.1070 | 0.9379 | 0.9666 | 0.9684 | nan | 0.9493 | 0.9838 | nan | 0.9306 | 0.9452 |
88
+ | 0.0685 | 48.33 | 580 | 0.1075 | 0.9378 | 0.9665 | 0.9684 | nan | 0.9489 | 0.9841 | nan | 0.9305 | 0.9452 |
89
+ | 0.0437 | 50.0 | 600 | 0.1067 | 0.9379 | 0.9665 | 0.9684 | nan | 0.9485 | 0.9845 | nan | 0.9305 | 0.9452 |
90
+
91
+
92
+ ### Framework versions
93
+
94
+ - Transformers 4.35.0.dev0
95
+ - Pytorch 2.1.0+cu118
96
+ - Datasets 2.14.5
97
+ - Tokenizers 0.14.0
config.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "nvidia/mit-b1",
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
+ 64,
26
+ 128,
27
+ 320,
28
+ 512
29
+ ],
30
+ "id2label": {
31
+ "0": "unlabeled",
32
+ "1": "traversable",
33
+ "2": "non-traversable"
34
+ },
35
+ "image_size": 224,
36
+ "initializer_range": 0.02,
37
+ "label2id": {
38
+ "non-traversable": 2,
39
+ "traversable": 1,
40
+ "unlabeled": 0
41
+ },
42
+ "layer_norm_eps": 1e-06,
43
+ "mlp_ratios": [
44
+ 4,
45
+ 4,
46
+ 4,
47
+ 4
48
+ ],
49
+ "model_type": "segformer",
50
+ "num_attention_heads": [
51
+ 1,
52
+ 2,
53
+ 5,
54
+ 8
55
+ ],
56
+ "num_channels": 3,
57
+ "num_encoder_blocks": 4,
58
+ "patch_sizes": [
59
+ 7,
60
+ 3,
61
+ 3,
62
+ 3
63
+ ],
64
+ "reshape_last_stage": true,
65
+ "semantic_loss_ignore_index": 255,
66
+ "sr_ratios": [
67
+ 8,
68
+ 4,
69
+ 2,
70
+ 1
71
+ ],
72
+ "strides": [
73
+ 4,
74
+ 2,
75
+ 2,
76
+ 2
77
+ ],
78
+ "torch_dtype": "float32",
79
+ "transformers_version": "4.35.0.dev0"
80
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd4c4f6629ec967fcc01aa3c9a218a056455c204b5e904cadd24018a5cfbdc36
3
+ size 54785866
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e93e1f95a132ff274f1fa291c6dd6063dee8ddce4e14c32d91cda17030054bbd
3
+ size 4536