Hugging Face's logo

unreal-hug
/
segformer-b0-finetuned-segments-ECHO-dev-01-v1

Image Segmentation
Transformers
TensorBoard
Safetensors
segformer
vision
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
unreal-hug commited on
Commit
c44ced1
•
1 Parent(s): 0a46c5e

End of training

Browse files
Files changed (5) hide show
  1. README.md +91 -0
  2. config.json +84 -0
  3. model.safetensors +3 -0
  4. runs/Dec01_14-26-56_e5846b8eef77/events.out.tfevents.1701440838.e5846b8eef77.246.0 +3 -0
  5. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ base_model: nvidia/mit-b0
4
+ tags:
5
+ - vision
6
+ - image-segmentation
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: segformer-b0-finetuned-segments-ECHO-dev-01-v1
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-b0-finetuned-segments-ECHO-dev-01-v1
17
+
18
+ This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on the unreal-hug/SYNTH_DATASET_SEG dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.1147
21
+ - Mean Iou: 0.7718
22
+ - Mean Accuracy: 0.9647
23
+ - Overall Accuracy: 0.9651
24
+ - Accuracy Unlabeled: nan
25
+ - Accuracy Lv: 0.9592
26
+ - Accuracy Lr: 0.9722
27
+ - Accuracy Ra: 0.9540
28
+ - Accuracy La: 0.9733
29
+ - Iou Unlabeled: 0.0
30
+ - Iou Lv: 0.9592
31
+ - Iou Lr: 0.9722
32
+ - Iou Ra: 0.9540
33
+ - Iou La: 0.9733
34
+
35
+ ## Model description
36
+
37
+ More information needed
38
+
39
+ ## Intended uses & limitations
40
+
41
+ More information needed
42
+
43
+ ## Training and evaluation data
44
+
45
+ More information needed
46
+
47
+ ## Training procedure
48
+
49
+ ### Training hyperparameters
50
+
51
+ The following hyperparameters were used during training:
52
+ - learning_rate: 6e-05
53
+ - train_batch_size: 2
54
+ - eval_batch_size: 2
55
+ - seed: 42
56
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
57
+ - lr_scheduler_type: linear
58
+ - num_epochs: 50
59
+
60
+ ### Training results
61
+
62
+ | Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Unlabeled | Accuracy Lv | Accuracy Lr | Accuracy Ra | Accuracy La | Iou Unlabeled | Iou Lv | Iou Lr | Iou Ra | Iou La |
63
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:------------------:|:-----------:|:-----------:|:-----------:|:-----------:|:-------------:|:------:|:------:|:------:|:------:|
64
+ | 0.9325 | 2.5 | 20 | 1.3095 | 0.4524 | 0.7068 | 0.7433 | nan | 0.9170 | 0.8666 | 0.2895 | 0.7542 | 0.0 | 0.7498 | 0.6467 | 0.2538 | 0.6116 |
65
+ | 0.6633 | 5.0 | 40 | 0.7431 | 0.6359 | 0.8411 | 0.8600 | nan | 0.9559 | 0.9196 | 0.6304 | 0.8583 | 0.0 | 0.8810 | 0.8526 | 0.6270 | 0.8191 |
66
+ | 0.5492 | 7.5 | 60 | 0.4682 | 0.7583 | 0.9515 | 0.9548 | nan | 0.9702 | 0.9610 | 0.9452 | 0.9295 | 0.0 | 0.9630 | 0.9610 | 0.9380 | 0.9295 |
67
+ | 0.5418 | 10.0 | 80 | 0.3925 | 0.7453 | 0.9323 | 0.9367 | nan | 0.9520 | 0.9515 | 0.9050 | 0.9206 | 0.0 | 0.9509 | 0.9515 | 0.9036 | 0.9206 |
68
+ | 0.3586 | 12.5 | 100 | 0.3216 | 0.7612 | 0.9515 | 0.9561 | nan | 0.9594 | 0.9767 | 0.9359 | 0.9340 | 0.0 | 0.9594 | 0.9767 | 0.9359 | 0.9340 |
69
+ | 0.2943 | 15.0 | 120 | 0.2719 | 0.7615 | 0.9518 | 0.9541 | nan | 0.9480 | 0.9691 | 0.9413 | 0.9490 | 0.0 | 0.9480 | 0.9691 | 0.9413 | 0.9490 |
70
+ | 0.3039 | 17.5 | 140 | 0.2505 | 0.7765 | 0.9763 | 0.9743 | nan | 0.9742 | 0.9650 | 0.9799 | 0.9861 | 0.0 | 0.9742 | 0.9650 | 0.9572 | 0.9861 |
71
+ | 0.2639 | 20.0 | 160 | 0.2208 | 0.7743 | 0.9679 | 0.9690 | nan | 0.9676 | 0.9784 | 0.9477 | 0.9778 | 0.0 | 0.9676 | 0.9784 | 0.9477 | 0.9778 |
72
+ | 0.2252 | 22.5 | 180 | 0.1928 | 0.7710 | 0.9637 | 0.9655 | nan | 0.9618 | 0.9784 | 0.9483 | 0.9664 | 0.0 | 0.9618 | 0.9784 | 0.9483 | 0.9664 |
73
+ | 0.1816 | 25.0 | 200 | 0.1756 | 0.7690 | 0.9612 | 0.9619 | nan | 0.9574 | 0.9696 | 0.9501 | 0.9679 | 0.0 | 0.9574 | 0.9696 | 0.9501 | 0.9679 |
74
+ | 0.1676 | 27.5 | 220 | 0.1556 | 0.7610 | 0.9513 | 0.9541 | nan | 0.9483 | 0.9721 | 0.9387 | 0.9460 | 0.0 | 0.9483 | 0.9721 | 0.9387 | 0.9460 |
75
+ | 0.1833 | 30.0 | 240 | 0.1468 | 0.7786 | 0.9733 | 0.9742 | nan | 0.9669 | 0.9837 | 0.9639 | 0.9786 | 0.0 | 0.9669 | 0.9837 | 0.9639 | 0.9786 |
76
+ | 0.1487 | 32.5 | 260 | 0.1367 | 0.7708 | 0.9635 | 0.9649 | nan | 0.9580 | 0.9776 | 0.9479 | 0.9705 | 0.0 | 0.9580 | 0.9776 | 0.9479 | 0.9705 |
77
+ | 0.1482 | 35.0 | 280 | 0.1320 | 0.7712 | 0.9641 | 0.9655 | nan | 0.9576 | 0.9779 | 0.9555 | 0.9653 | 0.0 | 0.9576 | 0.9779 | 0.9555 | 0.9653 |
78
+ | 0.1412 | 37.5 | 300 | 0.1241 | 0.7763 | 0.9704 | 0.9706 | nan | 0.9696 | 0.9738 | 0.9590 | 0.9791 | 0.0 | 0.9696 | 0.9738 | 0.9590 | 0.9791 |
79
+ | 0.1282 | 40.0 | 320 | 0.1213 | 0.7724 | 0.9655 | 0.9665 | nan | 0.9588 | 0.9778 | 0.9512 | 0.9742 | 0.0 | 0.9588 | 0.9778 | 0.9512 | 0.9742 |
80
+ | 0.133 | 42.5 | 340 | 0.1155 | 0.7745 | 0.9681 | 0.9686 | nan | 0.9640 | 0.9752 | 0.9580 | 0.9751 | 0.0 | 0.9640 | 0.9752 | 0.9580 | 0.9751 |
81
+ | 0.1172 | 45.0 | 360 | 0.1178 | 0.7673 | 0.9603 | 0.9607 | nan | 0.9562 | 0.9665 | 0.9510 | 0.9676 | 0.0 | 0.9562 | 0.9665 | 0.9460 | 0.9676 |
82
+ | 0.1469 | 47.5 | 380 | 0.1138 | 0.7734 | 0.9668 | 0.9673 | nan | 0.9629 | 0.9743 | 0.9545 | 0.9753 | 0.0 | 0.9629 | 0.9743 | 0.9545 | 0.9753 |
83
+ | 0.1247 | 50.0 | 400 | 0.1147 | 0.7718 | 0.9647 | 0.9651 | nan | 0.9592 | 0.9722 | 0.9540 | 0.9733 | 0.0 | 0.9592 | 0.9722 | 0.9540 | 0.9733 |
84
+
85
+
86
+ ### Framework versions
87
+
88
+ - Transformers 4.35.2
89
+ - Pytorch 2.1.0+cu118
90
+ - Datasets 2.15.0
91
+ - Tokenizers 0.15.0
config.json ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "LV",
33
+ "2": "LR",
34
+ "3": "RA",
35
+ "4": "LA"
36
+ },
37
+ "image_size": 224,
38
+ "initializer_range": 0.02,
39
+ "label2id": {
40
+ "LA": 4,
41
+ "LR": 2,
42
+ "LV": 1,
43
+ "RA": 3,
44
+ "unlabeled": 0
45
+ },
46
+ "layer_norm_eps": 1e-06,
47
+ "mlp_ratios": [
48
+ 4,
49
+ 4,
50
+ 4,
51
+ 4
52
+ ],
53
+ "model_type": "segformer",
54
+ "num_attention_heads": [
55
+ 1,
56
+ 2,
57
+ 5,
58
+ 8
59
+ ],
60
+ "num_channels": 3,
61
+ "num_encoder_blocks": 4,
62
+ "patch_sizes": [
63
+ 7,
64
+ 3,
65
+ 3,
66
+ 3
67
+ ],
68
+ "reshape_last_stage": true,
69
+ "semantic_loss_ignore_index": 255,
70
+ "sr_ratios": [
71
+ 8,
72
+ 4,
73
+ 2,
74
+ 1
75
+ ],
76
+ "strides": [
77
+ 4,
78
+ 2,
79
+ 2,
80
+ 2
81
+ ],
82
+ "torch_dtype": "float32",
83
+ "transformers_version": "4.35.2"
84
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:992f2654ed98aef129ec34ca94cf45c225897bcd8fae22b3796c0919d33a3280
3
+ size 14887860
runs/Dec01_14-26-56_e5846b8eef77/events.out.tfevents.1701440838.e5846b8eef77.246.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d76faa851caf998bef91339dc7a935ea6ed840cc20193978735fa4f8768d4e0
3
+ size 87105
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23f6467dbab4bdbfa59657fe59b90cecec0cc4789ed77fecce79dd0d9819a779
3
+ size 4664