Hugging Face's logo

andrewljohnson
/
segformer-b5-finetuned-magic-cards-230117-2

Image Segmentation
Transformers
PyTorch
segformer
vision
Generated from Trainer
Inference Endpoints
Model card Files Community
1
andrewljohnson commited on
Commit
f89476d
•
1 Parent(s): 884ab98

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +81 -0
README.md ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ tags:
4
+ - vision
5
+ - image-segmentation
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: segformer-b5-finetuned-magic-cards-230117-2
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
+ # segformer-b5-finetuned-magic-cards-230117-2
16
+
17
+ This model is a fine-tuned version of [nvidia/mit-b5](https://huggingface.co/nvidia/mit-b5) on the andrewljohnson/magic_cards dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.0491
20
+ - Mean Iou: 0.6649
21
+ - Mean Accuracy: 0.9974
22
+ - Overall Accuracy: 0.9972
23
+ - Accuracy Unlabeled: nan
24
+ - Accuracy Front: 0.9990
25
+ - Accuracy Back: 0.9957
26
+ - Iou Unlabeled: 0.0
27
+ - Iou Front: 0.9990
28
+ - Iou Back: 0.9957
29
+
30
+ ## Model description
31
+
32
+ More information needed
33
+
34
+ ## Intended uses & limitations
35
+
36
+ More information needed
37
+
38
+ ## Training and evaluation data
39
+
40
+ More information needed
41
+
42
+ ## Training procedure
43
+
44
+ ### Training hyperparameters
45
+
46
+ The following hyperparameters were used during training:
47
+ - learning_rate: 6e-05
48
+ - train_batch_size: 1
49
+ - eval_batch_size: 1
50
+ - seed: 42
51
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
+ - lr_scheduler_type: linear
53
+ - num_epochs: 5
54
+
55
+ ### Training results
56
+
57
+ | Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Unlabeled | Accuracy Front | Accuracy Back | Iou Unlabeled | Iou Front | Iou Back |
58
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:------------------:|:--------------:|:-------------:|:-------------:|:---------:|:--------:|
59
+ | 0.5968 | 0.33 | 20 | 0.4422 | 0.6366 | 0.9701 | 0.9690 | nan | 0.9812 | 0.9590 | 0.0 | 0.9507 | 0.9590 |
60
+ | 0.8955 | 0.66 | 40 | 0.2353 | 0.6496 | 0.9819 | 0.9807 | nan | 0.9944 | 0.9695 | 0.0 | 0.9792 | 0.9695 |
61
+ | 0.1269 | 0.98 | 60 | 0.1739 | 0.6566 | 0.9922 | 0.9916 | nan | 0.9979 | 0.9866 | 0.0 | 0.9832 | 0.9866 |
62
+ | 0.7629 | 1.31 | 80 | 0.1664 | 0.6561 | 0.9915 | 0.9909 | nan | 0.9975 | 0.9856 | 0.0 | 0.9826 | 0.9856 |
63
+ | 0.106 | 1.64 | 100 | 0.1005 | 0.6641 | 0.9968 | 0.9967 | nan | 0.9978 | 0.9959 | 0.0 | 0.9966 | 0.9959 |
64
+ | 0.3278 | 1.97 | 120 | 0.0577 | 0.6632 | 0.9948 | 0.9947 | nan | 0.9963 | 0.9934 | 0.0 | 0.9963 | 0.9934 |
65
+ | 0.061 | 2.3 | 140 | 0.0655 | 0.6642 | 0.9963 | 0.9962 | nan | 0.9972 | 0.9953 | 0.0 | 0.9972 | 0.9953 |
66
+ | 0.0766 | 2.62 | 160 | 0.0470 | 0.6635 | 0.9953 | 0.9954 | nan | 0.9940 | 0.9966 | 0.0 | 0.9940 | 0.9966 |
67
+ | 0.0664 | 2.95 | 180 | 0.0436 | 0.6617 | 0.9926 | 0.9931 | nan | 0.9877 | 0.9975 | 0.0 | 0.9877 | 0.9975 |
68
+ | 0.0655 | 3.28 | 200 | 0.0632 | 0.6649 | 0.9973 | 0.9971 | nan | 0.9994 | 0.9953 | 0.0 | 0.9994 | 0.9953 |
69
+ | 0.0356 | 3.61 | 220 | 0.0755 | 0.6661 | 0.9991 | 0.9991 | nan | 0.9992 | 0.9991 | 0.0 | 0.9992 | 0.9991 |
70
+ | 0.0516 | 3.93 | 240 | 0.0470 | 0.6643 | 0.9965 | 0.9963 | nan | 0.9987 | 0.9943 | 0.0 | 0.9987 | 0.9943 |
71
+ | 0.0517 | 4.26 | 260 | 0.0481 | 0.6645 | 0.9967 | 0.9965 | nan | 0.9989 | 0.9945 | 0.0 | 0.9989 | 0.9945 |
72
+ | 0.1886 | 4.59 | 280 | 0.0823 | 0.6659 | 0.9988 | 0.9987 | nan | 0.9999 | 0.9977 | 0.0 | 0.9999 | 0.9977 |
73
+ | 0.0453 | 4.92 | 300 | 0.0491 | 0.6649 | 0.9974 | 0.9972 | nan | 0.9990 | 0.9957 | 0.0 | 0.9990 | 0.9957 |
74
+
75
+
76
+ ### Framework versions
77
+
78
+ - Transformers 4.25.1
79
+ - Pytorch 1.12.1
80
+ - Datasets 2.8.0
81
+ - Tokenizers 0.13.0.dev0