Hugging Face's logo

ahishamm
/
vit-large-binary-isic-patch-16

Image Classification
Transformers
PyTorch
TensorBoard
vit
Generated from Trainer
Model card Files
xet
Metrics Community
1
ahishamm commited on
Commit
8d57bed
·
1 Parent(s): 4810b56

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +107 -0
README.md ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - accuracy
7
+ - recall
8
+ - f1
9
+ - precision
10
+ model-index:
11
+ - name: vit-large-binary-isic-patch-16
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ # vit-large-binary-isic-patch-16
19
+
20
+ This model is a fine-tuned version of [google/vit-large-patch16-224-in21k](https://huggingface.co/google/vit-large-patch16-224-in21k) on the None dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 0.4499
23
+ - Accuracy: 0.8983
24
+ - Recall: 0.8983
25
+ - F1: 0.8983
26
+ - Precision: 0.8983
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: 0.0002
46
+ - train_batch_size: 16
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: 4
52
+
53
+ ### Training results
54
+
55
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Recall | F1 | Precision |
56
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:---------:|
57
+ | 0.5596 | 0.09 | 100 | 0.4728 | 0.7781 | 0.7781 | 0.7781 | 0.7781 |
58
+ | 0.3373 | 0.19 | 200 | 0.3594 | 0.8266 | 0.8266 | 0.8266 | 0.8266 |
59
+ | 0.397 | 0.28 | 300 | 0.5284 | 0.7695 | 0.7695 | 0.7695 | 0.7695 |
60
+ | 0.3913 | 0.37 | 400 | 0.3315 | 0.8384 | 0.8384 | 0.8384 | 0.8384 |
61
+ | 0.3147 | 0.46 | 500 | 0.4425 | 0.7778 | 0.7778 | 0.7778 | 0.7778 |
62
+ | 0.2709 | 0.56 | 600 | 0.3787 | 0.8352 | 0.8352 | 0.8352 | 0.8352 |
63
+ | 0.4062 | 0.65 | 700 | 0.3613 | 0.8193 | 0.8193 | 0.8193 | 0.8193 |
64
+ | 0.3047 | 0.74 | 800 | 0.3086 | 0.8480 | 0.8480 | 0.8480 | 0.8480 |
65
+ | 0.3542 | 0.84 | 900 | 0.3232 | 0.8620 | 0.8620 | 0.8620 | 0.8620 |
66
+ | 0.2096 | 0.93 | 1000 | 0.2981 | 0.8734 | 0.8734 | 0.8734 | 0.8734 |
67
+ | 0.2214 | 1.02 | 1100 | 0.3148 | 0.8623 | 0.8623 | 0.8623 | 0.8623 |
68
+ | 0.2646 | 1.12 | 1200 | 0.3193 | 0.8592 | 0.8592 | 0.8592 | 0.8592 |
69
+ | 0.2464 | 1.21 | 1300 | 0.4324 | 0.8347 | 0.8347 | 0.8347 | 0.8347 |
70
+ | 0.2769 | 1.3 | 1400 | 0.2832 | 0.8716 | 0.8716 | 0.8716 | 0.8716 |
71
+ | 0.2726 | 1.39 | 1500 | 0.2838 | 0.8705 | 0.8705 | 0.8705 | 0.8705 |
72
+ | 0.3334 | 1.49 | 1600 | 0.3292 | 0.8494 | 0.8494 | 0.8494 | 0.8494 |
73
+ | 0.2172 | 1.58 | 1700 | 0.3023 | 0.8635 | 0.8635 | 0.8635 | 0.8635 |
74
+ | 0.2382 | 1.67 | 1800 | 0.3191 | 0.8514 | 0.8514 | 0.8514 | 0.8514 |
75
+ | 0.1616 | 1.77 | 1900 | 0.3044 | 0.8875 | 0.8875 | 0.8875 | 0.8875 |
76
+ | 0.1527 | 1.86 | 2000 | 0.2963 | 0.8789 | 0.8789 | 0.8789 | 0.8789 |
77
+ | 0.2123 | 1.95 | 2100 | 0.2719 | 0.8742 | 0.8742 | 0.8742 | 0.8742 |
78
+ | 0.1489 | 2.04 | 2200 | 0.3445 | 0.8605 | 0.8605 | 0.8605 | 0.8605 |
79
+ | 0.2052 | 2.14 | 2300 | 0.3297 | 0.8799 | 0.8799 | 0.8799 | 0.8799 |
80
+ | 0.172 | 2.23 | 2400 | 0.3089 | 0.8834 | 0.8834 | 0.8834 | 0.8834 |
81
+ | 0.1167 | 2.32 | 2500 | 0.2973 | 0.8763 | 0.8763 | 0.8763 | 0.8763 |
82
+ | 0.0705 | 2.42 | 2600 | 0.3585 | 0.8912 | 0.8912 | 0.8912 | 0.8912 |
83
+ | 0.212 | 2.51 | 2700 | 0.4051 | 0.8671 | 0.8671 | 0.8671 | 0.8671 |
84
+ | 0.2053 | 2.6 | 2800 | 0.3088 | 0.8911 | 0.8911 | 0.8911 | 0.8911 |
85
+ | 0.0718 | 2.7 | 2900 | 0.3223 | 0.8894 | 0.8894 | 0.8894 | 0.8894 |
86
+ | 0.0648 | 2.79 | 3000 | 0.3427 | 0.8776 | 0.8776 | 0.8776 | 0.8776 |
87
+ | 0.0889 | 2.88 | 3100 | 0.3504 | 0.8880 | 0.8880 | 0.8880 | 0.8880 |
88
+ | 0.098 | 2.97 | 3200 | 0.3520 | 0.8770 | 0.8770 | 0.8770 | 0.8770 |
89
+ | 0.1231 | 3.07 | 3300 | 0.4712 | 0.8799 | 0.8799 | 0.8799 | 0.8799 |
90
+ | 0.0598 | 3.16 | 3400 | 0.4759 | 0.8779 | 0.8779 | 0.8779 | 0.8779 |
91
+ | 0.0558 | 3.25 | 3500 | 0.4180 | 0.8798 | 0.8798 | 0.8798 | 0.8798 |
92
+ | 0.0595 | 3.35 | 3600 | 0.5600 | 0.8865 | 0.8865 | 0.8865 | 0.8865 |
93
+ | 0.0796 | 3.44 | 3700 | 0.4691 | 0.8922 | 0.8922 | 0.8922 | 0.8922 |
94
+ | 0.0122 | 3.53 | 3800 | 0.4117 | 0.8935 | 0.8935 | 0.8935 | 0.8935 |
95
+ | 0.0633 | 3.62 | 3900 | 0.4275 | 0.8957 | 0.8957 | 0.8957 | 0.8957 |
96
+ | 0.0659 | 3.72 | 4000 | 0.4218 | 0.8936 | 0.8936 | 0.8936 | 0.8936 |
97
+ | 0.0155 | 3.81 | 4100 | 0.4189 | 0.8981 | 0.8981 | 0.8981 | 0.8981 |
98
+ | 0.0296 | 3.9 | 4200 | 0.4444 | 0.8974 | 0.8974 | 0.8974 | 0.8974 |
99
+ | 0.0703 | 4.0 | 4300 | 0.4499 | 0.8983 | 0.8983 | 0.8983 | 0.8983 |
100
+
101
+
102
+ ### Framework versions
103
+
104
+ - Transformers 4.30.2
105
+ - Pytorch 2.0.1+cu118
106
+ - Datasets 2.13.1
107
+ - Tokenizers 0.13.3