trpakov commited on
Commit
5fad412
1 Parent(s): 3056cfb

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +84 -0
README.md ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - chest-xray-classification
7
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: vit-pneumonia
11
+ results:
12
+ - task:
13
+ name: Image Classification
14
+ type: image-classification
15
+ dataset:
16
+ name: chest-xray-classification
17
+ type: chest-xray-classification
18
+ config: full
19
+ split: validation
20
+ args: full
21
+ metrics:
22
+ - name: Accuracy
23
+ type: accuracy
24
+ value: 0.976824034334764
25
+ ---
26
+
27
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
28
+ should probably proofread and complete it, then remove this comment. -->
29
+
30
+ # vit-pneumonia
31
+
32
+ This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the chest-xray-classification dataset.
33
+ It achieves the following results on the evaluation set:
34
+ - Loss: 0.1086
35
+ - Accuracy: 0.9768
36
+
37
+ ## Model description
38
+
39
+ More information needed
40
+
41
+ ## Intended uses & limitations
42
+
43
+ More information needed
44
+
45
+ ## Training and evaluation data
46
+
47
+ More information needed
48
+
49
+ ## Training procedure
50
+
51
+ ### Training hyperparameters
52
+
53
+ The following hyperparameters were used during training:
54
+ - learning_rate: 0.0002
55
+ - train_batch_size: 64
56
+ - eval_batch_size: 64
57
+ - seed: 42
58
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
+ - lr_scheduler_type: cosine
60
+ - lr_scheduler_warmup_ratio: 0.25
61
+ - num_epochs: 10
62
+
63
+ ### Training results
64
+
65
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
+ | 0.0357 | 1.0 | 192 | 0.0955 | 0.9691 |
68
+ | 0.0404 | 2.0 | 384 | 0.0720 | 0.9751 |
69
+ | 0.0546 | 3.0 | 576 | 0.2275 | 0.9468 |
70
+ | 0.0113 | 4.0 | 768 | 0.1386 | 0.9648 |
71
+ | 0.0101 | 5.0 | 960 | 0.1212 | 0.9708 |
72
+ | 0.0003 | 6.0 | 1152 | 0.0929 | 0.9777 |
73
+ | 0.0002 | 7.0 | 1344 | 0.1051 | 0.9777 |
74
+ | 0.0002 | 8.0 | 1536 | 0.1075 | 0.9777 |
75
+ | 0.0002 | 9.0 | 1728 | 0.1084 | 0.9768 |
76
+ | 0.0002 | 10.0 | 1920 | 0.1086 | 0.9768 |
77
+
78
+
79
+ ### Framework versions
80
+
81
+ - Transformers 4.26.1
82
+ - Pytorch 1.13.1+cu116
83
+ - Datasets 2.10.1
84
+ - Tokenizers 0.13.2