Hugging Face's logo

dvs
/
swin-tiny-patch4-window7-224-uploads-classifier-v2

Image Classification
Transformers
PyTorch
TensorBoard
swin
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
dvs commited on
Commit
536a35b
•
1 Parent(s): 027c2e2

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +96 -0
README.md ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - imagefolder
7
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: swin-tiny-patch4-window7-224-uploads-classifier-v2
11
+ results:
12
+ - task:
13
+ name: Image Classification
14
+ type: image-classification
15
+ dataset:
16
+ name: imagefolder
17
+ type: imagefolder
18
+ config: default
19
+ split: train
20
+ args: default
21
+ metrics:
22
+ - name: Accuracy
23
+ type: accuracy
24
+ value: 0.9725490196078431
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
+ # swin-tiny-patch4-window7-224-uploads-classifier-v2
31
+
32
+ This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
33
+ It achieves the following results on the evaluation set:
34
+ - Loss: 0.0820
35
+ - Accuracy: 0.9725
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: 5e-05
55
+ - train_batch_size: 32
56
+ - eval_batch_size: 32
57
+ - seed: 42
58
+ - gradient_accumulation_steps: 4
59
+ - total_train_batch_size: 128
60
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
+ - lr_scheduler_type: linear
62
+ - lr_scheduler_warmup_ratio: 0.1
63
+ - num_epochs: 20
64
+
65
+ ### Training results
66
+
67
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
+ | 1.2482 | 1.0 | 18 | 0.4781 | 0.8824 |
70
+ | 0.3036 | 2.0 | 36 | 0.0936 | 0.9804 |
71
+ | 0.1687 | 3.0 | 54 | 0.0745 | 0.9843 |
72
+ | 0.1392 | 4.0 | 72 | 0.0980 | 0.9725 |
73
+ | 0.14 | 5.0 | 90 | 0.0778 | 0.9765 |
74
+ | 0.1186 | 6.0 | 108 | 0.0837 | 0.9725 |
75
+ | 0.1088 | 7.0 | 126 | 0.0645 | 0.9804 |
76
+ | 0.0789 | 8.0 | 144 | 0.0675 | 0.9765 |
77
+ | 0.0644 | 9.0 | 162 | 0.0940 | 0.9686 |
78
+ | 0.0582 | 10.0 | 180 | 0.0879 | 0.9725 |
79
+ | 0.0591 | 11.0 | 198 | 0.0935 | 0.9686 |
80
+ | 0.0538 | 12.0 | 216 | 0.0540 | 0.9804 |
81
+ | 0.0588 | 13.0 | 234 | 0.0725 | 0.9686 |
82
+ | 0.0538 | 14.0 | 252 | 0.0637 | 0.9765 |
83
+ | 0.0462 | 15.0 | 270 | 0.0694 | 0.9725 |
84
+ | 0.0352 | 16.0 | 288 | 0.0771 | 0.9686 |
85
+ | 0.0536 | 17.0 | 306 | 0.0629 | 0.9804 |
86
+ | 0.0403 | 18.0 | 324 | 0.0933 | 0.9686 |
87
+ | 0.0412 | 19.0 | 342 | 0.0848 | 0.9725 |
88
+ | 0.0305 | 20.0 | 360 | 0.0820 | 0.9725 |
89
+
90
+
91
+ ### Framework versions
92
+
93
+ - Transformers 4.28.0
94
+ - Pytorch 2.0.1+cu118
95
+ - Datasets 2.14.5
96
+ - Tokenizers 0.13.3