Hugging Face's logo

mansee
/
swin-tiny-patch4-window7-224-blank_img

Image Classification
Transformers
PyTorch
TensorBoard
Safetensors
swin
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
mansee commited on
Commit
8df56d6
•
1 Parent(s): 0a390f7

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +11 -12
README.md CHANGED
@@ -1,6 +1,5 @@
1
  ---
2
  license: apache-2.0
3
- base_model: mansee/swin-tiny-patch4-window7-224-blank_img
4
  tags:
5
  - generated_from_trainer
6
  datasets:
@@ -22,7 +21,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.9738372093023255
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -30,10 +29,10 @@ should probably proofread and complete it, then remove this comment. -->
30
 
31
  # swin-tiny-patch4-window7-224-blank_img
32
 
33
- This model is a fine-tuned version of [mansee/swin-tiny-patch4-window7-224-blank_img](https://huggingface.co/mansee/swin-tiny-patch4-window7-224-blank_img) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.1016
36
- - Accuracy: 0.9738
37
 
38
  ## Model description
39
 
@@ -67,16 +66,16 @@ The following hyperparameters were used during training:
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | 0.0502 | 0.99 | 72 | 0.1300 | 0.9651 |
71
- | 0.1107 | 1.99 | 145 | 0.1023 | 0.9729 |
72
- | 0.0917 | 3.0 | 218 | 0.1277 | 0.9651 |
73
- | 0.1022 | 4.0 | 291 | 0.1258 | 0.9719 |
74
- | 0.0888 | 4.95 | 360 | 0.1016 | 0.9738 |
75
 
76
 
77
  ### Framework versions
78
 
79
- - Transformers 4.35.2
80
  - Pytorch 2.1.0+cu121
81
  - Datasets 2.15.0
82
- - Tokenizers 0.15.0
 
1
  ---
2
  license: apache-2.0
 
3
  tags:
4
  - generated_from_trainer
5
  datasets:
 
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
+ value: 0.9728682170542635
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
29
 
30
  # swin-tiny-patch4-window7-224-blank_img
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: 0.0848
35
+ - Accuracy: 0.9729
36
 
37
  ## Model description
38
 
 
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
+ | 0.1329 | 0.99 | 72 | 0.0882 | 0.9767 |
70
+ | 0.1247 | 1.99 | 144 | 0.0805 | 0.9767 |
71
+ | 0.0742 | 2.99 | 216 | 0.0721 | 0.9767 |
72
+ | 0.0745 | 3.99 | 288 | 0.0726 | 0.9797 |
73
+ | 0.1289 | 4.99 | 360 | 0.0848 | 0.9729 |
74
 
75
 
76
  ### Framework versions
77
 
78
+ - Transformers 4.26.1
79
  - Pytorch 2.1.0+cu121
80
  - Datasets 2.15.0
81
+ - Tokenizers 0.13.3