Hugging Face's logo

Soulaimen
/
swin-tiny-patch4-window7-224-mixed-bottoms

Image Classification
Transformers
PyTorch
TensorBoard
swin
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Metrics Community
1
Soulaimen commited on
Commit
ceba481
·
1 Parent(s): 7ca0fea

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -13
README.md CHANGED
@@ -21,7 +21,7 @@ model-index:
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
- value: 0.9895561357702349
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,8 +31,8 @@ should probably proofread and complete it, then remove this comment. -->
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: 0.0299
35
- - Accuracy: 0.9896
36
 
37
  ## Model description
38
 
@@ -66,16 +66,16 @@ The following hyperparameters were used during training:
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
- | 0.1816 | 0.99 | 61 | 0.1264 | 0.9452 |
70
- | 0.1673 | 2.0 | 123 | 0.1478 | 0.9399 |
71
- | 0.125 | 2.99 | 184 | 0.0667 | 0.9739 |
72
- | 0.1034 | 4.0 | 246 | 0.0553 | 0.9817 |
73
- | 0.0843 | 4.99 | 307 | 0.0336 | 0.9843 |
74
- | 0.0744 | 5.99 | 369 | 0.0396 | 0.9843 |
75
- | 0.0702 | 7.0 | 431 | 0.0690 | 0.9791 |
76
- | 0.063 | 7.99 | 492 | 0.0394 | 0.9843 |
77
- | 0.0497 | 9.0 | 554 | 0.0301 | 0.9869 |
78
- | 0.0502 | 9.91 | 610 | 0.0299 | 0.9896 |
79
 
80
 
81
  ### Framework versions
 
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
+ value: 0.9888682745825603
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
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: 0.0272
35
+ - Accuracy: 0.9889
36
 
37
  ## Model description
38
 
 
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
+ | 0.1479 | 0.99 | 86 | 0.1040 | 0.9592 |
70
+ | 0.145 | 2.0 | 173 | 0.1033 | 0.9592 |
71
+ | 0.1248 | 2.99 | 259 | 0.0640 | 0.9777 |
72
+ | 0.0667 | 4.0 | 346 | 0.0378 | 0.9907 |
73
+ | 0.0826 | 4.99 | 432 | 0.0400 | 0.9814 |
74
+ | 0.0635 | 6.0 | 519 | 0.0331 | 0.9907 |
75
+ | 0.0688 | 7.0 | 606 | 0.0461 | 0.9852 |
76
+ | 0.0549 | 7.99 | 692 | 0.0335 | 0.9889 |
77
+ | 0.0501 | 9.0 | 779 | 0.0241 | 0.9907 |
78
+ | 0.0434 | 9.93 | 860 | 0.0272 | 0.9889 |
79
 
80
 
81
  ### Framework versions