Hugging Face's logo

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

Image Classification
Transformers
PyTorch
swin
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
4
mansee commited on
Commit
881fd76
•
1 Parent(s): 5840baf

Model save

Browse files
Files changed (1) hide show
  1. README.md +14 -9
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.7797476986021139
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [mansee/swin-tiny-patch4-window7-224-img_orientation](https://huggingface.co/mansee/swin-tiny-patch4-window7-224-img_orientation) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.3966
36
- - Accuracy: 0.7797
37
 
38
  ## Model description
39
 
@@ -61,17 +61,22 @@ The following hyperparameters were used during training:
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_ratio: 0.1
64
- - num_epochs: 5
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | 0.4741 | 1.0 | 412 | 0.4774 | 0.7346 |
71
- | 0.4958 | 2.0 | 825 | 0.4403 | 0.7569 |
72
- | 0.473 | 3.0 | 1237 | 0.4093 | 0.7659 |
73
- | 0.4476 | 4.0 | 1650 | 0.4011 | 0.7734 |
74
- | 0.4093 | 4.99 | 2060 | 0.3966 | 0.7797 |
 
 
 
 
 
75
 
76
 
77
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.7794067507671326
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
32
 
33
  This model is a fine-tuned version of [mansee/swin-tiny-patch4-window7-224-img_orientation](https://huggingface.co/mansee/swin-tiny-patch4-window7-224-img_orientation) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.4538
36
+ - Accuracy: 0.7794
37
 
38
  ## Model description
39
 
 
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_ratio: 0.1
64
+ - num_epochs: 10
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | 0.3217 | 1.0 | 412 | 0.4922 | 0.7533 |
71
+ | 0.3716 | 2.0 | 825 | 0.4986 | 0.7601 |
72
+ | 0.3756 | 3.0 | 1237 | 0.4427 | 0.7762 |
73
+ | 0.3926 | 4.0 | 1650 | 0.4515 | 0.7733 |
74
+ | 0.3859 | 5.0 | 2062 | 0.4394 | 0.7717 |
75
+ | 0.3822 | 6.0 | 2475 | 0.4410 | 0.7784 |
76
+ | 0.3804 | 7.0 | 2887 | 0.4561 | 0.7767 |
77
+ | 0.3231 | 8.0 | 3300 | 0.4505 | 0.7784 |
78
+ | 0.3295 | 9.0 | 3712 | 0.4607 | 0.7789 |
79
+ | 0.321 | 9.99 | 4120 | 0.4538 | 0.7794 |
80
 
81
 
82
  ### Framework versions