Hugging Face's logo

navradio
/
swin-tiny-patch4-window7-224-finetuned-eurosat

Image Classification
Transformers
PyTorch
swin
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
navradio commited on
Commit
d5daf50
•
1 Parent(s): 26d2b3b

Model save

Browse files
Files changed (1) hide show
  1. README.md +37 -37
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.7722370456736698
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 [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.4877
36
- - Accuracy: 0.7722
37
 
38
  ## Model description
39
 
@@ -65,43 +65,43 @@ The following hyperparameters were used during training:
65
 
66
  ### Training results
67
 
68
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
- |:-------------:|:-----:|:-----:|:---------------:|:--------:|
70
- | 0.5611 | 1.0 | 392 | 0.5374 | 0.7341 |
71
- | 0.5299 | 2.0 | 784 | 0.5180 | 0.7486 |
72
- | 0.5289 | 3.0 | 1176 | 0.5049 | 0.7568 |
73
- | 0.5208 | 4.0 | 1568 | 0.4980 | 0.7622 |
74
- | 0.5051 | 5.0 | 1960 | 0.4996 | 0.7621 |
75
- | 0.5035 | 6.0 | 2352 | 0.4890 | 0.7672 |
76
- | 0.5028 | 7.0 | 2744 | 0.4880 | 0.7685 |
77
- | 0.5129 | 8.0 | 3136 | 0.4966 | 0.7644 |
78
- | 0.5014 | 9.0 | 3528 | 0.4895 | 0.7669 |
79
- | 0.4923 | 10.0 | 3920 | 0.4880 | 0.7702 |
80
- | 0.496 | 11.0 | 4312 | 0.4932 | 0.7673 |
81
- | 0.4978 | 12.0 | 4704 | 0.4868 | 0.7718 |
82
- | 0.4993 | 13.0 | 5096 | 0.4827 | 0.7723 |
83
- | 0.4928 | 14.0 | 5488 | 0.4826 | 0.7724 |
84
- | 0.4883 | 15.0 | 5880 | 0.4826 | 0.7729 |
85
- | 0.4951 | 16.0 | 6272 | 0.4815 | 0.7717 |
86
- | 0.4955 | 17.0 | 6664 | 0.4879 | 0.7700 |
87
- | 0.4931 | 18.0 | 7056 | 0.4837 | 0.7720 |
88
- | 0.4803 | 19.0 | 7448 | 0.4841 | 0.7732 |
89
- | 0.4906 | 20.0 | 7840 | 0.4812 | 0.7737 |
90
- | 0.4718 | 21.0 | 8232 | 0.4880 | 0.7731 |
91
- | 0.479 | 22.0 | 8624 | 0.4826 | 0.7733 |
92
- | 0.483 | 23.0 | 9016 | 0.4825 | 0.7719 |
93
- | 0.4748 | 24.0 | 9408 | 0.4828 | 0.7738 |
94
- | 0.4708 | 25.0 | 9800 | 0.4877 | 0.7722 |
95
- | 0.4746 | 26.0 | 10192 | 0.4856 | 0.7734 |
96
- | 0.4659 | 27.0 | 10584 | 0.4879 | 0.7725 |
97
- | 0.4732 | 28.0 | 10976 | 0.4864 | 0.7721 |
98
- | 0.4672 | 29.0 | 11368 | 0.4866 | 0.7725 |
99
- | 0.4677 | 30.0 | 11760 | 0.4877 | 0.7722 |
100
 
101
 
102
  ### Framework versions
103
 
104
- - Transformers 4.32.0
105
  - Pytorch 2.0.1+cu117
106
- - Datasets 2.14.4
107
  - Tokenizers 0.13.3
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.0
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 [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 5.5031
36
+ - Accuracy: 0.0
37
 
38
  ## Model description
39
 
 
65
 
66
  ### Training results
67
 
68
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | No log | 1.0 | 1 | 0.6744 | 1.0 |
71
+ | No log | 2.0 | 2 | 0.7507 | 0.0 |
72
+ | No log | 3.0 | 3 | 0.9175 | 0.0 |
73
+ | No log | 4.0 | 4 | 1.1669 | 0.0 |
74
+ | No log | 5.0 | 5 | 1.4443 | 0.0 |
75
+ | No log | 6.0 | 6 | 1.7218 | 0.0 |
76
+ | No log | 7.0 | 7 | 2.0269 | 0.0 |
77
+ | No log | 8.0 | 8 | 2.3374 | 0.0 |
78
+ | No log | 9.0 | 9 | 2.6657 | 0.0 |
79
+ | 0.0781 | 10.0 | 10 | 2.9900 | 0.0 |
80
+ | 0.0781 | 11.0 | 11 | 3.2990 | 0.0 |
81
+ | 0.0781 | 12.0 | 12 | 3.5921 | 0.0 |
82
+ | 0.0781 | 13.0 | 13 | 3.8577 | 0.0 |
83
+ | 0.0781 | 14.0 | 14 | 4.1048 | 0.0 |
84
+ | 0.0781 | 15.0 | 15 | 4.3232 | 0.0 |
85
+ | 0.0781 | 16.0 | 16 | 4.5163 | 0.0 |
86
+ | 0.0781 | 17.0 | 17 | 4.6854 | 0.0 |
87
+ | 0.0781 | 18.0 | 18 | 4.8332 | 0.0 |
88
+ | 0.0781 | 19.0 | 19 | 4.9602 | 0.0 |
89
+ | 0.0003 | 20.0 | 20 | 5.0735 | 0.0 |
90
+ | 0.0003 | 21.0 | 21 | 5.1691 | 0.0 |
91
+ | 0.0003 | 22.0 | 22 | 5.2486 | 0.0 |
92
+ | 0.0003 | 23.0 | 23 | 5.3151 | 0.0 |
93
+ | 0.0003 | 24.0 | 24 | 5.3696 | 0.0 |
94
+ | 0.0003 | 25.0 | 25 | 5.4131 | 0.0 |
95
+ | 0.0003 | 26.0 | 26 | 5.4466 | 0.0 |
96
+ | 0.0003 | 27.0 | 27 | 5.4711 | 0.0 |
97
+ | 0.0003 | 28.0 | 28 | 5.4879 | 0.0 |
98
+ | 0.0003 | 29.0 | 29 | 5.4983 | 0.0 |
99
+ | 0.0 | 30.0 | 30 | 5.5031 | 0.0 |
100
 
101
 
102
  ### Framework versions
103
 
104
+ - Transformers 4.33.3
105
  - Pytorch 2.0.1+cu117
106
+ - Datasets 2.14.5
107
  - Tokenizers 0.13.3