Hugging Face's logo

marvind434
/
swin-tiny-patch4-window7-224-finetuned-eurosat

Image Classification
Transformers
PyTorch
TensorBoard
swin
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
1
marvind434 commited on
Commit
d2eb2e0
·
1 Parent(s): 9d97762

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +22 -22
README.md CHANGED
@@ -31,7 +31,7 @@ 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: 0.2495
35
  - Accuracy: 1.0
36
 
37
  ## Model description
@@ -66,31 +66,31 @@ The following hyperparameters were used during training:
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
- | No log | 1.0 | 1 | 0.5248 | 0.75 |
70
- | No log | 2.0 | 2 | 0.4808 | 0.75 |
71
- | No log | 3.0 | 3 | 0.4250 | 0.75 |
72
- | No log | 4.0 | 4 | 0.4285 | 0.75 |
73
- | No log | 5.0 | 5 | 0.4803 | 0.75 |
74
- | No log | 6.0 | 6 | 0.4423 | 0.75 |
75
- | No log | 7.0 | 7 | 0.3370 | 0.75 |
76
- | No log | 8.0 | 8 | 0.2495 | 1.0 |
77
- | No log | 9.0 | 9 | 0.1909 | 1.0 |
78
- | 0.1032 | 10.0 | 10 | 0.1470 | 1.0 |
79
- | 0.1032 | 11.0 | 11 | 0.1294 | 1.0 |
80
- | 0.1032 | 12.0 | 12 | 0.1204 | 1.0 |
81
- | 0.1032 | 13.0 | 13 | 0.1102 | 1.0 |
82
- | 0.1032 | 14.0 | 14 | 0.1067 | 1.0 |
83
- | 0.1032 | 15.0 | 15 | 0.1072 | 1.0 |
84
- | 0.1032 | 16.0 | 16 | 0.1085 | 1.0 |
85
- | 0.1032 | 17.0 | 17 | 0.1152 | 1.0 |
86
- | 0.1032 | 18.0 | 18 | 0.1272 | 1.0 |
87
- | 0.1032 | 19.0 | 19 | 0.1370 | 1.0 |
88
- | 0.0647 | 20.0 | 20 | 0.1418 | 1.0 |
89
 
90
 
91
  ### Framework versions
92
 
93
- - Transformers 4.21.2
94
  - Pytorch 1.12.1+cu113
95
  - Datasets 2.4.0
96
  - Tokenizers 0.12.1
 
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: 0.3026
35
  - Accuracy: 1.0
36
 
37
  ## Model description
 
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
+ | No log | 1.0 | 1 | 1.0940 | 0.25 |
70
+ | No log | 2.0 | 2 | 0.9836 | 0.25 |
71
+ | No log | 3.0 | 3 | 0.7624 | 0.25 |
72
+ | No log | 4.0 | 4 | 0.6527 | 0.5 |
73
+ | No log | 5.0 | 5 | 0.5697 | 0.75 |
74
+ | No log | 6.0 | 6 | 0.5167 | 1.0 |
75
+ | No log | 7.0 | 7 | 0.4898 | 0.75 |
76
+ | No log | 8.0 | 8 | 0.4572 | 0.75 |
77
+ | No log | 9.0 | 9 | 0.4286 | 0.75 |
78
+ | 0.299 | 10.0 | 10 | 0.3976 | 0.75 |
79
+ | 0.299 | 11.0 | 11 | 0.3678 | 1.0 |
80
+ | 0.299 | 12.0 | 12 | 0.3531 | 1.0 |
81
+ | 0.299 | 13.0 | 13 | 0.3384 | 1.0 |
82
+ | 0.299 | 14.0 | 14 | 0.3264 | 1.0 |
83
+ | 0.299 | 15.0 | 15 | 0.3188 | 1.0 |
84
+ | 0.299 | 16.0 | 16 | 0.3114 | 1.0 |
85
+ | 0.299 | 17.0 | 17 | 0.3083 | 1.0 |
86
+ | 0.299 | 18.0 | 18 | 0.3071 | 1.0 |
87
+ | 0.299 | 19.0 | 19 | 0.3041 | 1.0 |
88
+ | 0.2051 | 20.0 | 20 | 0.3026 | 1.0 |
89
 
90
 
91
  ### Framework versions
92
 
93
+ - Transformers 4.21.3
94
  - Pytorch 1.12.1+cu113
95
  - Datasets 2.4.0
96
  - Tokenizers 0.12.1