Hugging Face's logo

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

Image Classification
Transformers
TensorBoard
Safetensors
swin
generated_from_trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
mohameddemes commited on
Commit
17059cd
•
1 Parent(s): 033b4a9

Model save

Browse files
Files changed (1) hide show
  1. README.md +15 -8
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.9011764705882352
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: 0.2882
36
- - Accuracy: 0.9012
37
 
38
  ## Model description
39
 
@@ -61,20 +61,27 @@ 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: 3
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | 0.9086 | 1.0 | 30 | 0.5747 | 0.8118 |
71
- | 0.5057 | 2.0 | 60 | 0.3523 | 0.8706 |
72
- | 0.4594 | 3.0 | 90 | 0.2882 | 0.9012 |
 
 
 
 
 
 
 
73
 
74
 
75
  ### Framework versions
76
 
77
- - Transformers 4.39.2
78
  - Pytorch 2.2.2+cu121
79
  - Datasets 2.18.0
80
  - Tokenizers 0.15.2
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.9764705882352941
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: 0.0625
36
+ - Accuracy: 0.9765
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
+ | 1.506 | 1.0 | 30 | 1.1397 | 0.5976 |
71
+ | 0.5645 | 2.0 | 60 | 0.3396 | 0.88 |
72
+ | 0.4507 | 3.0 | 90 | 0.1972 | 0.9247 |
73
+ | 0.418 | 4.0 | 120 | 0.1484 | 0.9506 |
74
+ | 0.3169 | 5.0 | 150 | 0.1866 | 0.92 |
75
+ | 0.3346 | 6.0 | 180 | 0.0973 | 0.9718 |
76
+ | 0.2823 | 7.0 | 210 | 0.0973 | 0.9694 |
77
+ | 0.2711 | 8.0 | 240 | 0.0805 | 0.9671 |
78
+ | 0.2638 | 9.0 | 270 | 0.0749 | 0.9718 |
79
+ | 0.2755 | 10.0 | 300 | 0.0625 | 0.9765 |
80
 
81
 
82
  ### Framework versions
83
 
84
+ - Transformers 4.39.3
85
  - Pytorch 2.2.2+cu121
86
  - Datasets 2.18.0
87
  - Tokenizers 0.15.2