Hugging Face's logo

Prachetas
/
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
Prachetas commited on
Commit
d802897
•
1 Parent(s): cd86695

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +15 -20
README.md CHANGED
@@ -21,7 +21,7 @@ model-index:
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
- value: 0.7989690721649485
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: 0.6150
35
- - Accuracy: 0.7990
36
 
37
  ## Model description
38
 
@@ -60,32 +60,27 @@ The following hyperparameters were used during training:
60
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
  - lr_scheduler_type: linear
62
  - lr_scheduler_warmup_ratio: 0.1
63
- - num_epochs: 15
64
 
65
  ### Training results
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
- | No log | 0.96 | 6 | 1.1081 | 0.6701 |
70
- | 0.6578 | 1.92 | 12 | 0.7939 | 0.6701 |
71
- | 0.6578 | 2.88 | 18 | 0.7289 | 0.7784 |
72
- | 0.8064 | 4.0 | 25 | 0.7616 | 0.6804 |
73
- | 0.7259 | 4.96 | 31 | 0.6280 | 0.7320 |
74
- | 0.7259 | 5.92 | 37 | 0.6325 | 0.7474 |
75
- | 0.6316 | 6.88 | 43 | 0.6799 | 0.7320 |
76
- | 0.607 | 8.0 | 50 | 0.7444 | 0.7887 |
77
- | 0.607 | 8.96 | 56 | 0.6150 | 0.7990 |
78
- | 0.5268 | 9.92 | 62 | 0.5973 | 0.7577 |
79
- | 0.5268 | 10.88 | 68 | 0.7381 | 0.7732 |
80
- | 0.4797 | 12.0 | 75 | 0.6777 | 0.7732 |
81
- | 0.4618 | 12.96 | 81 | 0.6430 | 0.7887 |
82
- | 0.4618 | 13.92 | 87 | 0.6717 | 0.7784 |
83
- | 0.3618 | 14.4 | 90 | 0.6744 | 0.7938 |
84
 
85
 
86
  ### Framework versions
87
 
88
- - Transformers 4.29.1
89
  - Pytorch 2.0.0+cu118
90
  - Datasets 2.12.0
91
  - Tokenizers 0.13.3
 
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
+ value: 0.8247422680412371
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: 0.5465
35
+ - Accuracy: 0.8247
36
 
37
  ## Model description
38
 
 
60
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
  - lr_scheduler_type: linear
62
  - lr_scheduler_warmup_ratio: 0.1
63
+ - num_epochs: 10
64
 
65
  ### Training results
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
+ | No log | 1.0 | 7 | 1.2679 | 0.2990 |
70
+ | 1.3643 | 2.0 | 14 | 1.1288 | 0.5258 |
71
+ | 1.0267 | 3.0 | 21 | 0.6534 | 0.7010 |
72
+ | 1.0267 | 4.0 | 28 | 0.6587 | 0.7629 |
73
+ | 0.6635 | 5.0 | 35 | 0.7360 | 0.6701 |
74
+ | 0.5462 | 6.0 | 42 | 0.6479 | 0.7320 |
75
+ | 0.5462 | 7.0 | 49 | 0.5546 | 0.7835 |
76
+ | 0.4471 | 8.0 | 56 | 0.5583 | 0.7835 |
77
+ | 0.3094 | 9.0 | 63 | 0.5257 | 0.8247 |
78
+ | 0.242 | 10.0 | 70 | 0.5465 | 0.8247 |
 
 
 
 
 
79
 
80
 
81
  ### Framework versions
82
 
83
+ - Transformers 4.28.0
84
  - Pytorch 2.0.0+cu118
85
  - Datasets 2.12.0
86
  - Tokenizers 0.13.3