Hugging Face's logo

Yogesh1p
/
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
Yogesh1p commited on
Commit
b6f7180
•
1 Parent(s): 459b57f

Model save

Browse files
Files changed (3) hide show
  1. README.md +15 -8
  2. model.safetensors +1 -1
  3. runs/Nov17_09-35-47_5aafc1ba1313/events.out.tfevents.1700213755.5aafc1ba1313.3404.0 +2 -2
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.5208333333333334
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: 0.7238
36
- - Accuracy: 0.5208
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
- | No log | 0.86 | 3 | 0.7238 | 0.5208 |
71
- | No log | 2.0 | 7 | 0.6829 | 0.5208 |
72
- | No log | 2.57 | 9 | 0.6899 | 0.5208 |
 
 
 
 
 
 
 
73
 
74
 
75
  ### Framework versions
76
 
77
  - Transformers 4.35.2
78
  - Pytorch 2.1.0+cu118
79
- - Datasets 2.14.7
80
  - Tokenizers 0.15.0
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.7555555555555555
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: 0.4821
36
+ - Accuracy: 0.7556
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
+ | No log | 0.92 | 3 | 0.8976 | 0.6 |
71
+ | No log | 1.85 | 6 | 0.9456 | 0.4889 |
72
+ | No log | 2.77 | 9 | 0.7695 | 0.6222 |
73
+ | 0.8575 | 4.0 | 13 | 0.5789 | 0.7778 |
74
+ | 0.8575 | 4.92 | 16 | 0.5423 | 0.7333 |
75
+ | 0.8575 | 5.85 | 19 | 0.5269 | 0.7111 |
76
+ | 0.5728 | 6.77 | 22 | 0.4836 | 0.7556 |
77
+ | 0.5728 | 8.0 | 26 | 0.4813 | 0.7556 |
78
+ | 0.5728 | 8.92 | 29 | 0.4823 | 0.7556 |
79
+ | 0.504 | 9.23 | 30 | 0.4821 | 0.7556 |
80
 
81
 
82
  ### Framework versions
83
 
84
  - Transformers 4.35.2
85
  - Pytorch 2.1.0+cu118
86
+ - Datasets 2.15.0
87
  - Tokenizers 0.15.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ad0c6a246fccacc6137445cc460135d472921849fab34cfead88a88940c9697
3
  size 110345908
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:776685b28f2734abb56daeb800e7a986b48391a6cab4b693e1a9b01ba53a0d02
3
  size 110345908
runs/Nov17_09-35-47_5aafc1ba1313/events.out.tfevents.1700213755.5aafc1ba1313.3404.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d95efcafa47382f5084195612b90101f6b9c83af7dfa2479aca8e651a8de33f1
3
- size 7932
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ae6ab30fde1e5adf46d71427da5bc3b1474c2080c54abf936d175b2a2b032e5
3
+ size 8751