Hugging Face's logo

morganchen1007
/
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
morganchen1007 commited on
Commit
9d8b3ff
·
1 Parent(s): d3cb68a

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +16 -7
README.md CHANGED
@@ -21,7 +21,7 @@ model-index:
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
- value: 0.948729184925504
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: 0.1460
35
- - Accuracy: 0.9487
36
 
37
  ## Model description
38
 
@@ -60,15 +60,24 @@ 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: 3
64
 
65
  ### Training results
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
- | 0.2751 | 1.0 | 160 | 0.1808 | 0.9233 |
70
- | 0.2127 | 2.0 | 320 | 0.1461 | 0.9443 |
71
- | 0.1935 | 3.0 | 480 | 0.1460 | 0.9487 |
 
 
 
 
 
 
 
 
 
72
 
73
 
74
  ### Framework versions
 
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
+ value: 0.9341978866474544
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: 0.1507
35
+ - Accuracy: 0.9342
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: 12
64
 
65
  ### Training results
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
+ | 0.2891 | 1.0 | 146 | 0.2322 | 0.9068 |
70
+ | 0.2609 | 2.0 | 292 | 0.1710 | 0.9227 |
71
+ | 0.2417 | 3.0 | 438 | 0.1830 | 0.9251 |
72
+ | 0.2406 | 4.0 | 584 | 0.1809 | 0.9198 |
73
+ | 0.2113 | 5.0 | 730 | 0.1631 | 0.9289 |
74
+ | 0.1812 | 6.0 | 876 | 0.1561 | 0.9308 |
75
+ | 0.2082 | 7.0 | 1022 | 0.1507 | 0.9342 |
76
+ | 0.1922 | 8.0 | 1168 | 0.1611 | 0.9294 |
77
+ | 0.1715 | 9.0 | 1314 | 0.1536 | 0.9308 |
78
+ | 0.1675 | 10.0 | 1460 | 0.1609 | 0.9289 |
79
+ | 0.194 | 11.0 | 1606 | 0.1499 | 0.9337 |
80
+ | 0.1706 | 12.0 | 1752 | 0.1514 | 0.9323 |
81
 
82
 
83
  ### Framework versions