Hugging Face's logo

bliebfl
/
swin-tiny-patch4-window7-224-finetuned-kuzushiji

Image Classification
Transformers
TensorBoard
Safetensors
swin
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
bliebfl commited on
Commit
a6fa687
•
1 Parent(s): dbd6f47

Model save

Browse files
Files changed (2) hide show
  1. README.md +14 -7
  2. model.safetensors +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.7496974935177182
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: 1.2842
36
- - Accuracy: 0.7497
37
 
38
  ## Model description
39
 
@@ -61,15 +61,22 @@ 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
- | 2.5294 | 1.0 | 406 | 2.1071 | 0.5865 |
71
- | 1.9362 | 2.0 | 813 | 1.4541 | 0.7219 |
72
- | 1.8206 | 2.99 | 1218 | 1.2842 | 0.7497 |
 
 
 
 
 
 
 
73
 
74
 
75
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.9403630077787382
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: 0.3101
36
+ - Accuracy: 0.9404
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
+ | 1.5645 | 1.0 | 406 | 1.0880 | 0.7905 |
71
+ | 1.3126 | 2.0 | 813 | 0.7987 | 0.8399 |
72
+ | 1.2335 | 3.0 | 1220 | 0.6398 | 0.8742 |
73
+ | 1.1244 | 4.0 | 1627 | 0.4977 | 0.9041 |
74
+ | 0.9785 | 5.0 | 2033 | 0.4473 | 0.9139 |
75
+ | 0.9625 | 6.0 | 2440 | 0.3930 | 0.9200 |
76
+ | 0.8414 | 7.0 | 2847 | 0.3538 | 0.9328 |
77
+ | 0.8336 | 8.0 | 3254 | 0.3333 | 0.9334 |
78
+ | 0.758 | 9.0 | 3660 | 0.3181 | 0.9405 |
79
+ | 0.7343 | 9.98 | 4060 | 0.3101 | 0.9404 |
80
 
81
 
82
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d94685f6e0f6bc8e9029baf4bb1a3fed2d4c7c3f284d19c1e04f12ef596974ce
3
  size 112253100
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:480c3209d3d179b1d3d5f69bb0ee9daac3445e4c0b4b5fe353a85dabc2c3cacf
3
  size 112253100