Hugging Face's logo

tdhcuong
/
swin-tiny-patch4-window7-224-finetuned-azure-poc-img-classification

Image Classification
Transformers
Safetensors
swin
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
tdhcuong commited on
Commit
5bb9e53
·
verified ·
1 Parent(s): b9eefa1

Model save

Browse files
Files changed (1) hide show
  1. README.md +14 -9
README.md CHANGED
@@ -23,7 +23,7 @@ model-index:
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
- value: 0.9139414802065404
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,8 +33,8 @@ should probably proofread and complete it, then remove this comment. -->
33
 
34
  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.
35
  It achieves the following results on the evaluation set:
36
- - Loss: 0.2522
37
- - Accuracy: 0.9139
38
 
39
  ## Model description
40
 
@@ -62,17 +62,22 @@ The following hyperparameters were used during training:
62
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
63
  - lr_scheduler_type: linear
64
  - lr_scheduler_warmup_ratio: 0.1
65
- - num_epochs: 5
66
 
67
  ### Training results
68
 
69
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
70
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
71
- | 0.4227 | 1.0 | 41 | 0.3246 | 0.8898 |
72
- | 0.3169 | 2.0 | 82 | 0.2736 | 0.8950 |
73
- | 0.2632 | 3.0 | 123 | 0.2522 | 0.9139 |
74
- | 0.2034 | 4.0 | 164 | 0.2449 | 0.8985 |
75
- | 0.1984 | 5.0 | 205 | 0.2464 | 0.8985 |
 
 
 
 
 
76
 
77
 
78
  ### Framework versions
 
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
+ value: 0.9122203098106713
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
33
 
34
  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.
35
  It achieves the following results on the evaluation set:
36
+ - Loss: 0.2119
37
+ - Accuracy: 0.9122
38
 
39
  ## Model description
40
 
 
62
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
63
  - lr_scheduler_type: linear
64
  - lr_scheduler_warmup_ratio: 0.1
65
+ - num_epochs: 10
66
 
67
  ### Training results
68
 
69
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
70
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
71
+ | 0.5888 | 1.0 | 41 | 0.4436 | 0.8348 |
72
+ | 0.3118 | 2.0 | 82 | 0.3028 | 0.8692 |
73
+ | 0.2284 | 3.0 | 123 | 0.2879 | 0.8795 |
74
+ | 0.203 | 4.0 | 164 | 0.2368 | 0.8950 |
75
+ | 0.2254 | 5.0 | 205 | 0.2276 | 0.8985 |
76
+ | 0.1976 | 6.0 | 246 | 0.2339 | 0.8967 |
77
+ | 0.1603 | 7.0 | 287 | 0.2191 | 0.9036 |
78
+ | 0.1556 | 8.0 | 328 | 0.2249 | 0.9036 |
79
+ | 0.1488 | 9.0 | 369 | 0.2018 | 0.9071 |
80
+ | 0.158 | 10.0 | 410 | 0.2119 | 0.9122 |
81
 
82
 
83
  ### Framework versions