Hugging Face's logo

vintage-lavender619
/
swinv2-tiny-patch4-window8-256-finalterm

Image Classification
Transformers
TensorBoard
Safetensors
swinv2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
vintage-lavender619 commited on
Commit
48cabee
·
verified ·
1 Parent(s): fccc0f7

Model save

Browse files
Files changed (2) hide show
  1. README.md +23 -23
  2. model.safetensors +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.89375
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/swinv2-tiny-patch4-window8-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.3096
36
- - Accuracy: 0.8938
37
 
38
  ## Model description
39
 
@@ -67,26 +67,26 @@ The following hyperparameters were used during training:
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | 1.3728 | 1.0 | 10 | 1.2644 | 0.5156 |
71
- | 1.1308 | 2.0 | 20 | 0.8816 | 0.625 |
72
- | 0.8721 | 3.0 | 30 | 0.6829 | 0.7063 |
73
- | 0.6919 | 4.0 | 40 | 0.5298 | 0.8063 |
74
- | 0.5876 | 5.0 | 50 | 0.4100 | 0.8688 |
75
- | 0.5504 | 6.0 | 60 | 0.4153 | 0.8531 |
76
- | 0.459 | 7.0 | 70 | 0.3828 | 0.8594 |
77
- | 0.4501 | 8.0 | 80 | 0.3941 | 0.8625 |
78
- | 0.4312 | 9.0 | 90 | 0.3650 | 0.8719 |
79
- | 0.4119 | 10.0 | 100 | 0.3515 | 0.875 |
80
- | 0.4014 | 11.0 | 110 | 0.3110 | 0.8969 |
81
- | 0.3896 | 12.0 | 120 | 0.3030 | 0.9031 |
82
- | 0.3822 | 13.0 | 130 | 0.3473 | 0.8812 |
83
- | 0.3985 | 14.0 | 140 | 0.3288 | 0.8875 |
84
- | 0.3826 | 15.0 | 150 | 0.2925 | 0.9 |
85
- | 0.3716 | 16.0 | 160 | 0.3619 | 0.875 |
86
- | 0.365 | 17.0 | 170 | 0.2941 | 0.9 |
87
- | 0.3379 | 18.0 | 180 | 0.3239 | 0.8844 |
88
- | 0.3365 | 19.0 | 190 | 0.3260 | 0.8906 |
89
- | 0.3429 | 20.0 | 200 | 0.3096 | 0.8938 |
90
 
91
 
92
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.9
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/swinv2-tiny-patch4-window8-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.2805
36
+ - Accuracy: 0.9
37
 
38
  ## Model description
39
 
 
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | 1.3578 | 1.0 | 10 | 1.2444 | 0.475 |
71
+ | 1.1054 | 2.0 | 20 | 0.9180 | 0.6531 |
72
+ | 0.8485 | 3.0 | 30 | 0.6632 | 0.725 |
73
+ | 0.674 | 4.0 | 40 | 0.4736 | 0.7969 |
74
+ | 0.5968 | 5.0 | 50 | 0.4341 | 0.8125 |
75
+ | 0.508 | 6.0 | 60 | 0.5391 | 0.8187 |
76
+ | 0.4852 | 7.0 | 70 | 0.3906 | 0.8344 |
77
+ | 0.4354 | 8.0 | 80 | 0.3257 | 0.8656 |
78
+ | 0.4165 | 9.0 | 90 | 0.3478 | 0.8656 |
79
+ | 0.4385 | 10.0 | 100 | 0.3114 | 0.8781 |
80
+ | 0.4156 | 11.0 | 110 | 0.3461 | 0.8781 |
81
+ | 0.4055 | 12.0 | 120 | 0.3108 | 0.8844 |
82
+ | 0.4282 | 13.0 | 130 | 0.2916 | 0.8875 |
83
+ | 0.3546 | 14.0 | 140 | 0.2972 | 0.9 |
84
+ | 0.3608 | 15.0 | 150 | 0.3428 | 0.8688 |
85
+ | 0.369 | 16.0 | 160 | 0.2885 | 0.8969 |
86
+ | 0.3525 | 17.0 | 170 | 0.2861 | 0.9 |
87
+ | 0.338 | 18.0 | 180 | 0.2832 | 0.9062 |
88
+ | 0.3633 | 19.0 | 190 | 0.2797 | 0.9031 |
89
+ | 0.3712 | 20.0 | 200 | 0.2805 | 0.9 |
90
 
91
 
92
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:16d99c9c68650fc6e8704f3a3eec88cf82949eb0412a5da2872bce58fd164f65
3
  size 110356296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0aa7e94aac65bb0840defc0428d64be163c667c262e290ac9831079d30996222
3
  size 110356296