Hugging Face's logo

Alex-VisTas
/
swin-tiny-patch4-window7-224-finetuned-woody

Image Classification
Transformers
PyTorch
TensorBoard
swin
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
1
Alex-VisTas commited on
Commit
09e00e7
·
1 Parent(s): 7a507ea

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +35 -11
README.md CHANGED
@@ -21,7 +21,7 @@ model-index:
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
- value: 0.7321212121212122
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: 0.5392
35
- - Accuracy: 0.7321
36
 
37
  ## Model description
38
 
@@ -60,23 +60,47 @@ 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: 6
64
 
65
  ### Training results
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
- | 0.574 | 1.0 | 58 | 0.5392 | 0.7321 |
70
- | 0.5784 | 2.0 | 116 | 0.5392 | 0.7321 |
71
- | 0.5476 | 3.0 | 174 | 0.5392 | 0.7321 |
72
- | 0.5571 | 4.0 | 232 | 0.5392 | 0.7321 |
73
- | 0.5577 | 5.0 | 290 | 0.5392 | 0.7321 |
74
- | 0.5625 | 6.0 | 348 | 0.5392 | 0.7321 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
75
 
76
 
77
  ### Framework versions
78
 
79
  - Transformers 4.23.1
80
  - Pytorch 1.12.1+cu113
81
- - Datasets 2.5.2
82
  - Tokenizers 0.13.1
 
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
+ value: 0.7927272727272727
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: 0.4349
35
+ - Accuracy: 0.7927
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: 30
64
 
65
  ### Training results
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
+ | 0.632 | 1.0 | 58 | 0.5883 | 0.6836 |
70
+ | 0.6067 | 2.0 | 116 | 0.6017 | 0.6848 |
71
+ | 0.5865 | 3.0 | 174 | 0.5695 | 0.7042 |
72
+ | 0.553 | 4.0 | 232 | 0.5185 | 0.7515 |
73
+ | 0.5468 | 5.0 | 290 | 0.5108 | 0.7430 |
74
+ | 0.5473 | 6.0 | 348 | 0.4882 | 0.7648 |
75
+ | 0.5381 | 7.0 | 406 | 0.4800 | 0.7588 |
76
+ | 0.5468 | 8.0 | 464 | 0.5056 | 0.7358 |
77
+ | 0.5191 | 9.0 | 522 | 0.4784 | 0.7673 |
78
+ | 0.5318 | 10.0 | 580 | 0.4762 | 0.7636 |
79
+ | 0.5079 | 11.0 | 638 | 0.4859 | 0.7673 |
80
+ | 0.5216 | 12.0 | 696 | 0.4691 | 0.7697 |
81
+ | 0.515 | 13.0 | 754 | 0.4857 | 0.7624 |
82
+ | 0.5186 | 14.0 | 812 | 0.4685 | 0.7733 |
83
+ | 0.4748 | 15.0 | 870 | 0.4536 | 0.7818 |
84
+ | 0.4853 | 16.0 | 928 | 0.4617 | 0.7770 |
85
+ | 0.4868 | 17.0 | 986 | 0.4622 | 0.7782 |
86
+ | 0.4572 | 18.0 | 1044 | 0.4583 | 0.7770 |
87
+ | 0.4679 | 19.0 | 1102 | 0.4590 | 0.7733 |
88
+ | 0.4508 | 20.0 | 1160 | 0.4576 | 0.7903 |
89
+ | 0.4663 | 21.0 | 1218 | 0.4542 | 0.7891 |
90
+ | 0.4533 | 22.0 | 1276 | 0.4428 | 0.7903 |
91
+ | 0.4892 | 23.0 | 1334 | 0.4372 | 0.7867 |
92
+ | 0.4704 | 24.0 | 1392 | 0.4414 | 0.7903 |
93
+ | 0.4304 | 25.0 | 1450 | 0.4430 | 0.7988 |
94
+ | 0.4411 | 26.0 | 1508 | 0.4348 | 0.7818 |
95
+ | 0.4604 | 27.0 | 1566 | 0.4387 | 0.7927 |
96
+ | 0.441 | 28.0 | 1624 | 0.4378 | 0.7964 |
97
+ | 0.442 | 29.0 | 1682 | 0.4351 | 0.7915 |
98
+ | 0.4585 | 30.0 | 1740 | 0.4349 | 0.7927 |
99
 
100
 
101
  ### Framework versions
102
 
103
  - Transformers 4.23.1
104
  - Pytorch 1.12.1+cu113
105
+ - Datasets 2.6.0
106
  - Tokenizers 0.13.1