Hugging Face's logo

gaborcselle
/
font-identifier

Image Classification
Transformers
TensorBoard
Safetensors
English
resnet
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
gaborcselle commited on
Commit
3470dcd
•
1 Parent(s): e7fcef0

Model save

Browse files
Files changed (1) hide show
  1. README.md +23 -23
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.9040816326530612
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/resnet-18](https://huggingface.co/microsoft/resnet-18) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.3626
36
- - Accuracy: 0.9041
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
- | 3.929 | 0.98 | 30 | 3.8215 | 0.0429 |
71
- | 3.2162 | 1.98 | 61 | 2.9144 | 0.2816 |
72
- | 2.4387 | 2.99 | 92 | 2.1019 | 0.4776 |
73
- | 1.9404 | 4.0 | 123 | 1.5607 | 0.6041 |
74
- | 1.5756 | 4.98 | 153 | 1.3012 | 0.6449 |
75
- | 1.3374 | 5.98 | 184 | 1.0699 | 0.7102 |
76
- | 1.1912 | 6.99 | 215 | 0.9145 | 0.7633 |
77
- | 1.0716 | 8.0 | 246 | 0.7864 | 0.7898 |
78
- | 0.9751 | 8.98 | 276 | 0.6894 | 0.8204 |
79
- | 0.8211 | 9.98 | 307 | 0.6256 | 0.8510 |
80
- | 0.8254 | 10.99 | 338 | 0.5563 | 0.8633 |
81
- | 0.742 | 12.0 | 369 | 0.5149 | 0.8694 |
82
- | 0.6949 | 12.98 | 399 | 0.4625 | 0.8878 |
83
- | 0.6401 | 13.98 | 430 | 0.4799 | 0.8857 |
84
- | 0.6304 | 14.99 | 461 | 0.3970 | 0.8980 |
85
- | 0.6239 | 16.0 | 492 | 0.4016 | 0.9 |
86
- | 0.5911 | 16.98 | 522 | 0.4271 | 0.8755 |
87
- | 0.5764 | 17.98 | 553 | 0.3922 | 0.9 |
88
- | 0.5461 | 18.99 | 584 | 0.3750 | 0.9 |
89
- | 0.6236 | 19.51 | 600 | 0.3626 | 0.9041 |
90
 
91
 
92
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.9102040816326531
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/resnet-18](https://huggingface.co/microsoft/resnet-18) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.3980
36
+ - Accuracy: 0.9102
37
 
38
  ## Model description
39
 
 
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | 3.9105 | 0.98 | 30 | 3.7931 | 0.0551 |
71
+ | 3.2821 | 1.98 | 61 | 2.9878 | 0.2755 |
72
+ | 2.4752 | 2.99 | 92 | 2.1760 | 0.4408 |
73
+ | 1.9958 | 4.0 | 123 | 1.6964 | 0.5327 |
74
+ | 1.6609 | 4.98 | 153 | 1.4001 | 0.6265 |
75
+ | 1.4328 | 5.98 | 184 | 1.1766 | 0.6796 |
76
+ | 1.2677 | 6.99 | 215 | 1.0262 | 0.7163 |
77
+ | 1.1174 | 8.0 | 246 | 0.8758 | 0.7653 |
78
+ | 1.0564 | 8.98 | 276 | 0.7675 | 0.8184 |
79
+ | 0.9003 | 9.98 | 307 | 0.7161 | 0.8286 |
80
+ | 0.8711 | 10.99 | 338 | 0.6461 | 0.8224 |
81
+ | 0.7954 | 12.0 | 369 | 0.5683 | 0.8653 |
82
+ | 0.743 | 12.98 | 399 | 0.5438 | 0.8510 |
83
+ | 0.6914 | 13.98 | 430 | 0.5129 | 0.8878 |
84
+ | 0.6714 | 14.99 | 461 | 0.4418 | 0.8857 |
85
+ | 0.663 | 16.0 | 492 | 0.4555 | 0.8694 |
86
+ | 0.6326 | 16.98 | 522 | 0.4746 | 0.8755 |
87
+ | 0.5831 | 17.98 | 553 | 0.4263 | 0.8776 |
88
+ | 0.571 | 18.99 | 584 | 0.4305 | 0.8857 |
89
+ | 0.6543 | 19.51 | 600 | 0.3980 | 0.9102 |
90
 
91
 
92
  ### Framework versions