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
3642f0d
•
1 Parent(s): ba1a6d2

Model save

Browse files
Files changed (2) hide show
  1. README.md +53 -24
  2. model.safetensors +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.9102040816326531
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: 0.3980
36
- - Accuracy: 0.9102
37
 
38
  ## Model description
39
 
@@ -61,32 +61,61 @@ 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: 20
65
 
66
  ### Training results
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
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.963265306122449
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: 0.1172
36
+ - Accuracy: 0.9633
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: 50
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | 4.0243 | 0.98 | 30 | 3.9884 | 0.0204 |
71
+ | 3.7051 | 1.98 | 61 | 3.6012 | 0.0776 |
72
+ | 3.2036 | 2.99 | 92 | 2.9556 | 0.2939 |
73
+ | 2.6413 | 4.0 | 123 | 2.3054 | 0.4531 |
74
+ | 2.1015 | 4.98 | 153 | 1.7366 | 0.5224 |
75
+ | 1.6508 | 5.98 | 184 | 1.3509 | 0.6367 |
76
+ | 1.3986 | 6.99 | 215 | 1.0938 | 0.7163 |
77
+ | 1.1918 | 8.0 | 246 | 0.9012 | 0.7735 |
78
+ | 1.0633 | 8.98 | 276 | 0.7464 | 0.8143 |
79
+ | 0.8771 | 9.98 | 307 | 0.6569 | 0.8306 |
80
+ | 0.8309 | 10.99 | 338 | 0.5536 | 0.8551 |
81
+ | 0.7093 | 12.0 | 369 | 0.4795 | 0.8796 |
82
+ | 0.6579 | 12.98 | 399 | 0.4176 | 0.8837 |
83
+ | 0.5827 | 13.98 | 430 | 0.3888 | 0.8980 |
84
+ | 0.5418 | 14.99 | 461 | 0.3255 | 0.9122 |
85
+ | 0.5102 | 16.0 | 492 | 0.3139 | 0.9265 |
86
+ | 0.472 | 16.98 | 522 | 0.3141 | 0.9163 |
87
+ | 0.4273 | 17.98 | 553 | 0.2673 | 0.9245 |
88
+ | 0.384 | 18.99 | 584 | 0.2487 | 0.9265 |
89
+ | 0.3917 | 20.0 | 615 | 0.2353 | 0.9388 |
90
+ | 0.418 | 20.98 | 645 | 0.2113 | 0.9490 |
91
+ | 0.3662 | 21.98 | 676 | 0.2095 | 0.9327 |
92
+ | 0.3258 | 22.99 | 707 | 0.2139 | 0.9429 |
93
+ | 0.3268 | 24.0 | 738 | 0.1962 | 0.9449 |
94
+ | 0.3048 | 24.98 | 768 | 0.1935 | 0.9408 |
95
+ | 0.2696 | 25.98 | 799 | 0.2112 | 0.9408 |
96
+ | 0.2524 | 26.99 | 830 | 0.2310 | 0.9306 |
97
+ | 0.2491 | 28.0 | 861 | 0.1827 | 0.9449 |
98
+ | 0.2542 | 28.98 | 891 | 0.1720 | 0.9592 |
99
+ | 0.2898 | 29.98 | 922 | 0.1605 | 0.9490 |
100
+ | 0.2298 | 30.99 | 953 | 0.1326 | 0.9633 |
101
+ | 0.2137 | 32.0 | 984 | 0.1438 | 0.9571 |
102
+ | 0.2002 | 32.98 | 1014 | 0.1379 | 0.9551 |
103
+ | 0.2013 | 33.98 | 1045 | 0.1261 | 0.9653 |
104
+ | 0.1862 | 34.99 | 1076 | 0.1674 | 0.9408 |
105
+ | 0.1993 | 36.0 | 1107 | 0.1423 | 0.9571 |
106
+ | 0.2063 | 36.98 | 1137 | 0.1406 | 0.9592 |
107
+ | 0.2088 | 37.98 | 1168 | 0.1717 | 0.9429 |
108
+ | 0.1711 | 38.99 | 1199 | 0.1539 | 0.9510 |
109
+ | 0.1804 | 40.0 | 1230 | 0.1421 | 0.9571 |
110
+ | 0.1793 | 40.98 | 1260 | 0.0765 | 0.9776 |
111
+ | 0.2139 | 41.98 | 1291 | 0.1859 | 0.9449 |
112
+ | 0.1678 | 42.99 | 1322 | 0.1067 | 0.9796 |
113
+ | 0.1675 | 44.0 | 1353 | 0.0985 | 0.9735 |
114
+ | 0.1681 | 44.98 | 1383 | 0.1093 | 0.9653 |
115
+ | 0.1625 | 45.98 | 1414 | 0.1402 | 0.9592 |
116
+ | 0.1987 | 46.99 | 1445 | 0.1250 | 0.9673 |
117
+ | 0.1728 | 48.0 | 1476 | 0.1293 | 0.9633 |
118
+ | 0.1337 | 48.78 | 1500 | 0.1172 | 0.9633 |
119
 
120
 
121
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1e19d12ee9fdf0b8e5d457e26def075ca927726e745f7f0bceaaab149860289e
3
  size 44860804
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b928a5e6d8b9bc888fa263180f1f56b06e65b3de046d94453f8e1072f131fec4
3
  size 44860804