Instructions to use mlahr/font-identifier with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mlahr/font-identifier with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="mlahr/font-identifier") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# Load model directly from transformers import AutoImageProcessor, AutoModelForImageClassification processor = AutoImageProcessor.from_pretrained("mlahr/font-identifier") model = AutoModelForImageClassification.from_pretrained("mlahr/font-identifier") - Notebooks
- Google Colab
- Kaggle
Model save
Browse files- README.md +53 -53
- config.json +0 -1
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -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/resnet-18](https://huggingface.co/microsoft/resnet-18) on the imagefolder dataset.
|
| 35 |
It achieves the following results on the evaluation set:
|
| 36 |
-
- Loss: 0.2760
|
| 37 |
- Accuracy: 0.9162
|
|
|
|
| 38 |
|
| 39 |
## Model description
|
| 40 |
|
|
@@ -66,58 +66,58 @@ The following hyperparameters were used during training:
|
|
| 66 |
|
| 67 |
### Training results
|
| 68 |
|
| 69 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
| 70 |
-
|:-------------:|:-----:|:----:|:---------------
|
| 71 |
-
| 3.7676 | 1.0 | 24 |
|
| 72 |
-
| 3.607 | 2.0 | 48 |
|
| 73 |
-
| 3.2234 | 3.0 | 72 |
|
| 74 |
-
| 2.8944 | 4.0 | 96 |
|
| 75 |
-
| 2.1637 | 5.0 | 120 |
|
| 76 |
-
| 1.9347 | 6.0 | 144 |
|
| 77 |
-
| 1.6851 | 7.0 | 168 |
|
| 78 |
-
| 1.369 | 8.0 | 192 |
|
| 79 |
-
| 1.2987 | 9.0 | 216 | 0.
|
| 80 |
-
| 1.1044 | 10.0 | 240 | 0.
|
| 81 |
-
| 1.044 | 11.0 | 264 | 0.
|
| 82 |
-
| 1.0134 | 12.0 | 288 | 0.
|
| 83 |
-
| 0.9284 | 13.0 | 312 | 0.
|
| 84 |
-
| 0.8603 | 14.0 | 336 | 0.
|
| 85 |
-
| 0.7748 | 15.0 | 360 | 0.
|
| 86 |
-
| 0.8133 | 16.0 | 384 | 0.
|
| 87 |
-
| 0.8379 | 17.0 | 408 | 0.
|
| 88 |
-
| 0.751 | 18.0 | 432 | 0.
|
| 89 |
-
| 0.8585 | 19.0 | 456 | 0.
|
| 90 |
-
| 0.6627 | 20.0 | 480 | 0.
|
| 91 |
-
| 0.6497 | 21.0 | 504 | 0.
|
| 92 |
-
| 0.6422 | 22.0 | 528 | 0.
|
| 93 |
-
| 0.5964 | 23.0 | 552 | 0.
|
| 94 |
-
| 0.5793 | 24.0 | 576 | 0.
|
| 95 |
-
| 0.5909 | 25.0 | 600 | 0.
|
| 96 |
-
| 0.593 | 26.0 | 624 | 0.
|
| 97 |
-
| 0.5957 | 27.0 | 648 | 0.
|
| 98 |
-
| 0.5869 | 28.0 | 672 | 0.
|
| 99 |
-
| 0.4999 | 29.0 | 696 | 0.
|
| 100 |
-
| 0.4843 | 30.0 | 720 | 0.
|
| 101 |
-
| 0.5352 | 31.0 | 744 | 0.
|
| 102 |
-
| 0.4937 | 32.0 | 768 | 0.
|
| 103 |
-
| 0.483 | 33.0 | 792 | 0.
|
| 104 |
-
| 0.4265 | 34.0 | 816 | 0.
|
| 105 |
-
| 0.4412 | 35.0 | 840 | 0.
|
| 106 |
-
| 0.4324 | 36.0 | 864 | 0.
|
| 107 |
-
| 0.4681 | 37.0 | 888 | 0.
|
| 108 |
-
| 0.4813 | 38.0 | 912 | 0.
|
| 109 |
-
| 0.4585 | 39.0 | 936 | 0.
|
| 110 |
-
| 0.4151 | 40.0 | 960 | 0.
|
| 111 |
-
| 0.4351 | 41.0 | 984 | 0.
|
| 112 |
-
| 0.4364 | 42.0 | 1008 | 0.
|
| 113 |
-
| 0.4632 | 43.0 | 1032 | 0.
|
| 114 |
-
| 0.3867 | 44.0 | 1056 | 0.
|
| 115 |
-
| 0.4007 | 45.0 | 1080 | 0.
|
| 116 |
-
| 0.3848 | 46.0 | 1104 | 0.
|
| 117 |
-
| 0.4061 | 47.0 | 1128 | 0.
|
| 118 |
-
| 0.3901 | 48.0 | 1152 | 0.
|
| 119 |
-
| 0.3794 | 49.0 | 1176 | 0.
|
| 120 |
-
| 0.3583 | 50.0 | 1200 | 0.
|
| 121 |
|
| 122 |
|
| 123 |
### Framework versions
|
|
|
|
| 33 |
|
| 34 |
This model is a fine-tuned version of [microsoft/resnet-18](https://huggingface.co/microsoft/resnet-18) on the imagefolder dataset.
|
| 35 |
It achieves the following results on the evaluation set:
|
|
|
|
| 36 |
- Accuracy: 0.9162
|
| 37 |
+
- Loss: 0.2760
|
| 38 |
|
| 39 |
## Model description
|
| 40 |
|
|
|
|
| 66 |
|
| 67 |
### Training results
|
| 68 |
|
| 69 |
+
| Training Loss | Epoch | Step | Accuracy | Validation Loss |
|
| 70 |
+
|:-------------:|:-----:|:----:|:--------:|:---------------:|
|
| 71 |
+
| 3.7676 | 1.0 | 24 | 0.0459 | 3.6832 |
|
| 72 |
+
| 3.607 | 2.0 | 48 | 0.0919 | 3.4400 |
|
| 73 |
+
| 3.2234 | 3.0 | 72 | 0.1919 | 3.0452 |
|
| 74 |
+
| 2.8944 | 4.0 | 96 | 0.3324 | 2.5182 |
|
| 75 |
+
| 2.1637 | 5.0 | 120 | 0.4351 | 2.0193 |
|
| 76 |
+
| 1.9347 | 6.0 | 144 | 0.5595 | 1.6222 |
|
| 77 |
+
| 1.6851 | 7.0 | 168 | 0.6297 | 1.3065 |
|
| 78 |
+
| 1.369 | 8.0 | 192 | 0.6919 | 1.0945 |
|
| 79 |
+
| 1.2987 | 9.0 | 216 | 0.7270 | 0.9188 |
|
| 80 |
+
| 1.1044 | 10.0 | 240 | 0.7541 | 0.8216 |
|
| 81 |
+
| 1.044 | 11.0 | 264 | 0.8 | 0.7295 |
|
| 82 |
+
| 1.0134 | 12.0 | 288 | 0.8270 | 0.6655 |
|
| 83 |
+
| 0.9284 | 13.0 | 312 | 0.8189 | 0.6212 |
|
| 84 |
+
| 0.8603 | 14.0 | 336 | 0.8216 | 0.5687 |
|
| 85 |
+
| 0.7748 | 15.0 | 360 | 0.8649 | 0.5291 |
|
| 86 |
+
| 0.8133 | 16.0 | 384 | 0.8324 | 0.5337 |
|
| 87 |
+
| 0.8379 | 17.0 | 408 | 0.8486 | 0.4993 |
|
| 88 |
+
| 0.751 | 18.0 | 432 | 0.8514 | 0.4632 |
|
| 89 |
+
| 0.8585 | 19.0 | 456 | 0.8162 | 0.4908 |
|
| 90 |
+
| 0.6627 | 20.0 | 480 | 0.8622 | 0.4358 |
|
| 91 |
+
| 0.6497 | 21.0 | 504 | 0.8486 | 0.4240 |
|
| 92 |
+
| 0.6422 | 22.0 | 528 | 0.8486 | 0.4143 |
|
| 93 |
+
| 0.5964 | 23.0 | 552 | 0.8676 | 0.3912 |
|
| 94 |
+
| 0.5793 | 24.0 | 576 | 0.8568 | 0.4026 |
|
| 95 |
+
| 0.5909 | 25.0 | 600 | 0.8838 | 0.3531 |
|
| 96 |
+
| 0.593 | 26.0 | 624 | 0.8811 | 0.3661 |
|
| 97 |
+
| 0.5957 | 27.0 | 648 | 0.8892 | 0.3674 |
|
| 98 |
+
| 0.5869 | 28.0 | 672 | 0.8892 | 0.3710 |
|
| 99 |
+
| 0.4999 | 29.0 | 696 | 0.8919 | 0.3422 |
|
| 100 |
+
| 0.4843 | 30.0 | 720 | 0.8946 | 0.3178 |
|
| 101 |
+
| 0.5352 | 31.0 | 744 | 0.8865 | 0.3129 |
|
| 102 |
+
| 0.4937 | 32.0 | 768 | 0.8973 | 0.3399 |
|
| 103 |
+
| 0.483 | 33.0 | 792 | 0.8973 | 0.2855 |
|
| 104 |
+
| 0.4265 | 34.0 | 816 | 0.9 | 0.3316 |
|
| 105 |
+
| 0.4412 | 35.0 | 840 | 0.8865 | 0.3273 |
|
| 106 |
+
| 0.4324 | 36.0 | 864 | 0.8973 | 0.3167 |
|
| 107 |
+
| 0.4681 | 37.0 | 888 | 0.9270 | 0.2944 |
|
| 108 |
+
| 0.4813 | 38.0 | 912 | 0.9135 | 0.2943 |
|
| 109 |
+
| 0.4585 | 39.0 | 936 | 0.9027 | 0.3019 |
|
| 110 |
+
| 0.4151 | 40.0 | 960 | 0.8892 | 0.3399 |
|
| 111 |
+
| 0.4351 | 41.0 | 984 | 0.9081 | 0.2623 |
|
| 112 |
+
| 0.4364 | 42.0 | 1008 | 0.9135 | 0.2892 |
|
| 113 |
+
| 0.4632 | 43.0 | 1032 | 0.9081 | 0.3086 |
|
| 114 |
+
| 0.3867 | 44.0 | 1056 | 0.9 | 0.2913 |
|
| 115 |
+
| 0.4007 | 45.0 | 1080 | 0.9135 | 0.2502 |
|
| 116 |
+
| 0.3848 | 46.0 | 1104 | 0.9162 | 0.2702 |
|
| 117 |
+
| 0.4061 | 47.0 | 1128 | 0.9162 | 0.2634 |
|
| 118 |
+
| 0.3901 | 48.0 | 1152 | 0.9054 | 0.2975 |
|
| 119 |
+
| 0.3794 | 49.0 | 1176 | 0.8973 | 0.2590 |
|
| 120 |
+
| 0.3583 | 50.0 | 1200 | 0.9162 | 0.2760 |
|
| 121 |
|
| 122 |
|
| 123 |
### Framework versions
|
config.json
CHANGED
|
@@ -105,7 +105,6 @@
|
|
| 105 |
"out_indices": [
|
| 106 |
4
|
| 107 |
],
|
| 108 |
-
"problem_type": "single_label_classification",
|
| 109 |
"stage_names": [
|
| 110 |
"stem",
|
| 111 |
"stage1",
|
|
|
|
| 105 |
"out_indices": [
|
| 106 |
4
|
| 107 |
],
|
|
|
|
| 108 |
"stage_names": [
|
| 109 |
"stem",
|
| 110 |
"stage1",
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5777
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:439ea17f5ad2fa7dc71e7926cb3c0b1d631f394800cc9a0cea8829c3a3124bb0
|
| 3 |
size 5777
|