Image Classification
timm
Russian
English
manuscript
bookbinding
cultural-heritage
digital-humanities
convnext
fine-tuned
Instructions to use Infarondus/Klein-marchen_Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- timm
How to use Infarondus/Klein-marchen_Base with timm:
import timm model = timm.create_model("hf_hub:Infarondus/Klein-marchen_Base", pretrained=True) - Notebooks
- Google Colab
- Kaggle
Update README_convnext_binding.md
Browse files
README_convnext_binding.md
CHANGED
|
@@ -56,7 +56,7 @@ library_name: timm
|
|
| 56 |
|
| 57 |
**Базовая модель**: `convnext_tiny.fb_in22k` (ImageNet-22k pretrain, 28M параметров)
|
| 58 |
|
| 59 |
-
**Стратегия обучения**: обучение только классификационной головы при замороженном бэкбоне.
|
| 60 |
|
| 61 |
---
|
| 62 |
|
|
@@ -128,7 +128,7 @@ print(f"Не переплёт: {probs[0]:.1%} | Переплёт: {probs[1]:.1%}
|
|
| 128 |
@misc{kleine-marchen-binding,
|
| 129 |
author = {Infarondus},
|
| 130 |
title = {Kleine-Marchen — Binding Detector (ConvNeXt-Tiny)},
|
| 131 |
-
year = {
|
| 132 |
url = {https://github.com/Infarondus/Kleine-marchen}
|
| 133 |
}
|
| 134 |
```
|
|
|
|
| 56 |
|
| 57 |
**Базовая модель**: `convnext_tiny.fb_in22k` (ImageNet-22k pretrain, 28M параметров)
|
| 58 |
|
| 59 |
+
**Стратегия обучения**: обучение только классификационной головы при замороженном бэкбоне.
|
| 60 |
|
| 61 |
---
|
| 62 |
|
|
|
|
| 128 |
@misc{kleine-marchen-binding,
|
| 129 |
author = {Infarondus},
|
| 130 |
title = {Kleine-Marchen — Binding Detector (ConvNeXt-Tiny)},
|
| 131 |
+
year = {2026},
|
| 132 |
url = {https://github.com/Infarondus/Kleine-marchen}
|
| 133 |
}
|
| 134 |
```
|