Update README.md
Browse files
README.md
CHANGED
|
@@ -11,26 +11,36 @@ tags:
|
|
| 11 |
- image-to-text
|
| 12 |
---
|
| 13 |
|
| 14 |
-
> **Finetune SigLIP2 Image Classification
|
| 15 |
|
| 16 |
This notebook demonstrates how to fine-tune SigLIP 2, a robust multilingual vision-language model, for single-label image classification tasks. The fine-tuning process incorporates advanced techniques such as captioning-based pretraining, self-distillation, and masked prediction, unified within a streamlined training pipeline. The workflow supports datasets in both structured and unstructured forms, making it adaptable to various domains and resource levels.
|
| 17 |
|
| 18 |
| Notebook Name | Description | Notebook Link |
|
| 19 |
|-------------------------------------|--------------------------------------------------|----------------|
|
| 20 |
-
| notebook-siglip2-finetune-type1 | Train/Test Splits | [Download](https://huggingface.co/prithivMLmods/FineTuning-SigLIP2-Notebook/blob/main/Finetune-SigLIP2-Image-Classification/1.SigLIP2_Finetune_ImageClassification_TrainTest_Splits.ipynb) |
|
| 21 |
-
| notebook-siglip2-finetune-type2 | Only Train Split | [Download](https://huggingface.co/prithivMLmods/FineTuning-SigLIP2-Notebook/blob/main/Finetune-SigLIP2-Image-Classification/2.SigLIP2_Finetune_ImageClassification_OnlyTrain_Splits.ipynb) |
|
| 22 |
|
| 23 |
The notebook outlines two data handling scenarios. In the first, datasets include predefined train and test splits, enabling conventional supervised learning and generalization evaluation. In the second scenario, only a training split is available; in such cases, the training set is either partially reserved for validation or reused entirely for evaluation. This flexibility supports experimentation in constrained or domain-specific settings, where standard test annotations may not exist.
|
| 24 |
|
| 25 |
-
|
| 26 |
```
|
| 27 |
last updated : jul 2025
|
| 28 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
|
| 30 |
| **Type 1: Train/Test Splits** | **Type 2: Only Train Split** |
|
| 31 |
|------------------------------|------------------------------|
|
| 32 |
|  |  |
|
| 33 |
|
|
|
|
| 34 |
---
|
| 35 |
|
| 36 |
| Platform | Link |
|
|
|
|
| 11 |
- image-to-text
|
| 12 |
---
|
| 13 |
|
| 14 |
+
> **Finetune SigLIP2 Image Classification📦**
|
| 15 |
|
| 16 |
This notebook demonstrates how to fine-tune SigLIP 2, a robust multilingual vision-language model, for single-label image classification tasks. The fine-tuning process incorporates advanced techniques such as captioning-based pretraining, self-distillation, and masked prediction, unified within a streamlined training pipeline. The workflow supports datasets in both structured and unstructured forms, making it adaptable to various domains and resource levels.
|
| 17 |
|
| 18 |
| Notebook Name | Description | Notebook Link |
|
| 19 |
|-------------------------------------|--------------------------------------------------|----------------|
|
| 20 |
+
| notebook-siglip2-finetune-type1 | Train/Test Splits | [⬇️Download](https://huggingface.co/prithivMLmods/FineTuning-SigLIP2-Notebook/blob/main/Finetune-SigLIP2-Image-Classification/1.SigLIP2_Finetune_ImageClassification_TrainTest_Splits.ipynb) |
|
| 21 |
+
| notebook-siglip2-finetune-type2 | Only Train Split | [⬇️Download](https://huggingface.co/prithivMLmods/FineTuning-SigLIP2-Notebook/blob/main/Finetune-SigLIP2-Image-Classification/2.SigLIP2_Finetune_ImageClassification_OnlyTrain_Splits.ipynb) |
|
| 22 |
|
| 23 |
The notebook outlines two data handling scenarios. In the first, datasets include predefined train and test splits, enabling conventional supervised learning and generalization evaluation. In the second scenario, only a training split is available; in such cases, the training set is either partially reserved for validation or reused entirely for evaluation. This flexibility supports experimentation in constrained or domain-specific settings, where standard test annotations may not exist.
|
| 24 |
|
|
|
|
| 25 |
```
|
| 26 |
last updated : jul 2025
|
| 27 |
```
|
| 28 |
+
---
|
| 29 |
+
|
| 30 |
+
<div style="
|
| 31 |
+
background: rgba(255, 193, 61, 0.15);
|
| 32 |
+
padding: 16px;
|
| 33 |
+
border-radius: 6px;
|
| 34 |
+
border: 1px solid rgba(255, 165, 0, 0.3);
|
| 35 |
+
margin: 16px 0;
|
| 36 |
+
">
|
| 37 |
+
|
| 38 |
|
| 39 |
| **Type 1: Train/Test Splits** | **Type 2: Only Train Split** |
|
| 40 |
|------------------------------|------------------------------|
|
| 41 |
|  |  |
|
| 42 |
|
| 43 |
+
</div>
|
| 44 |
---
|
| 45 |
|
| 46 |
| Platform | Link |
|