Update README.md

README.md

@@ -1,149 +1,164 @@
----
-library_name: transformers
-tags:
-- siglip
-- siglip2
-- vision
-- clip
-- image-embeddings
-- pet-recognition
-model_id: AvitoTech/SigLIP2-giant-for-animal-identification
-pipeline_tag: image-feature-extraction
----
-
-# SigLIP2-Giant Fine-tuned for Animal Identification
-
-Fine-tuned SigLIP2-Giant model for individual animal identification, specializing in distinguishing between unique cats and dogs. This model produces robust image embeddings optimized for pet recognition, re-identification, and verification tasks.
-
-
-## Model Details
-
-- **Base Model**: google/siglip2-giant-opt-patch16-384
-- **Input**: Images (384x384)
-- **Output**: Image embeddings (1152-dimensional)
-- **Task**: Individual animal identification and verification
-
-## Training Data
-
-The model was trained on a comprehensive dataset combining multiple sources:
-
-- **[PetFace Dataset](https://arxiv.org/abs/2407.13555)**: Large-scale animal face dataset with 257,484 unique individuals across 13 animal families
-- **[Dogs-World](https://www.kaggle.com/datasets/lextoumbourou/dogs-world)**: Kaggle dataset for dog breed and individual identification
-- **[LCW (Labeled Cats in the Wild)](https://www.kaggle.com/datasets/dseidli/lcwlabeled-cats-in-the-wild)**: Cat identification dataset
-- **Web-scraped Data**: Additional curated images from various sources
-
-**Total Dataset Statistics:**
-- **1,904,157** total photographs
-- **695,091** unique individual animals (cats and dogs)
-
-## Training Details
-
-**Training Configuration:**
-- **Batch Size**: 116 samples (58 unique identities × 2 photos each)
-- **Optimizer**: Adam with learning rate 1e-4
-- **Training Duration**: 10 epochs
-- **Transfer Learning**: Final 5 transformer blocks unfrozen, lower layers frozen to preserve pre-trained features
-
-**Loss Function:**
-The model is trained using a combined loss function consisting of:
-1. **Triplet Loss** (margin α=0.45): Encourages separation between different animal identities
-2. **Intra-Pair Variance Regularization** (ε=0.01): Promotes consistency across multiple photos of the same animal
-
-Combined as: L_total = 1.0 × L_triplet + 0.5 × L_var
-
-This approach creates compact feature clusters for each individual animal while maintaining large separation between different identities.
-
-## Performance Metrics
-
-The model has been benchmarked against various vision encoders on multiple pet recognition datasets:
-
-### [Cat Individual Images Dataset](https://www.kaggle.com/datasets/timost1234/cat-individuals)
-
-| Model | ROC AUC | EER | Top-1 | Top-5 | Top-10 |
-|-------|---------|-----|-------|-------|--------|
-| CLIP-ViT-Base | 0.9821 | 0.0604 | 0.8359 | 0.9579 | 0.9711 |
-| DINOv2-Small | 0.9904 | 0.0422 | 0.8547 | 0.9660 | 0.9764 |
-| SigLIP-Base | 0.9899 | 0.0390 | 0.8649 | 0.9757 | 0.9842 |
-| SigLIP2-Base | 0.9894 | 0.0388 | 0.8660 | 0.9772 | 0.9863 |
-| Zer0int CLIP-L | 0.9881 | 0.0509 | 0.8768 | 0.9767 | 0.9845 |
-| **SigLIP2-Giant** | **0.9940** | **0.0344** | **0.8899** | **0.9868** | **0.9921** |
-| SigLIP2-Giant + E5-Small-v2 + gating | 0.9929 | 0.0344 | 0.8952 | 0.9872 | 0.9932 |
-
-### [DogFaceNet Dataset](https://www.springerprofessional.de/en/a-deep-learning-approach-for-dog-face-verification-and-recogniti/17094782)
-
-| Model | ROC AUC | EER | Top-1 | Top-5 | Top-10 |
-|-------|---------|-----|-------|-------|--------|
-| CLIP-ViT-Base | 0.9739 | 0.0772 | 0.4350 | 0.6417 | 0.7204 |
-| DINOv2-Small | 0.9829 | 0.0571 | 0.5581 | 0.7540 | 0.8139 |
-| SigLIP-Base | 0.9792 | 0.0606 | 0.5848 | 0.7746 | 0.8319 |
-| SigLIP2-Base | 0.9776 | 0.0672 | 0.5925 | 0.7856 | 0.8422 |
-| Zer0int CLIP-L | 0.9814 | 0.0625 | 0.6289 | 0.8092 | 0.8597 |
-| **SigLIP2-Giant** | **0.9926** | **0.0326** | **0.7475** | **0.9009** | **0.9316** |
-| SigLIP2-Giant + E5-Small-v2 + gating | 0.9920 | 0.0314 | 0.7818 | 0.9233 | 0.9482 |
-
-### Combined Test Dataset (Overall Performance)
-
-| Model | ROC AUC | EER | Top-1 | Top-5 | Top-10 |
-|-------|---------|-----|-------|-------|--------|
-| CLIP-ViT-Base | 0.9752 | 0.0729 | 0.6511 | 0.8122 | 0.8555 |
-| DINOv2-Small | 0.9848 | 0.0546 | 0.7180 | 0.8678 | 0.9009 |
-| SigLIP-Base | 0.9811 | 0.0572 | 0.7359 | 0.8831 | 0.9140 |
-| SigLIP2-Base | 0.9793 | 0.0631 | 0.7400 | 0.8889 | 0.9197 |
-| Zer0int CLIP-L | 0.9842 | 0.0565 | 0.7626 | 0.8994 | 0.9267 |
-| **SigLIP2-Giant** | **0.9912** | **0.0378** | **0.8243** | **0.9471** | **0.9641** |
-| SigLIP2-Giant + E5-Small-v2 + gating | 0.9882 | 0.0422 | 0.8428 | 0.9576 | 0.9722 |
-
-**Metrics Explanation:**
-- **ROC AUC**: Area Under the Receiver Operating Characteristic Curve - measures the model's ability to distinguish between different individuals
-- **EER**: Equal Error Rate - the error rate where false acceptance and false rejection rates are equal
-- **Top-K**: Accuracy of correct identification within the top K predictions
-
-## Basic Usage
-
-### Installation
-
-```bash
-pip install transformers torch pillow
-```
-
-### Get Image Embedding
-
-```python
-import torch
-import torch.nn.functional as F
-from PIL import Image
-from transformers import SiglipModel, SiglipProcessor
-
-# Load model and processor
-processor = SiglipProcessor.from_pretrained("google/siglip2-giant-opt-patch16-384")
-model = SiglipModel.from_pretrained("AvitoTech/SigLIP2-giant-for-animal-identification")
-
-device = "cuda" if torch.cuda.is_available() else "cpu"
-model = model.to(device).eval()
-
-# Load and process image
-image = Image.open("your_image.jpg").convert("RGB")
-
-with torch.no_grad():
-    inputs = processor(images=[image], return_tensors="pt").to(device)
-    image_features = model.get_image_features(**inputs)
-    image_features = F.normalize(image_features, dim=1)
-
-print(f"Embedding shape: {image_features.shape}")  # torch.Size([1, 1152])
-```
-
-## Citation
-
-If you use this model in your research or applications, please cite our work:
-
-```
-BibTeX citation will be added upon paper publication.
-```
-
-## Use Cases
-
-- Individual pet identification and re-identification
-- Lost and found pet matching systems
-- Veterinary record management
-- Animal behavior monitoring
-- Wildlife conservation and tracking
+---
+library_name: transformers
+tags:
+- siglip
+- siglip2
+- vision
+- clip
+- image-embeddings
+- pet-recognition
+model_id: AvitoTech/SigLIP2-giant-for-animal-identification
+pipeline_tag: image-feature-extraction
+---
+
+# SigLIP2-Giant Fine-tuned for Animal Identification
+
+Fine-tuned SigLIP2-Giant model for individual animal identification, specializing in distinguishing between unique cats and dogs. This model produces robust image embeddings optimized for pet recognition, re-identification, and verification tasks.
+
+
+## Model Details
+
+- **Base Model**: google/siglip2-giant-opt-patch16-384
+- **Input**: Images (384x384)
+- **Output**: Image embeddings (1536-dimensional)
+- **Task**: Individual animal identification and verification
+
+## Training Data
+
+The model was trained on a comprehensive dataset combining multiple sources:
+
+- **[PetFace Dataset](https://arxiv.org/abs/2407.13555)**: Large-scale animal face dataset with 257,484 unique individuals across 13 animal families
+- **[Dogs-World](https://www.kaggle.com/datasets/lextoumbourou/dogs-world)**: Kaggle dataset for dog breed and individual identification
+- **[LCW (Labeled Cats in the Wild)](https://www.kaggle.com/datasets/dseidli/lcwlabeled-cats-in-the-wild)**: Cat identification dataset
+- **Web-scraped Data**: Additional curated images from various sources
+
+**Total Dataset Statistics:**
+- **1,904,157** total photographs
+- **695,091** unique individual animals (cats and dogs)
+
+## Training Details
+
+**Training Configuration:**
+- **Batch Size**: 116 samples (58 unique identities × 2 photos each)
+- **Optimizer**: Adam with learning rate 1e-4
+- **Training Duration**: 10 epochs
+- **Transfer Learning**: Final 5 transformer blocks unfrozen, lower layers frozen to preserve pre-trained features
+
+**Loss Function:**
+The model is trained using a combined loss function consisting of:
+1. **Triplet Loss** (margin α=0.45): Encourages separation between different animal identities
+2. **Intra-Pair Variance Regularization** (ε=0.01): Promotes consistency across multiple photos of the same animal
+
+Combined as: L_total = 1.0 × L_triplet + 0.5 × L_var
+
+This approach creates compact feature clusters for each individual animal while maintaining large separation between different identities.
+
+## Performance Metrics
+
+The model has been benchmarked against various vision encoders on multiple pet recognition datasets:
+
+### [Cat Individual Images Dataset](https://www.kaggle.com/datasets/timost1234/cat-individuals)
+
+| Model | ROC AUC | EER | Top-1 | Top-5 | Top-10 |
+|-------|---------|-----|-------|-------|--------|
+| CLIP-ViT-Base | 0.9821 | 0.0604 | 0.8359 | 0.9579 | 0.9711 |
+| DINOv2-Small | 0.9904 | 0.0422 | 0.8547 | 0.9660 | 0.9764 |
+| SigLIP-Base | 0.9899 | 0.0390 | 0.8649 | 0.9757 | 0.9842 |
+| SigLIP2-Base | 0.9894 | 0.0388 | 0.8660 | 0.9772 | 0.9863 |
+| Zer0int CLIP-L | 0.9881 | 0.0509 | 0.8768 | 0.9767 | 0.9845 |
+| **SigLIP2-Giant** | **0.9940** | **0.0344** | **0.8899** | **0.9868** | **0.9921** |
+| SigLIP2-Giant + E5-Small-v2 + gating | 0.9929 | 0.0344 | 0.8952 | 0.9872 | 0.9932 |
+
+### [DogFaceNet Dataset](https://www.springerprofessional.de/en/a-deep-learning-approach-for-dog-face-verification-and-recogniti/17094782)
+
+| Model | ROC AUC | EER | Top-1 | Top-5 | Top-10 |
+|-------|---------|-----|-------|-------|--------|
+| CLIP-ViT-Base | 0.9739 | 0.0772 | 0.4350 | 0.6417 | 0.7204 |
+| DINOv2-Small | 0.9829 | 0.0571 | 0.5581 | 0.7540 | 0.8139 |
+| SigLIP-Base | 0.9792 | 0.0606 | 0.5848 | 0.7746 | 0.8319 |
+| SigLIP2-Base | 0.9776 | 0.0672 | 0.5925 | 0.7856 | 0.8422 |
+| Zer0int CLIP-L | 0.9814 | 0.0625 | 0.6289 | 0.8092 | 0.8597 |
+| **SigLIP2-Giant** | **0.9926** | **0.0326** | **0.7475** | **0.9009** | **0.9316** |
+| SigLIP2-Giant + E5-Small-v2 + gating | 0.9920 | 0.0314 | 0.7818 | 0.9233 | 0.9482 |
+
+### Combined Test Dataset (Overall Performance)
+
+| Model | ROC AUC | EER | Top-1 | Top-5 | Top-10 |
+|-------|---------|-----|-------|-------|--------|
+| CLIP-ViT-Base | 0.9752 | 0.0729 | 0.6511 | 0.8122 | 0.8555 |
+| DINOv2-Small | 0.9848 | 0.0546 | 0.7180 | 0.8678 | 0.9009 |
+| SigLIP-Base | 0.9811 | 0.0572 | 0.7359 | 0.8831 | 0.9140 |
+| SigLIP2-Base | 0.9793 | 0.0631 | 0.7400 | 0.8889 | 0.9197 |
+| Zer0int CLIP-L | 0.9842 | 0.0565 | 0.7626 | 0.8994 | 0.9267 |
+| **SigLIP2-Giant** | **0.9912** | **0.0378** | **0.8243** | **0.9471** | **0.9641** |
+| SigLIP2-Giant + E5-Small-v2 + gating | 0.9882 | 0.0422 | 0.8428 | 0.9576 | 0.9722 |
+
+**Metrics Explanation:**
+- **ROC AUC**: Area Under the Receiver Operating Characteristic Curve - measures the model's ability to distinguish between different individuals
+- **EER**: Equal Error Rate - the error rate where false acceptance and false rejection rates are equal
+- **Top-K**: Accuracy of correct identification within the top K predictions
+
+## Basic Usage
+
+### Installation
+
+```bash
+pip install transformers torch pillow
+```
+
+### Get Image Embedding
+
+```python
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+from PIL import Image
+from transformers import SiglipModel, SiglipProcessor
+from safetensors.torch import load_file
+from huggingface_hub import hf_hub_download
+
+class Model(nn.Module):
+    def __init__(self):
+        super().__init__()
+        ckpt = "google/siglip2-giant-opt-patch16-384"
+        self.clip = SiglipModel.from_pretrained(ckpt)
+        self.processor = SiglipProcessor.from_pretrained(ckpt)
+
+        
+    def forward(self, images):
+        clip_inputs = self.processor(images=images, return_tensors="pt").to(self.clip.device)
+        return self.clip.get_image_features(**clip_inputs)
+
+model = Model()
+
+weights_path = hf_hub_download(repo_id="AvitoTech/SigLIP2-giant", filename="model.safetensors")
+state_dict = load_file(weights_path)
+model.load_state_dict(state_dict)
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+model = model.to(device).eval()
+
+image = Image.open("your_image.jpg").convert("RGB")
+
+with torch.no_grad():
+    embedding = model([image])
+    embedding = F.normalize(embedding, dim=1)
+
+print(f"Embedding shape: {embedding.shape}")  # torch.Size([1, 1536])
+```
+
+## Citation
+
+If you use this model in your research or applications, please cite our work:
+
+```
+BibTeX citation will be added upon paper publication.
+```
+
+## Use Cases
+
+- Individual pet identification and re-identification
+- Lost and found pet matching systems
+- Veterinary record management
+- Animal behavior monitoring
+- Wildlife conservation and tracking