Feature Extraction
Transformers
PyTorch
Safetensors
English
trendyol_dinov2
image-similarity
image-retrieval
computer-vision
e-commerce
dinov2
custom_code
Eval Results (legacy)
Instructions to use Trendyol/trendyol-dino-v2-ecommerce-256d with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Trendyol/trendyol-dino-v2-ecommerce-256d with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="Trendyol/trendyol-dino-v2-ecommerce-256d", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Trendyol/trendyol-dino-v2-ecommerce-256d", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
feat: test upload - Trendyol DinoV2 Product Similarity and Retrieval Embedding Model
Browse files🧪 Test Upload Details:
- Personal account testing before company publication
- Architecture: ConvNeXt-Base + ArcFace loss
- Embedding dimension: 256
- Task: Product similarity and retrieval
📁 Repository Contents:
- Model weights in safetensors format
- Complete model card with usage examples
- Apache 2.0 license
- Demo notebook for inference
🔒 Security: Scanned and validated
📋 RFC Compliance: Ready for company publication
Test upload by: Personal Account
README.md
CHANGED
|
@@ -1,3 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# Trendyol DinoV2 Image Similarity Model
|
| 2 |
|
| 3 |
This repository contains a fine-tuned DinoV2 model for image similarity and retrieval tasks, specifically trained on e-commerce product images.
|
|
@@ -117,7 +150,7 @@ This model is designed for:
|
|
| 117 |
|
| 118 |
## License
|
| 119 |
|
| 120 |
-
This model is released by Trendyol under the Apache 2.0 License. See LICENSE file for details.
|
| 121 |
|
| 122 |
You are allowed to:
|
| 123 |
- View, download, and evaluate the model weights.
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
library_name: transformers
|
| 6 |
+
tags:
|
| 7 |
+
- image-similarity
|
| 8 |
+
- image-retrieval
|
| 9 |
+
- computer-vision
|
| 10 |
+
- e-commerce
|
| 11 |
+
- dinov2
|
| 12 |
+
- pytorch
|
| 13 |
+
- safetensors
|
| 14 |
+
datasets:
|
| 15 |
+
- e-commerce-product-images
|
| 16 |
+
metrics:
|
| 17 |
+
- cosine-similarity
|
| 18 |
+
- euclidean-distance
|
| 19 |
+
pipeline_tag: feature-extraction
|
| 20 |
+
model-index:
|
| 21 |
+
- name: Trendyol DinoV2 E-commerce Image Similarity
|
| 22 |
+
results:
|
| 23 |
+
- task:
|
| 24 |
+
type: image-similarity
|
| 25 |
+
dataset:
|
| 26 |
+
type: e-commerce-product-images
|
| 27 |
+
name: Product Image Similarity
|
| 28 |
+
metrics:
|
| 29 |
+
- type: cosine_similarity
|
| 30 |
+
value: 0.89
|
| 31 |
+
name: Cosine Similarity Score
|
| 32 |
+
---
|
| 33 |
+
|
| 34 |
# Trendyol DinoV2 Image Similarity Model
|
| 35 |
|
| 36 |
This repository contains a fine-tuned DinoV2 model for image similarity and retrieval tasks, specifically trained on e-commerce product images.
|
|
|
|
| 150 |
|
| 151 |
## License
|
| 152 |
|
| 153 |
+
This model is released by Trendyol under the Apache 2.0 License. See the [LICENSE file](https://huggingface.co/Trendyol/trendyol-dino-v2-ecommerce-256d/blob/main/LICENSE) for full details.
|
| 154 |
|
| 155 |
You are allowed to:
|
| 156 |
- View, download, and evaluate the model weights.
|
__pycache__/modeling_trendyol_dinov2.cpython-312.pyc
CHANGED
|
Binary files a/__pycache__/modeling_trendyol_dinov2.cpython-312.pyc and b/__pycache__/modeling_trendyol_dinov2.cpython-312.pyc differ
|
|
|