Feature Extraction
timm
Safetensors
trendyol_arcface
computer-vision
image-feature-extraction
arcface
product-similarity
e-commerce
image-embeddings
convnext
Instructions to use Trendyol/e-commerce-product-image-encoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- timm
How to use Trendyol/e-commerce-product-image-encoder with timm:
import timm model = timm.create_model("hf-hub:Trendyol/e-commerce-product-image-encoder", pretrained=True) - Notebooks
- Google Colab
- Kaggle
Commit History
-
Update README.md
Verified signatureb9b7025
-
Update README.md
Verified signature45728f9 -
Update LICENSE
Verified signature01e62b2 -
Update README.md
Verified signatured9a8a90 -
feat: initial model release - TYArcFace ConvNeXt Product Embeddingsβ
Verified signatureπ― Model Details: - Architecture: ConvNeXt-Base + ArcFace loss - Embedding dimension: 512 - Training: PyTorch Lightning (epoch 5, 108 steps) - Task: Product similarity and unification π Repository Contents: - Model weights in safetensors format - Complete model card with usage examples - Apache 2.0 license - Demo notebook for inference - Full configuration and metadata π Security: Scanned for secrets/PII, ready for publication π RFC Compliance: Follows Trendyol ML model publication guidelines Signed-off-by: Trendyol Data Science Platform Team0dfad2f -
initial commit
Verified signature4f84e54