Zero-Shot Image Classification
OpenCLIP
ONNX
Safetensors
Transformers
Transformers.js
English
siglip
clip
e-commerce
fashion
multimodal retrieval
custom_code
Instructions to use Marqo/marqo-fashionSigLIP with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- OpenCLIP
How to use Marqo/marqo-fashionSigLIP with OpenCLIP:
import open_clip model, preprocess_train, preprocess_val = open_clip.create_model_and_transforms('hf-hub:Marqo/marqo-fashionSigLIP') tokenizer = open_clip.get_tokenizer('hf-hub:Marqo/marqo-fashionSigLIP') - Transformers
How to use Marqo/marqo-fashionSigLIP with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-image-classification", model="Marqo/marqo-fashionSigLIP", trust_remote_code=True) pipe( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png", candidate_labels=["animals", "humans", "landscape"], )# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Marqo/marqo-fashionSigLIP", trust_remote_code=True, device_map="auto") - Transformers.js
How to use Marqo/marqo-fashionSigLIP with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('zero-shot-image-classification', 'Marqo/marqo-fashionSigLIP'); - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -51,6 +51,7 @@ Average evaluation results on 6 public multimodal fashion datasets ([Atlas](http
|
|
| 51 |
| OpenFashionCLIP | 0.132 | 0.060 | 0.204 | 0.135 |
|
| 52 |
| ViT-B-16-laion2b_s34b_b88k | 0.174 | 0.088 | 0.261 | 0.180 |
|
| 53 |
| ViT-B-16-SigLIP-webli | 0.212 | 0.111 | 0.314 | 0.214 |
|
|
|
|
| 54 |
**Category-To-Product (Averaged across 5 datasets)**
|
| 55 |
| Model | AvgP | P@1 | P@10 | MRR |
|
| 56 |
|----------------------------|-----------|-----------|-----------|-----------|
|
|
@@ -59,6 +60,7 @@ Average evaluation results on 6 public multimodal fashion datasets ([Atlas](http
|
|
| 59 |
| OpenFashionCLIP | 0.646 | 0.653 | 0.639 | 0.720 |
|
| 60 |
| ViT-B-16-laion2b_s34b_b88k | 0.662 | 0.673 | 0.652 | 0.743 |
|
| 61 |
| ViT-B-16-SigLIP-webli | 0.688 | 0.690 | 0.685 | 0.751 |
|
|
|
|
| 62 |
**Sub-Category-To-Product (Averaged across 4 datasets)**
|
| 63 |
| Model | AvgP | P@1 | P@10 | MRR |
|
| 64 |
|----------------------------|-----------|-----------|-----------|-----------|
|
|
|
|
| 51 |
| OpenFashionCLIP | 0.132 | 0.060 | 0.204 | 0.135 |
|
| 52 |
| ViT-B-16-laion2b_s34b_b88k | 0.174 | 0.088 | 0.261 | 0.180 |
|
| 53 |
| ViT-B-16-SigLIP-webli | 0.212 | 0.111 | 0.314 | 0.214 |
|
| 54 |
+
|
| 55 |
**Category-To-Product (Averaged across 5 datasets)**
|
| 56 |
| Model | AvgP | P@1 | P@10 | MRR |
|
| 57 |
|----------------------------|-----------|-----------|-----------|-----------|
|
|
|
|
| 60 |
| OpenFashionCLIP | 0.646 | 0.653 | 0.639 | 0.720 |
|
| 61 |
| ViT-B-16-laion2b_s34b_b88k | 0.662 | 0.673 | 0.652 | 0.743 |
|
| 62 |
| ViT-B-16-SigLIP-webli | 0.688 | 0.690 | 0.685 | 0.751 |
|
| 63 |
+
|
| 64 |
**Sub-Category-To-Product (Averaged across 4 datasets)**
|
| 65 |
| Model | AvgP | P@1 | P@10 | MRR |
|
| 66 |
|----------------------------|-----------|-----------|-----------|-----------|
|