Hugging Face's logo

Marqo
/
marqo-fashionCLIP

Zero-Shot Image Classification
OpenCLIP
ONNX
Safetensors
Transformers.js
English
clip
e-commerce
fashion
multimodal retrieval
custom_code
Model card Files Community
2
marqo-fashionCLIP / README.md
DavidJung's picture
DavidJung
Update README.md
df7f643 verified
preview code
|
raw
history blame
No virus
3.88 kB
metadata
tags:
  - clip
  - e-commerce
  - fashion
  - multimodal retrieval
library_name: open_clip
pipeline_tag: zero-shot-image-classification
license: apache-2.0
language:
  - en
metrics:
  - precision
  - recall
  - MRR

Marqo-FashionCLIP Model Card

Marqo-FashionCLIP leverages Generalised Contrastive Learning (GCL) which allows the model to be trained on not just text descriptions but also categories, style, colors, materials, keywords and fine-details to provide highly relevant search results on fashion products. The model was fine-tuned from ViT-B-16 (laion2b_s34b_b88k).

Github Page: Marqo-FashionCLIP

Blog: Marqo Blog

Usage

The model can be seamlessly used with OpenCLIP by

import open_clip
model, preprocess_train, preprocess_val = open_clip.create_model_and_transforms('hf-hub:Marqo/marqo-fashionCLIP')
tokenizer = open_clip.get_tokenizer('hf-hub:Marqo/marqo-fashionCLIP')

import torch
from PIL import Image

image = preprocess_val(Image.open("docs/fashion-hippo.png")).unsqueeze(0)
text = tokenizer(["a hat", "a t-shirt", "shoes"])

with torch.no_grad(), torch.cuda.amp.autocast():
    image_features = model.encode_image(image)
    text_features = model.encode_text(text)
    image_features /= image_features.norm(dim=-1, keepdim=True)
    text_features /= text_features.norm(dim=-1, keepdim=True)

    text_probs = (100.0 * image_features @ text_features.T).softmax(dim=-1)

print("Label probs:", text_probs)

Benchmark Results

Average evaluation results on 6 public multimodal fashion datasets (Atlas, DeepFashion (In-shop), DeepFashion (Multimodal), Fashion200k, KAGL, and Polyvore) are reported below:

Text-To-Image (Averaged across 6 datasets)

Model AvgRecall Recall@1 Recall@10 MRR
Marqo-FashionCLIP 0.192 0.094 0.290 0.200
FashionCLIP2.0 0.163 0.077 0.249 0.165
OpenFashionCLIP 0.132 0.060 0.204 0.135
ViT-B-16-laion2b_s34b_b88k 0.174 0.088 0.261 0.180

Category-To-Product (Averaged across 5 datasets)

Model AvgP P@1 P@10 MRR
Marqo-FashionCLIP 0.705 0.734 0.676 0.776
FashionCLIP2.0 0.684 0.681 0.686 0.741
OpenFashionCLIP 0.646 0.653 0.639 0.720
ViT-B-16-laion2b_s34b_b88k 0.662 0.673 0.652 0.743

Sub-Category-To-Product (Averaged across 4 datasets)

Model AvgP P@1 P@10 MRR
Marqo-FashionCLIP 0.707 0.747 0.667 0.772
FashionCLIP2.0 0.657 0.676 0.638 0.733
OpenFashionCLIP 0.598 0.619 0.578 0.689
ViT-B-16-laion2b_s34b_b88k 0.638 0.651 0.624 0.712