OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Models

Marqo Fashionclip

Marqo Fashionclip is a public Python repository containing Marqo-FashionCLIP and Marqo-FashionSigLIP, fashion-domain image-and-text embedding models, along with code and configurations for evaluating them on public fashion benchmarks.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Marqo Fashionclip — OpenViST project profile in AI Models.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when a fashion-focused image-text model or a reproducible benchmark starting point is relevant to a retrieval, matching or classification task.

Who it is for

  • Developers building fashion product image-text retrieval or classification workflows.
  • Researchers comparing fashion embedding models across public datasets.
  • Teams assessing category-to-product and sub-category-to-product matching.

Documented uses

  • Retrieve fashion product images using text queries.
  • Match products to categories or subcategories.
  • Load model weights and create image and text features for comparisons.
  • Evaluate model performance across the repository's public fashion benchmark datasets.
Before you choose

Requirements & limits

The repository is public and identifies its license as Apache-2.0.

  • The README provides two model choices: Marqo-FashionCLIP and Marqo-FashionSigLIP.
  • Evaluation scripts cover seven named public datasets, while the task and metadata available vary by dataset.
  • The README documents loading through Transformers or OpenCLIP, local benchmark evaluation, and a separate Marqo deployment path.
  • Reported benchmark averages cover different dataset counts by task, so they should be interpreted in that context.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Run a model benchmark on a supported dataset

Evaluate Marqo-FashionCLIP or Marqo-FashionSigLIP with one of the repository's named dataset configurations.

Before you start

  • Python environment with PyTorch installed
  • Repository requirements installed with pip install -r requirements.txt
  • A dataset configuration among deepfashion_inshop, deepfashion_multimodal, fashion200k, KAGL, atlas, polyvore or iMaterialist

Steps

  1. Install PyTorch.

  2. Install the repository dependencies with the command below.

    Documented command
    pip install -r requirements.txt

  3. Run the command below, replacing ${DATASET} with a supported dataset name; use Marqo/marqo-fashionSigLIP and Marqo-FashionSigLIP for the other model.

    Documented command
    python eval.py --dataset-config ./configs/${DATASET}.json --model-name Marqo/marqo-fashionCLIP --run-name Marqo-FashionCLIP

  4. Run the command below to summarize local results.

    Documented command
    python summarize_results.py

Expected outcome

A local benchmark run and a script for summarizing model results.

Guide limitations

  • Dataset metadata and tasks differ by dataset; consult the repository's task configurations.
  • The README documents evaluation and result summarization, not a deployment or serving workflow.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
16 October 2026
Original website title
marqo-ai/marqo-FashionCLIP · Official homepage title · retained in its source language
How we review sourcesSuggest a correction