Marqo Fashionclip

🚀 Marqo-FashionCLIP模型卡片

Marqo-FashionCLIP和Marqo-FashionSigLIP在性能上超越了以往最先進的時尚CLIP模型（具體結果見下文）。Marqo-FashionCLIP利用了廣義對比學習（GCL），這使得該模型不僅可以基於文本描述進行訓練，還能結合類別、風格、顏色、材質、關鍵詞和細節信息，從而為時尚產品搜索提供高度相關的結果。該模型是在ViT - B - 16（laion2b_s34b_b88k）的基礎上進行微調得到的。

Github頁面：Marqo-FashionCLIP

博客：Marqo博客

🚀 快速開始

本部分將介紹如何使用Marqo-FashionCLIP模型。

💻 使用示例

基礎用法

Hugging Face

可以使用AutoModel加載該模型：

from transformers import AutoModel, AutoProcessor
model = AutoModel.from_pretrained('Marqo/marqo-fashionCLIP', trust_remote_code=True)
processor = AutoProcessor.from_pretrained('Marqo/marqo-fashionCLIP', trust_remote_code=True)

import torch
from PIL import Image

image = [Image.open("docs/fashion-hippo.png")]
text = ["a hat", "a t-shirt", "shoes"]
processed = processor(text=text, images=image, padding='max_length', return_tensors="pt")

with torch.no_grad():
    image_features = model.get_image_features(processed['pixel_values'], normalize=True)
    text_features = model.get_text_features(processed['input_ids'], normalize=True)

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

print("Label probs:", text_probs)
# [0.99990773, 0.00006382, 0.00002847]

OpenCLIP

該模型可以與OpenCLIP無縫集成使用：

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, normalize=True)
    text_features = model.encode_text(text, normalize=True)

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

print("Label probs:", text_probs)
# [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

Transformers.js

你還可以使用Transformers.js庫在JavaScript中運行該模型。 首先，使用以下命令從NPM安裝：

npm i @huggingface/transformers

然後，按如下方式計算嵌入：

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

📚 詳細文檔

基準測試結果

以下是該模型在6個公開的多模態時尚數據集（Atlas、DeepFashion (In - shop)、DeepFashion (Multimodal)、Fashion200k、KAGL和Polyvore）上的平均評估結果：

文本到圖像（6個數據集的平均值）

類別到產品（5個數據集的平均值）

子類別到產品（4個數據集的平均值）

📄 許可證

本項目採用Apache - 2.0許可證。