Marqo-FashionSigLIP 模型卡片

from transformers import AutoModel, AutoProcessor
model = AutoModel.from_pretrained('Marqo/marqo-fashionSigLIP', trust_remote_code=True)
processor = AutoProcessor.from_pretrained('Marqo/marqo-fashionSigLIP', 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)
# [0.98379946, 0.01294010, 0.00326044]

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')

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)
# [0.9860219105287394, 0.00777916527489097, 0.006198924196369721]

npm i @huggingface/transformers

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

const model_id = 'Marqo/marqo-fashionSigLIP';

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

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await SiglipVisionModel.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);
// [0.9860219105287394, 0.00777916527489097, 0.006198924196369721]