SciScore

SciScore is finetuned on the base model CLIP-H using Science-T2I dataset. It takes an implicit prompt and a generated image as input and outputs a score that represents the scientific alignment between them.

Resources

• Website
• arXiv: Paper
• GitHub: Code
• Huggingface: Science-T2I-S&C Benchmark
• Huggingface: Science-T2I Trainset

Feature

Qick Start

from transformers import AutoProcessor, AutoModel
from PIL import Image
import torch

device = "cuda"
processor_name_or_path = "Jialuo21/SciScore"
model_pretrained_name_or_path = "Jialuo21/SciScore"

processor = AutoProcessor.from_pretrained(processor_name_or_path)
model = AutoModel.from_pretrained(model_pretrained_name_or_path).eval().to(device)

def calc_probs(prompt, images):
    
    image_inputs = processor(
        images=images,
        padding=True,
        truncation=True,
        max_length=77,
        return_tensors="pt",
    ).to(device)
    
    text_inputs = processor(
        text=prompt,
        padding=True,
        truncation=True,
        max_length=77,
        return_tensors="pt",
    ).to(device)

    with torch.no_grad():
        image_embs = model.get_image_features(**image_inputs)
        image_embs = image_embs / torch.norm(image_embs, dim=-1, keepdim=True)
    
        text_embs = model.get_text_features(**text_inputs)
        text_embs = text_embs / torch.norm(text_embs, dim=-1, keepdim=True)
    
        scores = model.logit_scale.exp() * (text_embs @ image_embs.T)[0]
        probs = torch.softmax(scores, dim=-1)
    return probs.cpu().tolist()

pil_images = [Image.open("./examples/camera_1.png"), Image.open("./examples/camera_2.png")]
prompt = "A camera screen without electricity sits beside the window, realistic."
print(calc_probs(prompt, pil_images))