app.py

import json
import gradio as gr
import os
from PIL import Image

clusters_12 = json.load(open("clusters/id_all_blip_clusters_12.json"))
clusters_24 = json.load(open("clusters/id_all_blip_clusters_24.json"))
clusters_48 = json.load(open("clusters/id_all_blip_clusters_48.json"))

clusters_by_size = {
    12: clusters_12,
    24: clusters_24,
    48: clusters_48,
}

def show_cluster(cl_id, num_clusters):
    cl_dct = clusters_by_size[num_clusters][cl_id]
    images = []
    for i in range(6):
        img_path = "/".join([st.replace("/", "") for st in cl_dct['img_path_list'][i].split("//")][3:])
        images.append((Image.open(os.path.join("identities-images", img_path)), "_".join([img_path.split("/")[0], img_path.split("/")[-1]])))
    return (len(cl_dct['img_path_list']),
           dict(cl_dct["labels_gender"]),
            dict(cl_dct["labels_model"]),
            dict(cl_dct["labels_ethnicity"]),
            images)

with gr.Blocks() as demo:
    gr.Markdown("# Cluster Explorer")
    gr.HTML("""<span style="color:red">⚠️ <b>DISCLAIMER: the images displayed by this tool were generated by text-to-image models and may depict offensive stereotypes or contain explicit content.</b></span>""")
    with gr.Row():
        num_clusters = gr.Radio([12, 24, 48], label="number of clusters")
        cluster_id = gr.Number(precision=0, label="cluster id")
        button = gr.Button(value="Go")
    with gr.Column():
        gallery = gr.Gallery(label="Most representative images in cluster").style(grid=6)
        a = gr.Text(label="Number of items in cluster")
        with gr.Row():
            c = gr.Text(label="Model makeup of cluster")
            b = gr.Text(label="Gender label makeup of cluster")
            d = gr.Text(label="Ethnicity label makeup of cluster")
    button.click(fn=show_cluster, inputs=[cluster_id, num_clusters], outputs=[a,b,c,d, gallery])
demo.launch(debug=True)