image_prompt_test.py

import gradio as gr
from gradio_image_prompter import ImagePrompter
import torch
from PIL import Image
from transformers import AutoModel, AutoTokenizer
import XGBoost_utils
import numpy as np

def calculate_areas(prompts, brand_num, pictorial_num, text_num):
    points_all = prompts["points"]
    brand_surf = 0
    for i in range(brand_num):
        x1 = points_all[i][0]; y1 = points_all[i][1]
        x2 = points_all[i][3]; y2 = points_all[i][4]
        brand_surf += np.abs((x1-x2)*(y1-y2))

    pictorial_surf = 0
    for i in range(brand_num, brand_num+pictorial_num):
        x1 = points_all[i][0]; y1 = points_all[i][1]
        x2 = points_all[i][3]; y2 = points_all[i][4]
        pictorial_surf += np.abs((x1-x2)*(y1-y2))
    
    text_surf = 0
    for i in range(brand_num+pictorial_num, brand_num+pictorial_num+text_num):
        x1 = points_all[i][0]; y1 = points_all[i][1]
        x2 = points_all[i][3]; y2 = points_all[i][4]
        text_surf += np.abs((x1-x2)*(y1-y2))

    ad_size = 0
    x1 = points_all[-2][0]; y1 = points_all[-2][1]
    x2 = points_all[-2][3]; y2 = points_all[-2][4]
    ad_size += np.abs((x1-x2)*(y1-y2))

    whole_size = 0
    x1 = points_all[-1][0]; y1 = points_all[-1][1]
    x2 = points_all[-1][3]; y2 = points_all[-1][4]
    whole_size += np.abs((x1-x2)*(y1-y2))

    return (brand_surf, pictorial_surf/whole_size*100, text_surf/whole_size*100, ad_size/whole_size*100, prompts["points"])


demo = gr.Interface(
    # lambda prompts1, prompts2: (prompts1["image"], prompts1["points"]),
    fn=calculate_areas,
    inputs=[ImagePrompter(label="Draw bounding boxes"),
            gr.Number(label="Number of brand bounding boxes"),
            gr.Number(label="Number of pictorial bounding boxes"),
            gr.Number(label="Number of text bounding boxes")],
    outputs=[gr.Number(label="brand surf %"),
             gr.Number(label="pictorial surf %"),
             gr.Number(label="text surf %"),
             gr.Number(label="ad size %"),
             gr.Dataframe(label="Points")],
    theme=gr.themes.Soft()
)

# demo2 = gr.Interface(
#     lambda prompts: (prompts["image"], prompts["points"]),
#     ImagePrompter(show_label=False),
#     [gr.Image(show_label=False), gr.Dataframe(label="Points")],
# )

# app = gr.TabbedInterface(interface_list=[demo, demo2], 
#                          tab_names = ["Image inference", "Video inference"])

demo.launch()