from turtle import title
import gradio as gr
from transformers import pipeline
import numpy as np
from PIL import Image


pipes = {
    "chinese-clip-vit-base-patch16": pipeline("zero-shot-image-classification", model="OFA-Sys/chinese-clip-vit-base-patch16"),
    "chinese-clip-vit-large-patch14": pipeline("zero-shot-image-classification", model="OFA-Sys/chinese-clip-vit-large-patch14"),
    "chinese-clip-vit-large-patch14-336px": pipeline("zero-shot-image-classification", model="OFA-Sys/chinese-clip-vit-large-patch14-336px"),
    "chinese-clip-vit-huge-patch14": pipeline("zero-shot-image-classification", model="OFA-Sys/chinese-clip-vit-huge-patch14"),
}
inputs = [
    gr.inputs.Image(type='pil'),
    "text",
    gr.inputs.Radio(choices=[
                                "chinese-clip-vit-base-patch16",
                                "chinese-clip-vit-large-patch14", 
                                "chinese-clip-vit-large-patch14-336px", 
                                "chinese-clip-vit-huge-patch14",
                            ], type="value", default="chinese-clip-vit-base-patch16", label="Model"), 
]
images="festival.jpg"

def shot(image, labels_text, model_name):
    labels = labels_text.strip(" ").split(",").strip(" ")
    res = pipes[model_name](images=image, 
           candidate_labels=labels,
           hypothesis_template= "一张{}的图片。")
    return {dic["label"]: dic["score"] for dic in res}

iface = gr.Interface(shot, 
                    inputs, 
                    "label", 
                    examples=[["festival.jpg", "灯笼, 鞭炮, 对联"], 
                              ["cat-dog-music.png", "音乐表演, 体育运动"],
                              ["football-match.jpg", "梅西, C罗, 马奎尔"]],
                    description="Add a picture and a list of labels separated by commas",
                    title="Zero-shot Image Classification")

iface.launch()