app.py

import torch
from transformers import pipeline

from PIL import Image

import matplotlib.pyplot as plt
import matplotlib.patches as patches
import gradio as gr
from random import choice
import io


model = pipeline(model="jaimin/ObjectDetect")



COLORS = ["#ff7f7f", "#ff7fbf", "#ff7fff", "#bf7fff",
            "#7f7fff", "#7fbfff", "#7fffff", "#7fffbf",
            "#7fff7f", "#bfff7f", "#ffff7f", "#ffbf7f"]

fdic = {
    "family" : "Impact",
    "style" : "italic",
    "size" : 15,
    "color" : "yellow",
    "weight" : "bold"
}


def get_figure(in_pil_img, in_results):
    plt.figure(figsize=(16, 10))
    plt.imshow(in_pil_img)
    #pyplot.gcf()
    ax = plt.gca()

    for prediction in in_results:
        selected_color = choice(COLORS)

        x, y = prediction['box']['xmin'], prediction['box']['ymin'],
        w, h = prediction['box']['xmax'] - prediction['box']['xmin'], prediction['box']['ymax'] - prediction['box']['ymin']

        ax.add_patch(plt.Rectangle((x, y), w, h, fill=False, color=selected_color, linewidth=3))
        ax.text(x, y, f"{prediction['label']}: {round(prediction['score']*100, 1)}%", fontdict=fdic)

    plt.axis("off")

    return plt.gcf()


def infer(model, in_pil_img):

    results = model(in_pil_img)

    figure = get_figure(in_pil_img, results)

    buf = io.BytesIO()
    figure.savefig(buf, bbox_inches='tight')
    buf.seek(0)
    output_pil_img = Image.open(buf)

    return output_pil_img


input = gr.inputs.Image(label="Upload your Image", type = 'pil', optional=True)
output = gr.outputs.Textbox(label="Captions")


interface = gr.Interface(
        fn=predict,
        inputs = input,
        outputs=output,
    )
interface.launch(debug=True)