app.py

import onnx
import numpy as np
import onnxruntime as ort
from PIL import Image
import cv2
import os
import gradio as gr

import mxnet
from mxnet.gluon.data.vision import transforms

os.system("wget https://s3.amazonaws.com/onnx-model-zoo/synset.txt")


with open('synset.txt', 'r') as f:
    labels = [l.rstrip() for l in f]
    
os.system("wget https://github.com/AK391/models/raw/main/vision/classification/shufflenet/model/shufflenet-9.onnx")

os.system("wget https://s3.amazonaws.com/model-server/inputs/kitten.jpg")



model_path = 'shufflenet-9.onnx'
model = onnx.load(model_path)
session = ort.InferenceSession(model.SerializeToString())

def get_image(path):
    with Image.open(path) as img:
        img = np.array(img.convert('RGB'))
    return img
    
    
def preprocess(img):
    '''
    Preprocessing required on the images for inference with mxnet gluon
    The function takes loaded image and returns processed tensor
    '''
    img = np.array(Image.fromarray(img).resize((224, 224))).astype(np.float32)
    img[:, :, 0] -= 123.68
    img[:, :, 1] -= 116.779
    img[:, :, 2] -= 103.939
    img[:,:,[0,1,2]] = img[:,:,[2,1,0]]
    img = img.transpose((2, 0, 1))
    img = np.expand_dims(img, axis=0)

    return img

def predict(path):
    img = get_image(path)
    img = preprocess(img)
    ort_inputs = {session.get_inputs()[0].name: img}
    preds = session.run(None, ort_inputs)[0]
    preds = np.squeeze(preds)
    a = np.argsort(preds)
    results = {}
    for i in a[0:5]:    
        results[labels[a[i]]] = float(preds[a[i]])
    return results
       

title="ShuffleNet-v1"
description="ShuffleNet is a deep convolutional network for image classification. ShuffleNetV2 is an improved architecture that is the state-of-the-art in terms of speed and accuracy tradeoff used for image classification."

examples=[['kitten.jpg']]
gr.Interface(predict,gr.inputs.Image(type='filepath'),"label",title=title,description=description,examples=examples).launch(enable_queue=True,debug=True)