app.py

import gradio as gr
import numpy as np
from PIL import Image

import tensorflow as tf
from hugsvision.inference.TorchVisionClassifierInference import TorchVisionClassifierInference

models_name = [
    "VGG16",
    "mobilenet_v2",
    "DenseNet"
]

# open categories.txt in read mode
categories = open("categories.txt", "r")
labels = categories.readline().split(";")

# create a radio
radio = gr.inputs.Radio(models_name, default="DenseNet", type="value")

def predict_image(image, model_name):


    print("======================")
    print(type(image))
    print(type(model_name))
    print("==========")
    print(image)
    print(model_name)
    print("======================")

    if model_name == "DenseNet":
        image = np.array(image) / 255
        image = np.expand_dims(image, axis=0)

        model = "./models/" + model_name + "model.h5"
        pred = model.predict(image)

        pred = dict((labels[i], "%.2f" % pred[0][i]) for i in range(len(labels)))
    else:
        
        image = Image.fromarray(np.uint8(image)).convert('RGB')
        classifier = TorchVisionClassifierInference(
            model_path = "./models/" + model_name
        )

        pred = classifier.predict_image(img=image, return_str=False)

        for key in pred.keys():
            pred[key] = pred[key]/100
    

    print(pred)
    return pred

image = gr.inputs.Image(shape=(300, 300), label="Upload Your Image Here")
label = gr.outputs.Label(num_top_classes=len(labels))

samples = ['samples/basking.jpg', 'samples/blacktip.jpg', 'samples/blue.jpg', 'samples/bull.jpg', 'samples/hammerhead.jpg',
        'samples/lemon.jpg', 'samples/mako.jpg', 'samples/nurse.jpg', 'samples/sand tiger.jpg', 'samples/thresher.jpg', 
        'samples/tigre.jpg', 'samples/whale.jpg', 'samples/white.jpg', 'samples/whitetip.jpg']
        
interface = gr.Interface(
    fn=predict_image, 
    inputs=image, 
    outputs=label, 
    capture_session=True, 
    allow_flagging=False, 
    examples=samples
)
interface.launch()