app.py

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

# Load model weights
model = torch.hub.load('ultralytics/yolov5', 'custom', "model_weights/datasets_1000_41class.pt",map_location=torch.device('cpu'))

# Define a yolo prediction function
def yolo(im, size=640):
    g = (size / max(im.size))  # gain
    im = im.resize((int(x * g) for x in im.size), Image.ANTIALIAS)  # resize

    results = model(im)  # inference
    results.render()  # updates results.imgs with boxes and labels
    return Image.fromarray(results.imgs[0])


inputs = gr.inputs.Image(type='pil', label="Original Image")
outputs = gr.outputs.Image(type="pil", label="Output Image")

title = "BandiCount: Detecting Australian native animal species"
description = "BandiCount: Detecting Australian native animal species in NSW national parks, using object detection. Upload an image or click an example image to use."
article = ""

examples = [['BrushtailPossum.jpg'], ['Eagle.jpg'], ['Macropod.jpg'], ['cat.jpg'], ['echidna.gif'], ['fox_in_snow.mp4'], ['godzilla_fantail.png'], ['ibis.jpg'], ['koala1.jpeg'], ['koala2.jpg'], ['lyrebird.mp4']]
gr.Interface(yolo, inputs, outputs, title=title, description=description, article=article, examples=examples, theme="huggingface").launch(cache_examples=True,enable_queue=True)