app.py

import torch
model = torch.hub.load('pytorch/vision:v0.9.0', 'deeplabv3_resnet101', pretrained=True)
model.eval()
# Download an example image from the pytorch website
import urllib
url, filename = ("https://github.com/pytorch/hub/raw/master/images/dog.jpg", "dog.jpg")
try: urllib.URLopener().retrieve(url, filename)
except: urllib.request.urlretrieve(url, filename)
# sample execution (requires torchvision)
from PIL import Image
from torchvision import transforms
import gradio as gr
import matplotlib.pyplot as plt


def inference(input_image):
    preprocess = transforms.Compose([
        transforms.ToTensor(),
        transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
    ])

    input_tensor = preprocess(input_image)
    input_batch = input_tensor.unsqueeze(0) # create a mini-batch as expected by the model

    # move the input and model to GPU for speed if available
    if torch.cuda.is_available():
        input_batch = input_batch.to('cuda')
        model.to('cuda')

    with torch.no_grad():
        output = model(input_batch)['out'][0]
    output_predictions = output.argmax(0)
    # create a color pallette, selecting a color for each class
    palette = torch.tensor([2 ** 25 - 1, 2 ** 15 - 1, 2 ** 21 - 1])
    colors = torch.as_tensor([i for i in range(21)])[:, None] * palette
    colors = (colors % 255).numpy().astype("uint8")

    # plot the semantic segmentation predictions of 21 classes in each color
    r = Image.fromarray(output_predictions.byte().cpu().numpy()).resize(input_image.size)
    r.putpalette(colors)
    plt.imshow(r)
    return plt

title = "DEEPLABV3-RESNET101"
description = "demo for DEEPLABV3-RESNET101, DeepLabV3 model with a ResNet-101 backbone. To use it, simply upload your image, or click one of the examples to load them. Read more at the links below."
article = "<p style='text-align: center'><a href='https://arxiv.org/abs/1706.05587'>Rethinking Atrous Convolution for Semantic Image Segmentation</a> | <a href='https://github.com/pytorch/vision/blob/master/torchvision/models/segmentation/deeplabv3.py'>Github Repo</a></p>"

gr.Interface(
    inference, 
    gr.inputs.Image(type="pil", label="Input"), 
    gr.outputs.Image(type="plot", label="Output"),
    title=title,
    description=description,
    article=article,
    examples=[
        ["dog.jpg"]
    ]).launch()