app.py

import requests
from PIL import Image
from io import BytesIO
from numpy import asarray
import gradio as gr
import numpy as np
from math import ceil
from huggingface_hub import from_pretrained_keras


def getRequest():
    r = requests.get(
        'https://api.nasa.gov/planetary/apod?api_key=0eyGPKWmJmE5Z0Ijx25oG56ydbTKWE2H75xuEefx')
    result = r.json()
    receive = requests.get(result['url'])
    img = Image.open(BytesIO(receive.content)).convert('RGB')
    return img


model = from_pretrained_keras("GIanlucaRub/autoencoder_model_d_0")


def double_res(input_image):
    input_height = input_image.shape[0]
    input_width = input_image.shape[1]
    height = ceil(input_height/128)
    width = ceil(input_width/128)
    expanded_input_image = np.zeros((128*height, 128*width, 3), dtype=np.uint8)
    np.copyto(expanded_input_image[0:input_height, 0:input_width], input_image)

    output_image = np.zeros((128*height*2, 128*width*2, 3), dtype=np.float32)

    for i in range(height):
        for j in range(width):
            temp_slice = expanded_input_image[i *
                                              128:(i+1)*128, j*128:(j+1)*128]/255
            upsampled_slice = model.predict(temp_slice[np.newaxis, ...])
            np.copyto(output_image[i*256:(i+1)*256, j *
                      256:(j+1)*256], upsampled_slice[0])
            if i != 0 and j != 0 and i != height-1 and j != width-1:
                # removing inner borders
                right_slice = expanded_input_image[i *
                                                   128:(i+1)*128, (j+1)*128-64:(j+1)*128+64]/255
                right_upsampled_slice = model.predict(
                    right_slice[np.newaxis, ...])
                resized_right_slice = right_upsampled_slice[0][64:192, 64:192]
                np.copyto(output_image[i*256+64:(i+1)*256-64,
                          (j+1)*256-64:(j+1)*256+64], resized_right_slice)

                left_slice = expanded_input_image[i *
                                                  128:(i+1)*128, j*128-64:(j)*128+64]/255
                left_upsampled_slice = model.predict(
                    left_slice[np.newaxis, ...])
                resized_left_slice = left_upsampled_slice[0][64:192, 64:192]
                np.copyto(output_image[i*256+64:(i+1)*256-64,
                          j*256-64:j*256+64], resized_left_slice)

                upper_slice = expanded_input_image[(
                    i+1)*128-64:(i+1)*128+64, j*128:(j+1)*128]/255
                upper_upsampled_slice = model.predict(
                    upper_slice[np.newaxis, ...])
                resized_upper_slice = upper_upsampled_slice[0][64:192, 64:192]
                np.copyto(output_image[(i+1)*256-64:(i+1)*256+64,
                          j*256+64:(j+1)*256-64], resized_upper_slice)

                lower_slice = expanded_input_image[i *
                                                   128-64:i*128+64, j*128:(j+1)*128]/255
                lower_upsampled_slice = model.predict(
                    lower_slice[np.newaxis, ...])
                resized_lower_slice = lower_upsampled_slice[0][64:192, 64:192]
                np.copyto(output_image[i*256-64:i*256+64,
                          j*256+64:(j+1)*256-64], resized_lower_slice)


# removing angles
                lower_right_slice = expanded_input_image[i *
                                                         128-64:i*128+64, (j+1)*128-64:(j+1)*128+64]/255
                lower_right_upsampled_slice = model.predict(
                    lower_right_slice[np.newaxis, ...])
                resized_lower_right_slice = lower_right_upsampled_slice[0][64:192, 64:192]
                np.copyto(output_image[i*256-64:i*256+64,  (j+1)
                          * 256-64:(j+1)*256+64], resized_lower_right_slice)

                lower_left_slice = expanded_input_image[i *
                                                        128-64:i*128+64, j*128-64:j*128+64]/255
                lower_left_upsampled_slice = model.predict(
                    lower_left_slice[np.newaxis, ...])
                resized_lower_left_slice = lower_left_upsampled_slice[0][64:192, 64:192]
                np.copyto(
                    output_image[i*256-64:i*256+64,  j*256-64:j*256+64], resized_lower_left_slice)

    resized_output_image = output_image[0:input_height*2, 0:input_width*2]
    return resized_output_image


with gr.Blocks() as demo:
    with gr.Row():
        with gr.Column():
            gr.Label("Original image")
            input_img = gr.Image(getRequest())
        with gr.Column():
            gr.Label("Image with resolution doubled")
            numpydata = asarray(getRequest())
            output = double_res(numpydata)  # numpy.ndarray
            input_img = gr.Image(output)
    with gr.Row().style(mobile_collapse=False, equal_height=True):
        btn_get = gr.Button("Get the new daily-image")
    # Event
    btn_get.click(demo.launch())
demo.launch()