import cv2
import numpy as np
import onnxruntime
import torch
import io
import requests
from PIL import Image

def get_image(image):
    if isinstance(image, Image.Image):
        img = np.array(image)
    elif isinstance(image, np.ndarray):
        img = image.copy()
    else:
        raise Exception("Input image should be either PIL Image or numpy array!")

    if img.ndim == 3:
        img = np.transpose(img, (2, 0, 1))  # chw
    elif img.ndim == 2:
        img = img[np.newaxis, ...]

    assert img.ndim == 3

    img = img.astype(np.float32) / 255
    return img


def ceil_modulo(x, mod):
    if x % mod == 0:
        return x
    return (x // mod + 1) * mod


def scale_image(img, factor, interpolation=cv2.INTER_AREA):
    if img.shape[0] == 1:
        img = img[0]
    else:
        img = np.transpose(img, (1, 2, 0))

    img = cv2.resize(img, dsize=None, fx=factor, fy=factor, interpolation=interpolation)

    if img.ndim == 2:
        img = img[None, ...]
    else:
        img = np.transpose(img, (2, 0, 1))
    return img


def pad_img_to_modulo(img, mod):
    channels, height, width = img.shape
    out_height = ceil_modulo(height, mod)
    out_width = ceil_modulo(width, mod)
    return np.pad(
        img,
        ((0, 0), (0, out_height - height), (0, out_width - width)),
        mode="symmetric",
    )


def prepare_img_and_mask(image, mask, device, pad_out_to_modulo=8, scale_factor=None):
    out_image = get_image(image)
    out_mask = get_image(mask)

    if scale_factor is not None:
        out_image = scale_image(out_image, scale_factor)
        out_mask = scale_image(out_mask, scale_factor, interpolation=cv2.INTER_NEAREST)

    if pad_out_to_modulo is not None and pad_out_to_modulo > 1:
        out_image = pad_img_to_modulo(out_image, pad_out_to_modulo)
        out_mask = pad_img_to_modulo(out_mask, pad_out_to_modulo)

    out_image = torch.from_numpy(out_image).unsqueeze(0).to(device)
    out_mask = torch.from_numpy(out_mask).unsqueeze(0).to(device)

    out_mask = (out_mask > 0) * 1

    return out_image, out_mask


def open_image(image):
    if isinstance(image, str):
      if image.startswith("http://") or image.startswith("https://"):
        image = Image.open(io.BytesIO(requests.get(image).content))
      else:
        image = Image.open(image)
    return image



sess_options = onnxruntime.SessionOptions()
model = onnxruntime.InferenceSession('models/lama_manga.onnx', sess_options=sess_options)

image_url = "https://huggingface.co/Carve/LaMa-ONNX/resolve/main/image.jpg" # @param {type:"string"}
mask_url = "https://huggingface.co/Carve/LaMa-ONNX/resolve/main/mask.png" # @param {type:"string"}

image = open_image(image_url).resize((512, 512))
mask = open_image(mask_url).convert("L").resize((512, 512))

image, mask = prepare_img_and_mask(image, mask, 'cpu')
# Run the model
outputs = model.run(None,
                    {'image': image.numpy().astype(np.float32),
                     'mask': mask.numpy().astype(np.float32)})


output = outputs[0][0] * 256
# Postprocess the outputs
output = output.transpose(1, 2, 0)
output = output.astype(np.uint8)
output = Image.fromarray(output)
output.show()