from doctest import Example
import gradio as gr
from transformers import DPTImageProcessor, DPTForDepthEstimation
import torch
import numpy as np
from PIL import Image, ImageOps
from pathlib import Path
import glob
from autostereogram.converter import StereogramConverter
from datetime import datetime
import time
import tempfile

feature_extractor = DPTImageProcessor.from_pretrained("Intel/dpt-large")
model = DPTForDepthEstimation.from_pretrained("Intel/dpt-large")

stereo_converter = StereogramConverter()


def process_image(image_path):
    print("\n\n\n")
    print("Processing image:", image_path)
    last_time = time.time()
    image_raw = Image.open(Path(image_path))

    image = image_raw.resize(
        (1280, int(1280 * image_raw.size[1] / image_raw.size[0])),
        Image.Resampling.LANCZOS,
    )

    # prepare image for the model
    encoding = feature_extractor(image, return_tensors="pt")

    # forward pass
    with torch.no_grad():
        outputs = model(**encoding)
        predicted_depth = outputs.predicted_depth

    # interpolate to original size
    prediction = torch.nn.functional.interpolate(
        predicted_depth.unsqueeze(1),
        size=image.size[::-1],
        mode="bicubic",
        align_corners=False,
    ).squeeze()
    output = prediction.cpu().numpy()
    depth_image = (output * 255 / np.max(output)).astype("uint8")
    depth_image_padded = np.array(
        ImageOps.pad(Image.fromarray(depth_image), (1280, 720))
    )

    stereo_image = stereo_converter.convert_depth_to_stereogram_with_thread_pool(
        depth_image_padded, False
    ).astype(np.uint8)

    stereo_image_pil = Image.fromarray(stereo_image).convert("RGB")
    with tempfile.NamedTemporaryFile(suffix=".jpg", delete=False) as f:
        image_name = f.name
        stereo_image_pil.save(image_name)

    return [depth_image_padded, stereo_image, image_name]


examples_images = [[f] for f in sorted(glob.glob("examples/*.jpg"))]


with gr.Blocks() as blocks:
    gr.Markdown(
        """
## Depth Image to Autostereogram (Magic Eye)
This demo is a variation from the original [DPT Demo](https://huggingface.co/spaces/nielsr/dpt-depth-estimation).
Zero-shot depth estimation from an image, then it uses [pystereogram](https://github.com/yxiao1996/pystereogram)
to generate the autostereogram (Magic Eye)
<base target="_blank">

"""
    )
    with gr.Row():
        with gr.Column():
            input_image = gr.Image(type="filepath", label="Input Image")
            button = gr.Button("Predict")
        with gr.Column():
            predicted_depth = gr.Image(label="Predicted Depth", type="pil")
    with gr.Row():
        autostereogram = gr.Image(label="Autostereogram", type="pil")
    with gr.Row():
        with gr.Column():
            file_download = gr.File(label="Download Image")
    with gr.Row():
        gr.Examples(
            examples=examples_images,
            fn=process_image,
            inputs=[input_image],
            outputs=[predicted_depth, autostereogram, file_download],
            cache_examples=True,
        )
    button.click(
        fn=process_image,
        inputs=[input_image],
        outputs=[predicted_depth, autostereogram, file_download],
    )
blocks.launch(debug=True)