app.py

import gradio as gr
import cv2
import matplotlib
import numpy as np
import os
from PIL import Image
import spaces
import torch
import tempfile
from gradio_imageslider import ImageSlider
from huggingface_hub import hf_hub_download

from ppd.utils.set_seed import set_seed
from ppd.models.ppd import PixelPerfectDepth

css = """
#img-display-container {
    max-height: 100vh;
}
#img-display-input {
    max-height: 80vh;
}
#img-display-output {
    max-height: 80vh;
}
#download {
    height: 62px;
}

#img-display-output .image-slider-image {
    object-fit: contain !important;
    width: 100% !important;
    height: 100% !important;
}
"""

DEVICE = 'cuda' if torch.cuda.is_available() else 'cpu'
model = PixelPerfectDepth(sampling_steps=4)
ckpt_path = hf_hub_download(
    repo_id="gangweix/Pixel-Perfect-Depth",
    filename="ppd.pth",
    repo_type="model"
)
state_dict = torch.load(ckpt_path, map_location="cpu")
model.load_state_dict(state_dict, strict=False)
model = model.to(DEVICE).eval()



title = "# Pixel-Perfect Depth"
description = """Official demo for **Pixel-Perfect Depth**.
Please refer to our [paper](), [project page](https://pixel-perfect-depth.github.io), and [github](https://github.com/gangweix/pixel-perfect-depth) for more details."""

@spaces.GPU
def predict_depth(image):
    return model.forward_test(image)

with gr.Blocks(css=css) as demo:
    gr.Markdown(title)
    gr.Markdown(description)
    gr.Markdown("### Depth Prediction demo")

    with gr.Row():
        input_image = gr.Image(label="Input Image", type='numpy', elem_id='img-display-input')
        depth_image_slider = ImageSlider(label="Depth Map with Slider View", elem_id='img-display-output', position=0.5)
    submit = gr.Button(value="Predict Depth")
    gray_depth_file = gr.File(label="Grayscale depth map", elem_id="download",)
    raw_file = gr.File(label="16-bit raw output (can be considered as disparity)", elem_id="download",)

    cmap = matplotlib.colormaps.get_cmap('Spectral')

    def on_submit(image):
        original_image = image.copy()

        h, w = image.shape[:2]

        depth = predict_depth(image[:, :, ::-1])

        raw_depth = Image.fromarray(depth.astype('uint16'))
        tmp_raw_depth = tempfile.NamedTemporaryFile(suffix='.png', delete=False)
        raw_depth.save(tmp_raw_depth.name)

        depth = (depth - depth.min()) / (depth.max() - depth.min()) * 255.0
        depth = depth.astype(np.uint8)
        colored_depth = (cmap(depth)[:, :, :3] * 255).astype(np.uint8)

        gray_depth = Image.fromarray(depth)
        tmp_gray_depth = tempfile.NamedTemporaryFile(suffix='.png', delete=False)
        gray_depth.save(tmp_gray_depth.name)

        return [(original_image, colored_depth), tmp_gray_depth.name, tmp_raw_depth.name]

    submit.click(on_submit, inputs=[input_image], outputs=[depth_image_slider, gray_depth_file, raw_file])

    example_files = os.listdir('assets/examples')
    example_files.sort()
    example_files = [os.path.join('assets/examples', filename) for filename in example_files]
    examples = gr.Examples(examples=example_files, inputs=[input_image], outputs=[depth_image_slider, gray_depth_file, raw_file], fn=on_submit)


if __name__ == '__main__':
    demo.queue().launch(share=True)