app.py

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

from networks.models import *
from depth_anything_utils import Resize, NormalizeImage, PrepareForNet

css = """
#img-display-container {
    max-height: 100vh;
}
#img-display-input {
    max-height: 80vh;
}
#img-display-output {
    max-height: 80vh;
}
#download {
    height: 62px;
}
"""
DEVICE = 'cuda' if torch.cuda.is_available() else 'cpu'
config = 'panda_large.yaml'
with open(config, 'r') as f:
    config = yaml.load(f, Loader=yaml.FullLoader)
hf_weight = hf_hub_download(repo_id=f"ZidongC/PanDA", filename=f"panda_large.pth", repo_type="model")
state_dict = torch.load(hf_weight, map_location="cpu")
new_state_dict = {}
for key, value in state_dict.items():
    new_key = key[7:] if key.startswith('module.') else key
    new_state_dict[new_key] = value
model = make(config['model'])
# if any(key.startswith('module') for key in state_dict.keys()):
#     model = nn.DataParallel(model)
model_state_dict = model.state_dict()
model.load_state_dict({k: v for k, v in new_state_dict.items() if k in model_state_dict})
model = model.to(DEVICE).eval()

title = "# PanDA"
description = """Official demo for **PanDA**.
Please refer to our [github](https://github.com/caozidong/PanDA) for more details."""

@spaces.GPU
def predict_depth(image):
    return model.infer_image(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="Compute 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_r')

    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])


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