Spaces:
Runtime error
Runtime error
File size: 4,121 Bytes
65a3200 17e4368 5505967 65a3200 5505967 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 |
import gradio as gr
import cv2
import numpy as np
import os
from PIL import Image
import spaces
import torch
import torch.nn.functional as F
from torchvision.transforms import Compose
import tempfile
from gradio_imageslider import ImageSlider
from depth_anything.dpt import DepthAnything
from depth_anything.util.transform import Resize, NormalizeImage, PrepareForNet
css = """
#img-display-container {
max-height: 100vh;
}
#img-display-input {
max-height: 80vh;
}
#img-display-output {
max-height: 80vh;
}
"""
DEVICE = 'cuda' if torch.cuda.is_available() else 'cpu'
encoder = 'vitl' # can also be 'vitb' or 'vitl'
model = DepthAnything.from_pretrained(f"LiheYoung/depth_anything_{encoder}14").to(DEVICE).eval()
title = "# Depth Anything"
description = """Official demo for **Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data**.
Please refer to our [paper](https://arxiv.org/abs/2401.10891), [project page](https://depth-anything.github.io), or [github](https://github.com/LiheYoung/Depth-Anything) for more details."""
transform = Compose([
Resize(
width=518,
height=518,
resize_target=False,
keep_aspect_ratio=True,
ensure_multiple_of=14,
resize_method='lower_bound',
image_interpolation_method=cv2.INTER_CUBIC,
),
NormalizeImage(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
PrepareForNet(),
])
@spaces.GPU
@torch.no_grad()
def predict_depth(model, image):
return model(image)
with gr.Blocks(css=css) as demo:
gr.Markdown(title)
gr.Markdown(description)
gr.Markdown("### Depth Prediction demo")
gr.Markdown("You can slide the output to compare the depth prediction with input image")
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,)
raw_file = gr.File(label="Normalized 16-bit depth")
submit = gr.Button("Submit")
def on_submit(image):
original_image = image.copy()
h, w = image.shape[:2]
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB) / 255.0
image = transform({'image': image})['image']
image = torch.from_numpy(image).unsqueeze(0).to(DEVICE)
depth = predict_depth(model, image)
depth = F.interpolate(depth[None], (h, w), mode='bilinear', align_corners=False)[0, 0]
# disp1 = depth.cpu().numpy()
# range1 = np.minimum (disp1.max() / (disp1.min() + 0.001), 100.0) # clamping the farthest depth to 100x of the nearest
# max1 = disp1.max()
# min1 = max1 / range1
# depth1 = 1 / np.maximum (disp1, min1)
# depth1 = (depth1 - depth1.min()) / (depth1.max() - depth1.min()) * 65535.0
# raw_depth = Image.fromarray(depth1.astype('uint16'))
# tmp = tempfile.NamedTemporaryFile(suffix=f'_{min1:.3f}_{max1:.3f}_.png', delete=False)
# raw_depth.save(tmp.name)
depth1 = (depth - depth.min()) / (depth.max() - depth.min()) * 65535.0
raw_depth = Image.fromarray(depth1.cpu().numpy().astype('uint16'))
tmp = tempfile.NamedTemporaryFile(suffix=f'_{depth.min():.6f}_{depth.max():.6f}_.png', delete=False)
raw_depth.save(tmp.name)
depth2 = (depth - depth.min()) / (depth.max() - depth.min()) * 255.0
depth2 = depth2.cpu().numpy().astype(np.uint8)
colored_depth = cv2.applyColorMap(depth2, cv2.COLORMAP_INFERNO)[:, :, ::-1]
return [(original_image, colored_depth), tmp.name]
submit.click(on_submit, inputs=[input_image], outputs=[depth_image_slider, raw_file])
example_files = os.listdir('examples')
example_files.sort()
example_files = [os.path.join('examples', filename) for filename in example_files]
examples = gr.Examples(examples=example_files, inputs=[input_image], outputs=[depth_image_slider, raw_file], fn=on_submit, cache_examples=True)
if __name__ == '__main__':
demo.queue().launch()
|