Spaces:
Runtime error
Runtime error
File size: 3,665 Bytes
6bb1ad5 |
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 |
import argparse
import cv2
import numpy as np
import os
import torch
import torch.nn.functional as F
from torchvision.transforms import Compose
from depth_anything.dpt import DepthAnything
from depth_anything.util.transform import Resize, NormalizeImage, PrepareForNet
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('--video-path', type=str)
parser.add_argument('--outdir', type=str, default='./vis_video_depth')
parser.add_argument('--encoder', type=str, default='vitl', choices=['vits', 'vitb', 'vitl'])
args = parser.parse_args()
margin_width = 50
DEVICE = 'cuda' if torch.cuda.is_available() else 'cpu'
depth_anything = DepthAnything.from_pretrained('LiheYoung/depth_anything_{}14'.format(args.encoder)).to(DEVICE).eval()
total_params = sum(param.numel() for param in depth_anything.parameters())
print('Total parameters: {:.2f}M'.format(total_params / 1e6))
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(),
])
if os.path.isfile(args.video_path):
if args.video_path.endswith('txt'):
with open(args.video_path, 'r') as f:
lines = f.read().splitlines()
else:
filenames = [args.video_path]
else:
filenames = os.listdir(args.video_path)
filenames = [os.path.join(args.video_path, filename) for filename in filenames if not filename.startswith('.')]
filenames.sort()
os.makedirs(args.outdir, exist_ok=True)
for k, filename in enumerate(filenames):
print('Progress {:}/{:},'.format(k+1, len(filenames)), 'Processing', filename)
raw_video = cv2.VideoCapture(filename)
frame_width, frame_height = int(raw_video.get(cv2.CAP_PROP_FRAME_WIDTH)), int(raw_video.get(cv2.CAP_PROP_FRAME_HEIGHT))
frame_rate = int(raw_video.get(cv2.CAP_PROP_FPS))
output_width = frame_width * 2 + margin_width
filename = os.path.basename(filename)
output_path = os.path.join(args.outdir, filename[:filename.rfind('.')] + '_video_depth.mp4')
out = cv2.VideoWriter(output_path, cv2.VideoWriter_fourcc(*"mp4v"), frame_rate, (output_width, frame_height))
while raw_video.isOpened():
ret, raw_frame = raw_video.read()
if not ret:
break
frame = cv2.cvtColor(raw_frame, cv2.COLOR_BGR2RGB) / 255.0
frame = transform({'image': frame})['image']
frame = torch.from_numpy(frame).unsqueeze(0).to(DEVICE)
with torch.no_grad():
depth = depth_anything(frame)
depth = F.interpolate(depth[None], (frame_height, frame_width), mode='bilinear', align_corners=False)[0, 0]
depth = (depth - depth.min()) / (depth.max() - depth.min()) * 255.0
depth = depth.cpu().numpy().astype(np.uint8)
depth_color = cv2.applyColorMap(depth, cv2.COLORMAP_INFERNO)
split_region = np.ones((frame_height, margin_width, 3), dtype=np.uint8) * 255
combined_frame = cv2.hconcat([raw_frame, split_region, depth_color])
out.write(combined_frame)
raw_video.release()
out.release()
|