83 lines
4.0 KiB
Python
83 lines
4.0 KiB
Python
|
import sys
|
||
|
|
sys.path.append('core')
|
||
|
|
|
||
|
|
import argparse
|
||
|
|
import glob
|
||
|
|
import numpy as np
|
||
|
|
import torch
|
||
|
|
from tqdm import tqdm
|
||
|
|
from pathlib import Path
|
||
|
|
from igev_stereo import IGEVStereo
|
||
|
|
from utils.utils import InputPadder
|
||
|
|
from PIL import Image
|
||
|
|
from matplotlib import pyplot as plt
|
||
|
|
import os
|
||
|
|
import skimage.io
|
||
|
|
import cv2
|
||
|
|
|
||
|
|
|
||
|
|
DEVICE = 'cuda'
|
||
|
|
|
||
|
|
os.environ['CUDA_VISIBLE_DEVICES'] = '0'
|
||
|
|
|
||
|
|
def load_image(imfile):
|
||
|
|
img = np.array(Image.open(imfile)).astype(np.uint8)
|
||
|
|
img = torch.from_numpy(img).permute(2, 0, 1).float()
|
||
|
|
return img[None].to(DEVICE)
|
||
|
|
|
||
|
|
def demo(args):
|
||
|
|
model = torch.nn.DataParallel(IGEVStereo(args), device_ids=[0])
|
||
|
|
model.load_state_dict(torch.load(args.restore_ckpt))
|
||
|
|
|
||
|
|
model = model.module
|
||
|
|
model.to(DEVICE)
|
||
|
|
model.eval()
|
||
|
|
|
||
|
|
output_directory = Path(args.output_directory)
|
||
|
|
output_directory.mkdir(exist_ok=True)
|
||
|
|
|
||
|
|
with torch.no_grad():
|
||
|
|
left_images = sorted(glob.glob(args.left_imgs, recursive=True))
|
||
|
|
right_images = sorted(glob.glob(args.right_imgs, recursive=True))
|
||
|
|
print(f"Found {len(left_images)} images. Saving files to {output_directory}/")
|
||
|
|
|
||
|
|
for (imfile1, imfile2) in tqdm(list(zip(left_images, right_images))):
|
||
|
|
image1 = load_image(imfile1)
|
||
|
|
image2 = load_image(imfile2)
|
||
|
|
padder = InputPadder(image1.shape, divis_by=32)
|
||
|
|
image1, image2 = padder.pad(image1, image2)
|
||
|
|
disp = model(image1, image2, iters=args.valid_iters, test_mode=True)
|
||
|
|
disp = padder.unpad(disp)
|
||
|
|
file_stem = os.path.join(output_directory, imfile1.split('/')[-1])
|
||
|
|
disp = disp.cpu().numpy().squeeze()
|
||
|
|
disp = np.round(disp * 256).astype(np.uint16)
|
||
|
|
skimage.io.imsave(file_stem, disp)
|
||
|
|
|
||
|
|
|
||
|
|
if __name__ == '__main__':
|
||
|
|
parser = argparse.ArgumentParser()
|
||
|
|
parser.add_argument('--restore_ckpt', help="restore checkpoint", default='./pretrained_models/kitti/kitti15.pth')
|
||
|
|
parser.add_argument('--save_numpy', action='store_true', help='save output as numpy arrays')
|
||
|
|
parser.add_argument('-l', '--left_imgs', help="path to all first (left) frames", default="/data/KITTI/KITTI_2015/testing/image_2/*_10.png")
|
||
|
|
parser.add_argument('-r', '--right_imgs', help="path to all second (right) frames", default="/data/KITTI/KITTI_2015/testing/image_3/*_10.png")
|
||
|
|
# parser.add_argument('-l', '--left_imgs', help="path to all first (left) frames", default="/data/KITTI/KITTI_2012/testing/colored_0/*_10.png")
|
||
|
|
# parser.add_argument('-r', '--right_imgs', help="path to all second (right) frames", default="/data/KITTI/KITTI_2012/testing/colored_1/*_10.png")
|
||
|
|
parser.add_argument('--output_directory', help="directory to save output", default="output")
|
||
|
|
parser.add_argument('--mixed_precision', action='store_true', help='use mixed precision')
|
||
|
|
parser.add_argument('--valid_iters', type=int, default=16, help='number of flow-field updates during forward pass')
|
||
|
|
|
||
|
|
# Architecture choices
|
||
|
|
parser.add_argument('--hidden_dims', nargs='+', type=int, default=[128]*3, help="hidden state and context dimensions")
|
||
|
|
parser.add_argument('--corr_implementation', choices=["reg", "alt", "reg_cuda", "alt_cuda"], default="reg", help="correlation volume implementation")
|
||
|
|
parser.add_argument('--shared_backbone', action='store_true', help="use a single backbone for the context and feature encoders")
|
||
|
|
parser.add_argument('--corr_levels', type=int, default=2, help="number of levels in the correlation pyramid")
|
||
|
|
parser.add_argument('--corr_radius', type=int, default=4, help="width of the correlation pyramid")
|
||
|
|
parser.add_argument('--n_downsample', type=int, default=2, help="resolution of the disparity field (1/2^K)")
|
||
|
|
parser.add_argument('--slow_fast_gru', action='store_true', help="iterate the low-res GRUs more frequently")
|
||
|
|
parser.add_argument('--n_gru_layers', type=int, default=3, help="number of hidden GRU levels")
|
||
|
|
parser.add_argument('--max_disp', type=int, default=192, help="max disp of geometry encoding volume")
|
||
|
|
|
||
|
|
args = parser.parse_args()
|
||
|
|
|
||
|
|
demo(args)
|