import time from tensorboardX import SummaryWriter from datasets import __datasets__ from models import __models__ from utils import * from torch.utils.data import DataLoader import gc import skimage cudnn.benchmark = True parser = argparse.ArgumentParser(description='Cascade Stereo Network (CasStereoNet)') parser.add_argument('--model', default='gwcnet-c', help='select a model structure', choices=__models__.keys()) parser.add_argument('--maxdisp', type=int, default=192, help='maximum disparity') parser.add_argument('--test_dataset', required=True, help='dataset name', choices=__datasets__.keys()) parser.add_argument('--test_datapath', required=True, help='data path') parser.add_argument('--testlist', required=True, help='testing list') parser.add_argument('--test_batch_size', type=int, default=1, help='testing batch size') parser.add_argument('--logdir', required=True, help='the directory to save logs and checkpoints') parser.add_argument('--loadckpt', help='load the weights from a specific checkpoint') parser.add_argument("--local_rank", type=int, default=0) parser.add_argument('--ndisps', type=str, default="48,24", help='ndisps') parser.add_argument('--disp_inter_r', type=str, default="4,1", help='disp_intervals_ratio') parser.add_argument('--dlossw', type=str, default="0.5,2.0", help='depth loss weight for different stage') parser.add_argument('--cr_base_chs', type=str, default="32,32,16", help='cost regularization base channels') parser.add_argument('--grad_method', type=str, default="detach", choices=["detach", "undetach"], help='predicted disp detach, undetach')
from torch.utils.data import DataLoader import gc from PIL import Image cudnn.benchmark = True parser = argparse.ArgumentParser(description='seg') parser.add_argument('--mode', type=str, default='test', help='train or test') parser.add_argument('--model', default='seg', help='select a model structure', choices=__models__.keys()) parser.add_argument('--dataset', required=True, help='dataset name', choices=__datasets__.keys()) parser.add_argument('--datapath', default='', help='data path') parser.add_argument('--channels', type=int, default=3, help='net input channels') parser.add_argument('--out_channels', type=int, default=1, help='net output channels') parser.add_argument('--testlist', required=True, help='testing list') parser.add_argument('--test_batch_size', type=int, default=8, help='testing batch size') parser.add_argument('--test_crop_height',
from models import __models__ from utils import * from torch.utils.data import DataLoader import gc from skimage import io from matplotlib import pyplot as plt os.environ["CUDA_VISIBLE_DEVICES"] = "1" cudnn.benchmark = True parser = argparse.ArgumentParser(description='Group-wise Correlation Stereo Network (GwcNet)') parser.add_argument('--model', default='gwcnet-gc', help='select a model structure', choices=__models__.keys()) parser.add_argument('--maxdisp', type=int, default=192, help='maximum disparity') parser.add_argument('--dataset', default='kitti', help='dataset name', choices=__datasets__.keys()) parser.add_argument('--datapath', default='/media/data1/dh/DataSet/SceneFlowData/KITTI2015', help='data path') parser.add_argument('--testlist', default='./filenames/kitti15_test.txt', help='testing list') parser.add_argument('--loadckpt', default='./checkpoints/kitti15/bm_1/checkpoint_000799.ckpt', help='load the weights from a specific checkpoint') # parse arguments args = parser.parse_args() # dataset, dataloader StereoDataset = __datasets__[args.dataset] test_dataset = StereoDataset(args.datapath, args.testlist, False) TestImgLoader = DataLoader(test_dataset, 2, shuffle=False, num_workers=4, drop_last=False) # # model, optimizer model = __models__[args.model](args.maxdisp) model = nn.DataParallel(model)