search

fangchangma / self-supervised-depth-completion

ICRA 2019 "Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and Monocular Camera"
MIT License
628 stars 134 forks source link

Depth from image #14

Open jadhu22 opened 5 years ago

jadhu22 commented 5 years ago

How is depth image generated from .png files for velodyne scans?

wuheng199112068 commented 5 years ago

An error occurred when entering such a parameter on the command line，what can we input about [checkpoint -path]？Can you give us an example?

Namespace(batch_size=1, criterion='l2', epochs=11, evaluate='[checkpoint-path]', i nput='gd', jitter=0.1, layers=34, lr=1e-05, pretrained=False, print_freq=10, rank_metric='rmse', result='..\results', resume='', start_epoch=0, train_mode='dense', use_d=True, use_g=True, use_pose=False, use_rgb=False, val='select', w1=0, w2=0, weight_decay=0, workers=4) => no model found at '[checkpoint-path]'

Rajat-Mehta commented 4 years ago

@jadhu22 did you figure that out? How to generate depth images from given rgb and velodyne scans?