go125 / depth_from_video_in_the_wild

Status output is added. This code is integrated to struct2depth_eval.
8 stars 0 forks source link

Depth from Video in the Wild: Unsupervised Monocular Depth Learning from Unknown Cameras

Original

This code is modified to apply for my own video.

This code is integrated to this code.

Train example

nohup python -m depth_from_video_in_the_wild.train \
--data_dir /home/ubuntu/data/kitti_result_all_20200715 \
--checkpoint_dir=/home/ubuntu/data/kitti_experiment_checkpoint_20200716 \
--imagenet_ckpt=/home/ubuntu/data/ResNet18/model.ckpt \
--train_steps=1000000 &

Finetuning with the video taken in Saitama

nohup python -m depth_from_video_in_the_wild.train \
--data_dir /home/ubuntu/Sayama/out \
--checkpoint_dir=/home/ubuntu/data/kitti_experiment_checkpoint_20200716 \
--imagenet_ckpt=/home/ubuntu/data/ResNet18/model.ckpt \
--train_steps=1000000 &