-
hi everyone,
I attempted to measure the metric depth performance on the KITTI datasets using the pretrained model provided in this project.
(δ1, δ2, δ3, AbsRel, RMS, log10)
but the result is fa…
-
Hi @zachteed @heilaw @anewell @jiadeng
I notice that you scale both the depth map and the translation in pose matrix with scaling ratio 0.1 when training the KITTI dataset.
However, in the data s…
-
There is also "instances" in nyu_depth_v2_labeled.mat, why you load labels but not instances mask in nyuv2/prepare_dataset.py or class NYU
-
(glp) ning@ubuntu:~/GLPDepth/datasets$ python ../code/utils/extract_official_train_test_set_from_mat.py nyu_depth_v2_labeled.mat splits.mat ./nyu_depth_v2/official_splits/
Traceback (most recent call…
-
I'm appreciating your great work.
when i test own depth data, I can't get the center coordinates and depth values of hand bbox advance. Therefore, when I try to remove "- center [index] [0] [2]" du…
-
(1)
(2) :
> File "test_nyu_metric.py", line 22, in
> merge_cfg_from_file(test_args)
> File "/home/Projects/consistent_depth/VNL_Mon…
-
I'm trying to train my own network following the tutorial in /training. The dataset is Matterport3D. I noticed an example json file about this dataset that includes "{"meta_data": "Matterport3D/data/S…