You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -8,7 +8,7 @@ This repository contains official code for [Universal Few-shot Learning of Dense
8
8
9
9
## Setup
10
10
1. Download Taskonomy Dataset (tiny split) from the official github page https://github.com/StanfordVL/taskonomy/tree/master/data.
11
-
* You may download data of `depth_euclidean`, `depth_zbuffer`, `keypoints2d`, `keypoints3d`, `normal`, `principal_curvature`, `reshading`, `segment_semantic`, and `rgb`.
11
+
* You may download data of `depth_euclidean`, `depth_zbuffer`, `edge_occlusion`, `keypoints2d`, `keypoints3d`, `normal`, `principal_curvature`, `reshading`, `segment_semantic`, and `rgb`.
12
12
* (Optional) Resize the images and labels into (256, 256) resolution.
13
13
* To reduce the I/O bottleneck of dataloader, we stored data from all buildings in a single directory. The directory structure looks like:
0 commit comments