Downloads · 30 days
0
s23dr-hoho-competition
Siromanec/s23dr-hoho-competition
s23dr-hoho-competition is a machine learning model from Siromanec. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
The model is an improved version of the handcrafted solution. The main components are 2D vertex and edge detection and depth estimation. Edge detection consists of basic connected components analysis with additional c…
Access
Public
Updated Jun 14, 2024
Repo size
239 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.ipynb170 MB · 71%
At a glance
- License
- mit
- Access
- Public
- Created
- May 24, 2024
- Updated
- Jun 14, 2024
- SHA
- e135556a
Datasets
Model card
From the Hugging Face model README
s23dr-hoho-competition
The model is an improved version of the handcrafted solution. The main components are 2D vertex and edge detection and depth estimation. Edge detection consists of basic connected components analysis with additional checks for connection validity. In this solution the pointcloud is used to estimate depth using the mean depth of n closest projected points.
(THIS IS NOT THE WRITEUP)
See the notebooks for additional visuals
Commit messages are mostly identical to the ones in the evaluation submitions, so getting the best soulution is a matter of reverting to that commit
- License
- mit
- Created
- May 24, 2024
- Updated
- Jun 14, 2024