Skip to main content

my version

This report contains the results of trained of a hyperparameter sweep for exploring a model designed for segmentation of 3D point cloud data. The runs are grouped by category to get an initial understanding of the dataset.
Created on December 7|Last edited on December 7

Section 1




Showing first 10 runs
050100150200Step0.20.40.60.8
123456789101112131415category0.000.020.040.060.080.100.120.140.160.180.20lr0.0000.0050.0100.0150.0200.0250.0300.0350.040lr_decay0.250.300.350.400.450.500.550.600.650.700.750.800.850.900.95iou

This report is a saved snapshot of Nick's research. He's published this example so you can see how to use W&B to visualize training and keep track of your work. Feel free to add a visualization, click on graphs and data, and play with features. Your edits won't overwrite his work.

Project Description

The goal of this model is to take input of a point cloud representing a real world object and provide segmentation of the object into different parts. 3D Semantic segmentation is a foundational problem of computer vision and has applications from self driving cars to medical diagnoses

Sweep: 2jt716r2
89


Section 2




Run set 1
55