carvana-pose

Pose estimation for carvana dataset

Data

I took all the Carvana data (everything they distribute as test and train for their image masking challenge) and adapted it for pose estimation by splitting it as follows:

Training: 3943 examples of each pose
Validation: 1315 examples of each pose
Test: 1314 examples of each pose

This corresponds to a 60/20/20 split between train/validate/test.

Example data

There are 16 poses for each car, evenly sampled across 360 degrees of yaw.

Here are some samples

Yaw 0

Yaw 5 (90 degrees)

Yaw 9 (180 degrees)

Yaw 13 (270 degrees)