How to limit the SO(3) rotation in the training set? about augmentedautoencoder

[MartinSmeyer]

Hi @AminSeffo,

there is no option for that in the config file. But you can simply adapt those two lines and recreate the codebook:

AugmentedAutoencoder/auto_pose/ae/dataset.py

Lines 43 to 44 in 9f0a56f

	azimuth_range = (0, 2 * np.pi)
	elev_range = (-0.5 * np.pi, 0.5 * np.pi)

[AminSeffo]

Hey @MartinSmeyer,
thanks a lot for your response.
I will try it out, I think the main problem is the rotational symmetry of the detected part..

[AminSeffo]

Hi @AminSeffo,

there is no option for that in the config file. But you can simply adapt those two lines and recreate the codebook:

AugmentedAutoencoder/auto_pose/ae/dataset.py

Lines 43 to 44 in 9f0a56f

	azimuth_range = (0, 2 * np.pi)
	elev_range = (-0.5 * np.pi, 0.5 * np.pi)

I could not realize any changes after changing these two lines to :

        azimuth_range = (0, 2 * np.pi)
        elev_range = (-0.5 * np.pi, 0)

After that I executed the following lines:

- pip install .
- ae_train exp_group/my_autoencoder
- ae_embed exp_group/my_autoencoder

• What I need are only these three views in different combinations (orientations):

The left view, the right view and the top view as can be seen below:

[MartinSmeyer]

The visualization is for the training, but only the codebook/embedding is changed in these two lines. It doesn't hurt that the training still covers the whole pose space as long as the embedding only contains the correct poses. You can visualize the generated rotations using this function:

AugmentedAutoencoder/auto_pose/ae/dataset.py

Line 177 in 9f0a56f

def render_rot(self, R, t=None ,downSample = 1):

If you still want to change it for training as well, you need to change adapt the code here:

AugmentedAutoencoder/auto_pose/ae/dataset.py

Line 243 in 9f0a56f

R = transform.random_rotation_matrix()[:3,:3]

I don't bother much with specific poses, as this process needs to be repeated for every object and thus does not scale. But feel free to engineer it, it will probably give better results.

[AminSeffo]

@MartinSmeyer
thank you a lot. I will try to test it just as you explained.