luis-armando-perez-rey / lsbd-vae Goto Github PK

If I have 8 3D models with 6 possible colors I should get 48 identities times 6 random walk steps I should get 288 images. When using batch_size of 5 I am getting 270 images. I don't have problem if the batch size is 6.

EDIT: Turned out it was not a bug. It was behaving as expected. I will leave this issue because it is important to know that the data loader is fine.

To increase training stability we should:

• Remove the use of sigmoid in the decoding neural networks
• Change the Bernoulli loss to use logits

Add dataset class that takes all possible combinations of the changing factors and creates randomly grouped data with the changing factors for each identity.

• Create jupyter notebook that trains semi-supervised
• Create jupyter notebook that trains supervised with paths
• Create jupyter notebook that shows how to calculate metric
  Important! Don't forget to push notebooks to the repository without the outputs!!!!

• Loading of data
• Training of models
• Reproduce arrow dataset experiments
• Reproduce pixel dataset experiments
• Reproduce airplane dataset experiments
• Reproduce modelnet dataset experiments
• Reproduce coil dataset experiments

• Add LSBD-VAE metric module torus
• Add LSBD-VAE metric module cylinder
• Add documentation to LSBD-VAE metric functions
• Add testing scripts for LSBD-VAE metric torus
• Add testing scripts for LSBD-VAE metric cylinder

RandomWalkIdentities subclass that can create a tf.data.Dataset that outputs a random walk for each element in a list of combinations of, e.g. colors and 3D models corresponding to the identities of the objects.

• Dependencies
• Explanation on how to run code
• Images
• Citation
• Add contacts

• Loading of data
• Training of models
• Reproduce arrow dataset experiments
• Reproduce pixel dataset experiments
• Reproduce airplane dataset experiments

Add class to load a tf.data.Dataset from a dataset of multiple factors. Similar to RandomWalkFactor dataset but each datapoint provided as output by dataset is of shape (num_identities, nfactors1, nfactors2, ... nfactorsN, *image_shape) where num_identities represents a certain object identity which can be defined by the user based on certain factors e.g. object shape and color.

Such dataset is important to evaluate DLSBD metric since this metric requires embeddings to be organized as (n_identity, nfactors1, ..., nfactorsN, latent_dim).

Add code that can take images with shape (n, h, w, d) and factors with shape (n, n_factors) and produce batches of images that can be used by an LSBDVAE

Add subclass of SupervisedLSBDVAE where embeddings of an Euclidean latent space get pushed together based on certain object identity.

There are some calls to architectures that we don't use in the LSBDVAE project