API

Preprocessing

class davae.network.da_cvae.DAVAE(input_size, latent_size=16, batches=2, path='')

Bases: object

build()

compile()

embedding(x, batches, save=True, use_mean=True)

train(x, batch, loss_weights, batch_size=100, epochs=300, gpu=False)

class davae.network.da_cvae.GradReverse(*args, **kwargs)

Bases: tensorflow.python.keras.engine.base_layer.Layer

call(x)

This is where the layer’s logic lives.

Note here that call() method in tf.keras is little bit different from keras API. In keras API, you can pass support masking for layers as additional arguments. Whereas tf.keras has compute_mask() method to support masking.

Parameters

• inputs – Input tensor, or list/tuple of input tensors.

• **kwargs – Additional keyword arguments. Currently unused.

Returns

A tensor or list/tuple of tensors.

davae.network.da_cvae.grad_reverse(x)

davae.network.da_cvae.integration(adata_list, epoch=20, batch_size=256, latent_size=6, sparse=False)

davae.network.da_cvae.reverse_gradient(X, hp_lambda)

Flips the sign of the incoming gradient during training.

davae.network.da_cvae.sampling(args)

VIPCCA

class davae.network.da_vae.DAVAE(input_size, latent_size=10, batches=2, path='')

Bases: object

build()

compile()

embedding(x, batches, save=True, use_mean=True)

train(x, batch, loss_weights, batch_size=100, epochs=300)