tl.zoo

Custom keras.Model-creating functions that have shown to work well in specific use cases.

Supply these (or your own) to tl.Crested(...) to use them in training.

Submodules

utils

Model blocks, utility functions and custom layers for model building.

Functions

basenji(seq_len, num_classes[, ...])	Construct a Basenji model.
borzoi(seq_len, num_classes[, ...])	Construct an fully replicated Borzoi model.
borzoi_prime(seq_len, num_classes[, ...])	Construct an fully replicated Borzoi Prime model.
deeptopic_cnn(seq_len, num_classes[, ...])	Construct a DeepTopicCNN model.
deeptopic_lstm(seq_len, num_classes[, ...])	Construct a DeepTopicLSTM model.
dilated_cnn(seq_len, num_classes[, ...])	Construct a CNN using dilated convolutions.
dilated_cnn_decoupled(seq_len, num_classes)	Construct a CNN using dilated convolutions with a separate dense head per output class.
enformer(seq_len, num_classes[, ...])	Construct an fully replicated Enformer model.
simple_convnet(seq_len, num_classes[, ...])	Construct a Simple ConvNet with standard convolutional and dense blocks.