Welcome to nn-blocks’s documentation!¶
A neural network library built from scratch, without dedicated deep learning packages. Training and testing deep neural networks and utilizing deep learning best practices for multi-class classification with fully connected neural networks, text generation with recurrent neural networks, and regression with fully connected networks.
Contents:
- nn-blocks
- activations module
- data_utils module
- grad_check module
- initializers module
- layers module
- losses module
- lr_schedules module
- metrics module
- models module
- opt_utils module
- optimizers module
- regularizers module
- test_activations module
- test_batch_normalization_layer module
- test_dense_layer module
- test_dropout_layer module
- test_initializers module
- test_losses module
- test_lr_schedules module
- test_metrics module
- test_models module
- test_opt_utils module
- test_optimizers module
- test_regularizers module
- text_utils module
- viz_utils module